What are the main sources of error in conducting an experiment. Of particular importance is the correct development of experimental techniques. Questions for self-control and discussion

General principles of experimental design

Comparison.

Randomization.

Replication.

Uniformity.

Stratification.

factor levels

Title: General principles of experimental design
Detailed description:

Since its inception, science has been looking for ways to understand the laws of the surrounding world. Making one discovery after another, scientists rise higher and higher on the ladder of knowledge, erasing the boundary of the unknown and reaching new frontiers of science. This path lies through experiment. By consciously limiting the infinite diversity of nature within the artificial framework of scientific experience, we transform it into a picture of the world understandable to the human mind.

Experiment as scientific research is the form in which and through which science exists and develops. The experiment requires careful preparation before it is carried out. In biomedical research, design of the experimental part of the study is especially important due to the wide variability of properties characteristic of biological objects. This feature is the main reason for the difficulties in interpreting the results, which can vary significantly from experiment to experiment.

Statistical problems justify the need to choose an experimental design that would minimize the influence of variability on the scientist's conclusions. Therefore, the goal of experimental design is to create the design necessary to obtain as much information as possible at the least cost to complete the study. More precisely, experimental planning can be defined as the procedure for selecting the number and conditions for conducting experiments that are necessary and sufficient to solve a given problem with the required accuracy.

Experimental design originated in agrobiology and is associated with the name of the English statistician and biologist Sir Ronald Aylmer Fisher. At the beginning of the 20th century, at the agrobiological station in Rothamsted (UK), studies began on the effect of fertilizers on the yield of various varieties of grain. Scientists were forced to take into account both the great variability of the research objects and the long duration of the experiments (about a year). Under these conditions, there was no other way but to develop a well-thought-out experimental design to reduce the negative impact of these factors on the accuracy of the conclusions. By applying statistical knowledge to biological problems, Fisher came to develop his own principles of statistical inference theory and pioneered the new science of design and analysis of experiments.

Ronald Fisher himself explained the basics of planning using the example of an experiment carried out to determine the ability of a certain English lady to distinguish what was poured into a cup first - tea or milk. It should be noted that for real English ladies it is important that tea is poured into milk, and not vice versa, a violation of the sequence will be a sign of ignorance and will spoil the taste of the drink.

The experiment is simple: the lady tries tea with milk and tries to understand by taste in what order both ingredients were poured. The design developed for this study has a number of properties.

Comparison. In many studies, precise determination of the measurement result is difficult or impossible. So, for example, a lady will not be able to quantify the quality of tea; she will compare it with the standard of a properly prepared drink, the taste of which has been familiar to her since childhood. Typically, in a scientific experiment, an object is compared either with some predetermined standard or with a control object.

Randomization. This is a very important point in planning. In our example, randomization refers to the order in which the cups are presented for tasting. Randomization is necessary to enable the use of statistical methods to analyze study results.

Replication. Repeatability is a necessary component of setting up an experiment. It is unacceptable to draw conclusions about the ability to determine the quality of tea from just one cup. The result of each individual measurement (tasting) carries with it a share of uncertainty arising under the influence of many random factors. Therefore, multiple tests must be performed to identify the source of variability. The sensitivity of the experiment is associated with this property. Fisher noted that until the number of cups of tea exceeds a certain minimum, it is impossible to draw any clear conclusions.

Uniformity. Although it is necessary to repeat measurements (replication), their number should not be too large so that homogeneity is not lost. Temperature differences between cups, dulling of taste, etc., when a certain limit number of repetitions is exceeded, can make it difficult to analyze the results of the experiment.

Stratification. Going beyond the example of R. Fischer to a more abstract description of the experimental design, one can additionally indicate such a property as stratification (blocking). Stratification is the distribution of experimental units into relatively homogeneous groups (blocks, layers). The stratification procedure allows us to minimize the effect of non-random sources of variability known to us. Within each block, the experimental error is assumed to be smaller compared to the option with random selection for the experiment of the same number of objects. For example, when researching a new drug, we have two levels of factor - “drug” and “placebo”, which are prescribed to men and women. In this case, gender is a blocking factor by which the subjects being studied are divided into subgroups.

The characteristics of an experimental design described above apply in whole or in part to any scientific experiment. However, to get started, knowledge about the general properties of the study is not enough; more thorough preparation is required. It is impossible to create a detailed guide in one article, so the most general information about the stages of experiment planning will be presented here.

Any research begins with setting a goal. The choice of problem to study and its formulation will influence both the design of the study and the conclusions that will be drawn from its results. In the simplest case, the problem statement should involve the questions “Who?”, “What?”, “When?”, “Why?” And How?".

An illustration of the importance of this planning stage is a study that collected information on road traffic accidents. Depending on the goal setting, work can be aimed at developing a new car or a new road surface. Although the same data set is used, the problem statement and conclusions differ significantly depending on the problem formulation.

After choosing the goal of the work, the so-called dependent variables should be determined. These are the variables that will be measured in the study. For example, indicators of the functioning of certain systems of the human body or laboratory animals (heart rate, blood pressure, enzyme content in the blood, etc.), as well as any other characteristics of research objects, changes in which will be informative for us.

Since there are dependent variables, there must also be independent variables. Another name for them is factors. The researcher operates with factors in an experiment. This could be the dose of the drug being studied, the level of stress, the degree of physical activity, etc. The relationship between the factor and the dependent variable is conveniently represented using a cybernetic system, often called a “black box”.

A black box is a system whose operating mechanism is unknown to us. However, the researcher has information about what happens at the input and output of the black box. In this case, the output state functionally depends on the input state. Accordingly, y1, y2, ..., yp are dependent variables, the value of which depends on factors (independent variables x1, x2, ..., xk). The parameters w1, w2, ..., wn represent disturbances that cannot be controlled or change over time.

In general, this can be written as follows: y=f(x1, x2, ..., xk).

Each factor in an experiment can take one of several values. Such values ​​are called factor levels. It may turn out that a factor can take on an infinite number of values ​​(for example, the dose of a drug), but in practice several discrete levels are selected, the number of which depends on the objectives of a particular experiment.

A fixed set of factor levels determines one of the possible states of the black box. At the same time, these are the conditions for conducting one of the possible experiments. If we enumerate all possible sets of such states, we will obtain a complete set of different states of a given system, the number of which will be the number of all possible experiments. In order to calculate the number of possible states, it is enough to raise the number of factor levels q (if it is the same for all factors) to the power of the number of factors k.

The set of all possible states determines the complexity of the black box. Thus, a system of ten factors at four levels can be in more than a million different states. Obviously, in such cases it is impossible to conduct a study that includes all possible experiments. Therefore, at the planning stage, the question of how many experiments and which ones are necessary to be carried out to solve the problem is decided.

It should be noted that the properties of the object of study are essential for the experiment. Firstly, we need to have information about the degree of reproducibility of the results of experiments with a given object. To do this, you can conduct an experiment, and then repeat it at irregular intervals and compare the results. If the spread of values ​​does not exceed our requirements for the accuracy of the experiment, then the object satisfies the requirement of reproducibility of results. Another requirement for an object is its controllability. A controlled object is an object on which an active experiment can be conducted. In turn, an active experiment is an experiment during which the researcher has the opportunity to select the levels of factors of interest to him.

In practice, there are no fully managed objects. As mentioned above, a real object is affected by both controllable and uncontrollable factors, which leads to variability in results between individual objects. We can separate random changes from regular changes caused by different levels of independent variables only with the help of statistical methods.

But statistical methods are effective only under certain conditions. One of these conditions is the requirement of a certain minimum sample size used in the experiment. Obviously, the wider the range of changes in characteristics from object to object, the greater the repetition of the experiment, i.e. the number of experimental groups, should be.

Since an unreasonably large number of trials will make the study too expensive, and an insufficient sample size may compromise the accuracy of the conclusions, determining the required sample size plays a critical role in experimental design. Methods for calculating the minimum sample size are described in detail in the specialized literature, so it is not possible to present them in the article. However, it should be mentioned that they require a preliminary determination of the average value of the indicator under study and its error. The source of such information can be publications about similar studies. If they have not yet been carried out, then there is a need to perform a preliminary “pilot” study to assess the variability of the trait.

The next step in designing experiments is randomization. Randomization is a process used to group subjects so that each has an equal chance of being assigned to a control or treatment group. In other words, the selection of study participants must be random so that the study is not biased toward the researcher's “preferred” outcome.

Randomization helps prevent bias due to reasons that were not directly taken into account in the experimental design. For this purpose, for example, the formation of experimental groups of laboratory animals is carried out randomly. However, complete randomization is not always possible. Thus, clinical trials involve patients of a certain age group, with a predetermined diagnosis and severity of the disease, and, therefore, the selection of participants is not random. In addition, so-called “block” experimental designs limit randomization. These designs imply that selection into each block is carried out in accordance with certain non-random conditions, and random selection of study subjects is possible only within blocks. The randomization process is easy to implement using specialized statistical software or special tables.

In conclusion, it is necessary to say about the need to take into account in the research plan, in addition to the requirements of medicine and statistics, also moral and ethical standards. We should not forget that not only people, but also laboratory animals must be involved in the experiment in accordance with ethical principles.

1. The formulated hypotheses do not reflect problematic situations or significant dependencies in the object being studied.

2. To incorrect empirical interpretation of variables, to the selection of inadequate indicators.

3. Mistakes were made when forming experimental and control groups. During the experiment, a significant difference between the groups was discovered, which raised doubts about the possibility of comparing these groups in terms of the composition of variables.

4. For the experimental one, a factor is identified as an independent variable that cannot be the cause, a stable determinant of the processes occurring in the phenomenon being studied.

5. The relationships between the dependent and independent variables are random. The variable structure is incorrectly set.

6. Errors were made in the preliminary description of objects, which made it difficult for the group to select a control group.

7. The effect of side factors cannot be neutralized; it is difficult to create an experimental situation.

8. A sufficient level of measurement and control over the state of variables is not provided.

9. When analyzing the data, a logical-mathematical apparatus was used, which is not applicable to the class of phenomena being studied.

10. When analyzing the results of an experiment, the sociologist overestimates the impact of the independent variable on the dependent variable and underestimates the influence of a number of random factors on changes in the experimental situation.

11. Among the organizers of the experimental work were people who were not interested in the positive results of the experiment.

12. During the experiment, conflicts arose among the participants regarding participation in the experiment.

13. The team refuses to take part in the experiment, motivating their refusal by the fact that they had previously had to participate in the experiment, and this participation did not bring anything but unnecessary worries.

As J.J. writes Davis, advertisers conduct experiments to determine how various actions ("independent variables") affect consumer attitudes, opinions, and behavior (dependent variables). Experiments help them find answers to questions regarding the introduction of a new product, its packaging, advertising content, advertising mix and advertising costs. In general, many research methods are purely descriptive (for example, the observation method discussed earlier). They provide an opportunity to take a “snapshot” of the market situation. “However, it happens that decision makers in the advertising business need more than just a description. Situations arise when it is necessary to understand how changes in advertising conditions, the structure of a product and its meta on the market affect the formation of attitudes, opinions and behavior or the positioning of a product in the market. This can be found out through experimental research, in which the researcher changes or transforms something in the environment of the consumer or product in order to find out what will happen.” So, this method involves changing one or more parameters and monitoring changes in other parameters that depend on the first. During the experiment, the researcher tries to find out causally-investigative connections between different factors influencing events, facts, phenomena, processes.

From the point of view of S.V. Veselov, in relation to advertising activities, this can be anything, for example, determining the degree of impact on the effectiveness of an advertising campaign by changing advertising products or advertising placement compared to the previous advertising campaign, or differences in perception by the target audience in the case of replacing one actor with another in an advertising video (options - replacing the slogan, advertising campaign style, ad design, etc.), or choosing a media channel among several, or the degree of influence of advertising intensity on sales of advertised products, etc. For example, if there are two TV spots for one campaign, then an experiment is carried out in different versions:

1) roller A is used;

2) roller B is used;

3) both videos A and B are used at once. Subsequent comparison of the results obtained allows us to draw conclusions about the real choice of priorities.

Components experiment:

1) dependent a variable is what the researcher is trying to explain; it is a criterion used to evaluate the influencing effect of an independent variable (for example, behavior and attitude when purchasing a product); it is a factor that changes under the influence of another factor. Thus, a dependent variable is a factor whose change is determined by the independent variable.

2) independent The (experimental) variable is what the researcher uses to explain the observed (during the experiment) changes in the dependent variable; it is something that changes during an experiment to affect the change in the dependent variable (effect). The independent variable (in relation to the dependent variable) is advertising exposure. The independent variable must be chosen in such a way that it can be easily observed or measured numerically to fix the intensity. In an experiment, only the independent variable is artificially changed, and the dependent variable changes as a response (consequence, consequence). Thus, the variable, direction or intensity of action, which is determined by the sociologist in accordance with a pre-developed program, is called a controlled (controlled) variable. For example, by varying the amount of exposure to an advertisement, we can learn how much it affects awareness or recall of the advertising message.

Experiment mechanism:

By identifying the interaction of the dependent and independent variables, we identify cause-and-effect relationships: manipulating the independent variable (“cause”) leads to changes in the dependent variable (“effect”), which allows us to draw appropriate conclusions (it is known that some factors act more strongly than others ; some – directly, others – indirectly, etc.). In either case, the advertising researcher manipulates and observes the effects of one, two, or more independent variables in an experiment.

Criteria for establishing a cause-and-effect relationship:

1. Events must occur in the appropriate order (manipulation of the independent variable must precede evaluation of the results). Cause and effect can be confused. For example, you increased the number of advertising messages, consumer awareness increased (your measurements recorded this) and at the same time the number of people buying the advertised product increased. On the one hand, the cause-and-effect series looks exactly like this. But we can offer another explanation for the simultaneity of all these events: people first purchased the product, and only then began to pay more attention to the advertising of this product.

2. The cause must be statistically related to the effect (effect): cause and effect must occur or replace each other at the same time.

3. Alternative explanations should be kept to a minimum. This criterion directly affects the internal validity of the experiment. Typically, the strict consistency and consistency of an experiment precludes alternative interpretations. However, there are always several factors that influence validity. The level of validity affects the degree to which the researcher is confident that there is a cause-and-effect relationship between the experimental manipulation (with the independent variable) and the results of the experiment. Typically, the level of validity decreases (may decrease) due to the following “threats”: interviews with respondents on the eve of the experiment or at the beginning of the experiment affects the perception and behavior of the subjects, background influence (You want to know the reaction of soft drink consumers to a new advertisement, and you are testing it in a very hot or cold weather - a distortion of the usual), instrumental error (during the experiment, the method of recording data was changed and now it is impossible to understand what to attribute the changes in the behavior of respondents to - a change in the independent variable or a change in recording methods, methods of data collection), incorrect selection of control or experimental groups respondents, etc.

To improve the quality of the experiment, at least two separate groups of respondents are usually involved:

1) a control group, whose members are not subject to experimental manipulation, serves as the basis for comparison with data from the experimental group;

2) an experimental group, the members of which, for example, are not only presented with a TV commercial, but also create other conditions for perceiving the advertising message, or include elements of change in the TV commercial, etc.

One way to test radio and television commercials (which is related to the forecasting techniques discussed in previous chapters) is to Schwerin test. The test is that a potential buyer is given the opportunity to choose a product from one of the brands from a list as a prize. After these people are shown the ad, they are again asked to select products from the same list. Any changes in brand selection will be attributed to advertising. A special trailer is also used where department store shoppers are invited to view the advertisement and then interviewed about their reaction to it. In the case of print advertising, advertising magazines may be distributed to a number of randomly selected houses. Housewives are persuaded in various ways to look at magazines and then describe their reaction to the advertisements.

Goals experimental audience method may be: modeling the behavior of potential consumers in a situation of free choice; identifying the peculiarities of perception of advertising products; study of stereotypes of individual consciousness. Several groups of consumers are selected for a comparative experiment. Next, changing and constant categories in the product or in the behavior of the subjects are identified and methods for recording the dynamics of variables are selected (this can be methods of objective registration of a person’s functional states, such as GSR, myogram, the method of evoked potentials, as well as oral reports of the subjects or the results of observation by the experimenter). What is important here is the choice of method for analyzing the obtained experimental data and their interpretation.

J.J. Davis gives the following example of a factorial experimental design. Factorial design is an experimental technique that simultaneously measures the effect of two or more independent variables (each having multiple levels) on one or more dependent variables. Factorial designs examine main effects and interactions. The main effect is the separate effect of each independent variable on the dependent variable. An advertising campaign was conceived, everything was agreed upon, but two questions remained stuck: who would represent the campaign in a TV commercial (an ordinary person or a celebrity) and what should be the tone (manner) of presenting the video.

The following objectives of the experimental study emerged: What effect will the replacement of the company “representative” (celebrity-ordinary person) have? What will be the effect of changing the tone (manner) of the video? What would be the effect of replacing both at the same time? In this example, the main effects are: 1) company spokesperson (two levels: celebrity or ordinary person) and tone (two levels: humorous or serious). The consequence of the combined effect of independent variables on the dependent variable will be their interaction. An interaction occurs when the combined (emergent) effect of two or more independent variables differs from the arithmetic (mechanical) sum and independent effects. (The third question is the goals of the experiment). Two experiments randomly selected a sample of 240 people. They were divided into 4 groups of 60 people; Each respondent was shown one commercial. The following distribution was obtained (factors and number of respondents in one table cell):

Respondents in the top left cell are shown a funny advertisement featuring a celebrity, while those in the bottom right cell are shown a serious advertisement featuring an ordinary person. After watching the TV commercial, all data (recorded reactions of respondents - dependent variable) are averaged (average degree of persuasiveness for each factor):

Thus, statistical analysis of the obtained data recorded that none of the main effects is significant (2.4 ~ 2.1 and 2.2 ~ 2.1). However, the data indicated a significant interaction effect (2.7 is significantly larger than all other options). Hence the general conclusion: in themselves (independently of each other) the participation of one or another representative (be it a celebrity or an ordinary person) and the tone of the TV commercial (humor or seriousness) do not affect the persuasiveness of the advertising message, however, together both of these factors can have an impact significant influence.

A. Kutlaliev and A. Popov give the example of CFX (Controlled Field experiment), which is considered the most reliable method for determining the advertising budget.

Scheme of a possible CFX experiment (stages, types of work):

1) the main independent variable is advertising costs;

2) the main dependent variable is sales volume;

3) additional dependent variables - awareness, knowledge, attitude, intentions to buy a product, etc.;

4) time of influence of the independent variable - 12 months (the effect of advertising appears within several months, so planning the experiment should begin long before the approval of the advertising budget);

5) measurement interval – 14 months (in addition, it is advisable to have time series of sales at your disposal to calculate trends and seasonality);

6) the number of UPE subjects - 5-10 local markets per level of advertising budget (the local market of the regional center of Tver is the city itself and the 20-30-kilometer zone around it);

7) at least 3 levels of budget management - for example, 75%, 100% (control), 150%;

11) influence on various markets (Moscow - St. Petersburg, cities with a population of over a million, regional centers, markets with different consumer potential, etc.);

It should be noted that the experiment is widely used in psychology advertising. Here are some examples.

Model of an ideal advertisement. In 1997, the Psychological Agency for Advertising Research (PARI) attempted to develop a model of the “psychologically ideal advertisement.” For this, 100 identical issues of the then popular advertising newspaper “Extra M” were used (99 pages of text) and 100 subjects were involved. The experiment involved studying voluntary and involuntary perception (also memory and attention). All advertisements were numbered, and at the first stage of the study, subjects were asked to: leaf through the newspaper at a certain speed, indicate those advertisements that attracted their attention in the first place. Then the subjects were asked to find some small advertisements on individual pages, but to describe in detail only those that spontaneously caught their eye. Result: the most effective ad turned out to be a strictly defined type: this is a small text with graphics, occupying approximately 1/4-1/8 of the entire advertising module, surrounded by an empty white blank field. By the way, advertisers who were asked to place such advertisements reacted extremely negatively to such “unconvincing” offers; besides, they did not want to “pay money for emptiness, but wanted to “save money.” Another important aspect: recommended advertisements appeared on the pages of the newspaper quite rarely, but if they began to appear often enough, then - according to the laws of perception - sooner or later the psychological effect of such models would be zero. Thus, it is necessary to fully emphasize not only the need for fundamental research, but also the importance of short-term research, which fixes the status quo and allows one to correctly navigate the constantly changing marketing environment.

Study of the features of suggestion in television advertising. In 1997, at the Psychological Agency for Advertising Research D.A. Sudak studied the dynamics and some features of suggestion in the form of repeatedly and continuously repeated advertising. As stimulus material, groups of subjects were continuously presented with two commercials with high (advertising for Shock chocolate - to one group) and low (advertising for Faindale cheese - to another group) dynamics (frame rate, rate of speech of the announcer, etc.). The results of objective effects were compared (galvanic skin response according to the method of V.V. Sukhodeev). It was revealed that a video with low dynamic characteristics caused emotional satiety in the subjects only after 7-8 presentations of the stimulus material, while in the case of a video with high dynamic characteristics it appeared already 3-4 times. Moreover, after the experiment, the subjects of both groups did not note any appetite; on the contrary, the presentation of videos above a certain norm began to cause irritation, verbal aggression, fatigue, and disgust. The conclusion was drawn: repeated and continuous presentation of various advertising videos above a certain norm does not provide the desired psychological effect, but, on the contrary, causes a defensive reaction and even rejection. The economic effect of the impact of videos (if they are shown multiple times) is manifested in phenomena of a different order: the interested audience expands, memorability and subsequent recollection increase, etc.

Studying the method of persuasion in advertising. In 1998, at the Psychological Agency for Advertising Research O.N. Popova conducted an experiment to test the hypothesis: which television commercials (directly addressed to the viewer or presented in the form of a dialogue between characters) have a greater persuasive effect. A battery of clips was constructed based on monologues and dialogues (5 clips for each situation). Two groups of 30 subjects each were presented with stimulus materials of the first and second categories. The evaluation of the videos was carried out using the semantic differential method. The study found that of the 15 characteristics assessed, dialogue-based materials received 70% positive ratings. They seem to the subjects less intrusive, more convincing, understandable, interesting, original, energetic, and truthful. Conclusion: advertising based on a direct appeal to the viewer, trying to convince him of the need to purchase a product, can be rated much lower and is more often rejected by the viewer.

Simulation of “25 frames” technology. L. Volkova and S. Sergeev in 1998 studied the mechanism of viewers’ perception of hidden information. Two groups of subjects were offered a plot (20 seconds) depicting a seascape against the backdrop of the rising sun. At the same time, when showing the plot, one of the groups inserted, using the “25th frame” technology, an abstract figure symbolizing the name of the travel agency, and a meaningless word (“KITAN”, “FATUR”, etc.), symbolizing the name of this travel agency. The inserts (logo and title) were presented for a very short time in the middle of the story. After watching, the experiment participants completed two tasks: they chose one from 8 names, one from 8 logos (in the opinion of the subjects, the most suitable for a travel agency). Result: the first group of subjects, who were presented with a plot without inserts, chose the logo and the word almost in random order; The second group of subjects, for the most part, chose the stimulus logo and word (or something similar to them). Conclusion: inserts like “25th frame” influence the viewer in a certain way, but only on the motivation of the choice; they are perceived as some kind of hint, but are not able to directly influence the will of the viewer; Basically, those people who have problems in the area of ​​independent decision-making are dependent on such tips.

Annex 1

K.A. Jafarov. Lecture course « Research in advertising»

Characteristics carrying out the experiment. Every experiment consists of four main steps: determine what exactly needs to be learned, take appropriate actions (conduct the experiment), observe the effect and consequences of these actions on other variables, determine to what extent the observed effect can be attributed to the actions taken.

Components of the experiment. At a minimum, there must be one dependent variable, one independent variable, and a manipulation. The dependent variable is what the researcher is trying to explain. The independent variable is what is used to explain changes in the dependent variable. Manipulation is changing the values ​​of an independent variable.

Requirements for establishing causation. To establish such a connection, i.e. to answer the question “is the change in the dependent variable related to manipulations with the independent variable?”, it is necessary to adhere to three criteria: events must occur in the appropriate order, the cause must be statistically related to the effect (cause and effect occurred or replaced each other at the same time time), alternative explanations should be kept to a minimum. The third criterion is the most important, since it affects internal validity(BB) experiment. BB refers to the extent to which alternative explanations can be eliminated. The more the advertiser manages to prove that it was the manipulation of the independent variable that caused the changes in the dependent variable, the higher the level of explosives of the experiment. The following factors influence IV: preliminary measurement, interaction, background influence, natural development, instrumental error, selection, dropout. The presence of such threats reduces the likelihood that research-based decisions will be correct.

1. Preliminary measurement and interaction.

The threat of premeasurement occurs when the conversation conducted at the beginning of the experiment directly affects the actions and behavior of the respondent. An interaction threat occurs when the conversation conducted at the beginning of the experiment increases the respondent's sensitivity and receptivity to the effects of the independent variable.

2. Background influence. Background - events and influences that take place in an experiment, in addition to those actions that the researcher purposefully manipulates, and potentially influence its outcome, as measured by the dependent variable. A threat arises under circumstances beyond our control.

3. Natural development. This threat arises when, during the experiment, respondents may become tired, hungry, thirsty, or lose interest in the study.

4. Instrumental error. This refers to changes in the testing of measuring instruments (questionnaires) or methods of recording data.

5. Selection and elimination. Such threats have to do with the composition and characteristics of the groups participating in the experiment. The experiment usually involves two groups: experimental And control. The control group is not manipulated. A selection threat arises when the characteristics of the two groups differ before the experiment begins. The threat of dropout arises when the characteristics of groups differ in important demographic characteristics, attitudes, and behavior; and also by its initial level in relation to the dependent variable, or by its likely susceptibility to the influence of the independent variable.

Now let's talk about plan experiment. First about quasi-experimental designs(false experiments). There are various options for such plans.

1. Single-group, posttest design:

Group 1. Exposure → Final testing. Disadvantages of this design: the researcher must rely on his own judgment when interpreting the results, there is no control group (the threat of background influence), and it is impossible to control for some threats (natural development, selection and attrition).

2. Single-group, pre-posttest design:

Group 1. Pre-testing → Exposure → Final testing. This plan is often used when testing the price of a product, packaging of a product, response to advertising). Disadvantages of the plan: It cannot be said with certainty that the differences in the levels of pre-test and post-test are caused by the advertising campaign.

Now about plans for true experiments. This is where the control group comes in. In addition, participants in these groups are randomly selected. Random selection makes it possible to control many of the explosive threats. These plans are more expensive but provide more information. Types.

1. Simulated plan with pre-test and post-test.

The plan is designed to control pre-measurement and interaction threats:

Group 1 (Random selection). Preliminary testing

Threats of pre-measurement and interaction are eliminated because pre-test and post-test are conducted on different individuals. But, there is the possibility of other threats (background influence, natural development, instrumental error, selection).

2. Design with posttest and control group. This design differs from the previous one in how the effect of the intervention (manipulation) is measured. In the previous plan, the grade is determined by comparing the results of the pretest and posttest. Here, the assessment is carried out by comparing the results of two final measurements (in different groups):

Group 1 (Random selection). Final testing

Group 2 (Random selection). Impact → Final testing.

3. Two groups - four dimensions: design with pretest, posttest and control group:

Group 1 (Random selection). Pre-testing → Impact → Final testing.

Group 2 (Random selection). Preliminary testing → Final testing.

This design is used when it is necessary to obtain direct evidence of equivalence between groups before experimental intervention, or when there is doubt about the degree of equivalence between groups.

4. Four groups - six dimensions: Solomon's plan with four groups.

The plan is the most effective, but also the most resource-intensive. Efficiency is ensured by the ability to control all threats:

Group 1 (random selection). Pre-testing → Impact → Final testing.

Group 2 (random selection). Preliminary testing → Final testing.

Group 3 (random selection). Impact → Final testing.

Group 4 (random selection). Final testing.

Appendix 2

Using a modeling experiment in marketing research (E. Ivanova)

In a situation where it is necessary to understand the reasons for choosing a particular product, the hidden motivational factors influencing the perception of advertising or a new product, to find the right “entry points” when developing a company’s communication strategy, the goal of which is to “conquer” the consumer, such methods are almost irreplaceable. Only they make it possible to reveal the underlying motives of behavior, which are often not realized by consumers themselves, and to neutralize the phenomenon of “social desirability” (the tendency to give “correct” answers approved by society to questions in a traditional questionnaire).

One of the most effective psychological methods is a modeling experiment - the reproduction in the form of a role-playing game of individual elements of a market situation: the consumer’s choice of goods and services, his decision to purchase, the situation of making a purchase of a product, the perception of advertising, etc. The main advantages of the method are the possibility study the behavior of representatives of various social groups in situations as close as possible to reality, as well as model new situations in accordance with the specifics of research tasks.

The simulation experiment is based on a role-playing game. From the point of view of solving marketing research, the resources of role-playing games are of interest, which significantly expand and complement the capabilities of other related methods used in marketing research (for example, the focus group method): creating a situation as close as possible to real conditions in the market; the ability to see patterns of behavior that people cannot describe in words; the ability to directly observe the reaction of experiment participants to certain events or arguments; the opportunity to obtain more comprehensive information about the hidden motives of consumer behavior; the ability to identify and formulate (i.e. bring to the level of consciousness) arguments in favor of one or another behavioral strategy and assess the degree of their influence on consumers; predictive capabilities of a modeling experiment, allowing you to “predict” consumer behavior.

Option No. 1. “Design" It is used in a situation where it is necessary to develop a communication campaign strategy or an image positioning strategy. The participants in the role-playing game include representatives of the target audience for whom the communication campaign is designed (for example, if the task is to develop an image positioning strategy for an insurance company, then the participants in the modeling experiment are consumers of insurance services). The number of participants in the role-playing game is from 20 to 30 people. All participants are divided into three teams: one team of the jury and two teams of “designers”.

Teams of “designers” are tasked with developing a campaign strategy (main creative idea, key messages, PR campaigns, etc.). Next, the jury evaluates the proposed company options and the winner is awarded. As a result, the method allows us to identify expectations from a communication campaign, understand what the consumer primarily pays attention to when choosing a particular type of product or service, and find the most effective methods of influencing the consumer. In our practice, this type of modeling experiment was used to develop an image positioning strategy when launching a new brand of chocolate candies in the premium segment. Two strategy options were developed. A modeling experiment was used as a tool to test both strategy options for the comparative effectiveness of key messages that trigger consumer behavior, as well as to clearly demonstrate to the Customer their impact on members of the target audience.

According to the scenario, two teams of strategy developers presented to a jury consisting of representatives of the target audience their own concept of a new brand and its leading attributes (brand values, its name, logo and slogan), as well as key positioning ideas (main advertising ideas, characters brand, etc.). Representatives of target audiences from among regular customers (who make a purchase at least once every two weeks) took part in the experiment. Based on the results of the analysis, information was obtained on the following parameters of consumer choice: Leading values ​​and needs associated with the use of this type of product (premium segment chocolates). Leading criteria for evaluating this type of product. Criteria for choosing a new product on the market. Criteria for maintaining loyalty to “old” brands and/or abandoning them (customer flow channels). The most effective key messages for an advertising campaign.

Option number 2. “Debate”. This version of the modeling experiment is used in a situation where it is necessary to develop a competitive strategy and demonstrate advantages compared to other market participants. All participants in the role-playing game are divided into opposing teams and a jury. According to the scenario, a situation is simulated in which teams of rivals are forced to convincingly prove their position when choosing a particular product or service (why do I prefer “this?”) For example, teams of supporters of different brands of cars, clients of different banks, supporters of different forms of leisure time collide etc. Next, the main parameters of the situation are set (the need to present the product at an exhibition, prove your point of view in a television show, etc.). After team representatives present the benefits of a particular product or service, debate begins between the participating teams. Based on the results of the competition, the jury awards the winning team. The game allows you to understand the underlying motives of consumer behavior and identify hidden, latent criteria for choosing goods and services. This option can be used not only in marketing research, but also to assess the mechanisms of political preferences of voters, as it allows us to identify the hidden springs of electoral choice.

This version of the modeling experiment was used by IMA Consulting to reposition the brand in the mid-priced juice market. The task was to identify during the experiment the strong and weak characteristics of the client’s brand, as well as two brands actively competing with it; determine the leading qualities that determine the choice of product in the market in question. A situation was simulated where group participants needed to convince a group of “new” buyers to make a choice in favor of one of three brands analyzed in the experiment. The groups of participants were formed from among loyal consumers of the three brands under study, as well as consumers who do not have strong preferences for the type of product in question.

Experimental technique

An experimental technique is a set of methods and techniques for conducting it. The methodology that applies to the entire study is general. For individual experiments within this study, additional private methods may be created. The importance of particular methods increases with the increase in the variety of phenomena to be studied.

The experimental research methodology determines the equipment, the number of experiments, the work plan, the cost of time and money.

Building the right methodology allows you to obtain the expected results from the experiment in the shortest possible time and with minimal environmental and labor costs and avoid the appearance of unnecessary experimental data from which no conclusions can be drawn.

The experiment can be carried out in a passive form (observation without interfering with the conditions for the development of a phenomenon) and active (creation of certain conditions for the development of a phenomenon).

Passive observation is used primarily for preliminary testing of the general correctness of the working hypothesis and establishing the direction of development of the phenomenon. During passive observation, the researcher records various parameters of interest that characterize the phenomenon. A variety of measuring instruments are used for registration. Passive observation can be alternated with active observation.

Observation becomes active when the researcher himself determines the conditions for the development of a phenomenon in the desired direction in order to obtain clear patterns.

The first stage of active observation is search experiments. The purpose of the exploratory experiments is to test individual parts of the developed methodology and the suitability of the instruments for the measurements defined by the methodology. During search experiments, the factors that determine development are also determined or the main factors are selected. Search experiments can also be carried out in order to find the basis for calculating the number of experiments.

After conducting search experiments, all factors that determine the phenomenon are divided into main ones, which have the greatest influence on the development of the phenomenon and carry the most information about it, and additional ones, which influence the development of the phenomenon in a secondary manner. When setting up an experiment, only parameters characterizing the main factors are measured.

It should be borne in mind that this division is largely conditional, since when the experimental conditions change, additional factors can become major and vice versa.

In order to eliminate or at least reduce the error that appears as a result of dividing factors into basic and additional ones, when, when setting up experiments, one tries to neutralize additional factors, i.e. create conditions under which the effect of additional factors would be more constant and insignificant. The researcher should strive to make only the main factors variable. Thus, the general principles of the study are the constancy of all other factors when selected ones change.

There are four main techniques for neutralizing additional factors.

Method of dramatically changing variable factors with relatively little change in the rest. With this method, they try to change the main factor in the widest range of values, and minimize the changes in the rest. For example, when taking the characteristics of a pump Q=f(p), or efficiency=f(p), it is desirable to change the pressure as widely as possible, and secondary factors such as machine wear, the influence of oil viscosity, temperature response, etc. to minimize, for which purpose it is better to conduct research on equally worn machines (for example, when comparing two different types of machines), to cool the engine, etc.

Method of control experiments, when changing additional factors simultaneously influence several objects with different gradations of the main factor, one of which is considered a control (standard) and all others are compared with it. For example, when studying the effect of an additive to an oil (lubricant) on bearing wear, an experiment can be carried out for two groups of bearings, of which a lubricant with an additive is used, and the other without. Since in most cases it is not possible to avoid the influence of changes in temperature, load and speed conditions on bearing wear, two groups are tested simultaneously in such changing conditions, which results in wear. There can be much more than two groups of bearings for testing; each of them can use different additives or different additive contents, and one of the groups is always the control (reference).

Method of “pure” experiments. With this method, one strives to artificially create conditions in which additional factors would not appear or would not influence the changing basic factors during experiments. This method is used only in laboratory conditions.

For example, in real operating conditions it is very difficult to study the operation of the hydraulic steering system of a car, because the moment of resistance to turning of the steered wheels is constantly changing due to the presence of unevenness in the road surface, different coefficients of friction in its different sections, etc. In addition, the magnitude of the moment of resistance to turning of the steered wheels during long-term testing will be influenced by tire wear, air pressure in the tires, changes in vehicle weight (for example, as a result of refueling), etc. It is extremely difficult to conduct accurate scientific research in such conditions, therefore, when testing the hydraulic steering system, it idealizes its interaction with the external environment, artificially creating in laboratory conditions constant and precisely known values ​​of resistance forces to wheel rotation, or, in other cases, ensuring changes in resistance forces according to a certain law . The same method of “partial” experiments will be very suitable for reproducing in laboratory conditions angular vibrations and impact impacts of the required magnitude on the steered wheels of a car, simulating the movement of a car over uneven roads. In real road conditions (outside special testing areas), it is almost impossible to obtain such disturbances on the system with the required frequency and amplitude.

Method of different signs consists in the fact that the same factor, which cannot be completely excluded, is first given a positive and then a negative value, so that when calculating the average value, errors from not taking into account the influence of this factor are cancelled.

For example, when studying the braking process of a car, the angle of the road in the longitudinal direction, as well as the wind speed, can lead to a noticeable error. To eliminate the error from the influence of these factors, experiments are carried out with the car moving in one and then the other (reverse) direction of the same road section, after which the data obtained are averaged.

Experiment planning. Number of experiments.

When determining the required number of experiments, one should be guided by two types of provisions.

Firstly, a number of experiments is needed that would sufficiently accurately reveal the form of the functional dependence of the two parameters. For example, the position of a straight line is determined by two points, while an arc of constant radius is determined by three. For more complex curves, the number of points is determined by the following rule: considering a complex curve as a combination of straight and simple curves, describe each bend in the curve with at least three points, and each section close to a straight line with two. To more accurately determine the numerical values ​​of the function, it is recommended to substantiate each inflection of the curve with at least five experiments. In addition, sharp bends in the curves or abrupt changes in the development of the phenomenon must be especially carefully observed.

To determine the number of experimental points, graphs of the working hypothesis pattern are used. If the pattern in the development of the phenomenon is unknown in advance, the experimental points are placed evenly along the abscise axis. During the experiments, the position of these points can be refined in accordance with the actual places of bends of the curves.

Secondly, it is necessary to take into account random experimental errors. As is known, to reduce the influence of such errors, experiments are repeated and the arithmetic mean is taken. Moreover, the number of required repetitions depends on the standard deviation of the measurements and the specified reliability of the result.

Under reliability experience will understand the probability of obtaining the same results with new measurements of the same quantity or with repetition of the experiment under the same conditions.

From the theory of probability it is known that the greater the relative fluctuations of the results and the greater the reliability of the experiment it is desirable to obtain, the more repetitions of the experiment should be carried out. This dependence was established in the most convenient way for practical use by V.I. Romanovsky and presented in table form

Required number of experiments (measurements)

	Reliability of R's experience.

In order to find the required number of experiments from this table, you need to set the reliability P and the error A, taken in fractions of the standard deviation σ.

For example, when measuring with a less precise instrument of any size, the standard deviation is 0.9 mm, and with a more accurate one - 0.15 mm. Let the permissible measurement error with a reliability of 0.95 be no more than 0.3 mm, which is 1/3σ when measuring with a less accurate instrument and 2σ when measuring with a more accurate instrument. Using the table, we determine that under these conditions more than 27 measurements are required with a less accurate instrument and only 4 measurements with a more accurate instrument.

If the standard deviation of the measurement result is unknown in advance, then such an analysis can be carried out sequentially with experiments according to the following scheme: after each measurement, starting from the third, the mathematical expectation and standard deviation are calculated. As soon as the reliability and calculation of the error in the fraction of the standard σ give the table the number of measurements that have already been made, the experiments are stopped.

In cases where there is no necessary data to determine the number of repeated experiments, and search experiments require no less costs than the main ones, triplicate repetition of experiments is often accepted as the minimum.

Planning of single-factor and multi-factor experiments.

A factor should be understood as a variable quantity that presumably influences the result of an experiment. The factor may be pressure, flow, viscosity of the fluid, etc.

When planning single-factor During the experiment, the correct choice of the number and location of experimental points on the function under study is of no small importance. In many cases, it is advisable to choose an experimental design with equal intervals between points. However, depending on the parameter for which an equal interval of change in its values ​​is taken, the result of the experiment may look different. For example, when studying fluid at a throttle depending on its flow rate (), the graphs will look like:

When changing the controlled variable ν at equal intervals Δν, we obtain a graph, images in Fig. A). In the area of ​​high speeds there are not enough points, but in the area of ​​low speeds there are an abundance of them. In Fig. b) the situation looks opposite. The most correct option would be the one shown in Fig. c), where between the experimental points there are identical segments ΔS of the experimental curve. However, this approach is difficult to calculate and to implement it, it is necessary to know the nature of the dependence being studied before conducting experiments.

When choosing between the options shown in Fig. a) and b) it is better to use the criterion relative accuracy of data in different parts of the function under study. For example, for hydraulic systems, tests performed at low pressure or low power will be the least accurate. From this position, the sections of the curve where the data are most in doubt are tried to be filled in with a large number of points. From this point of view, the option shown in Fig. a) preferable.

When planning multifactorial experiments consider two or more variables. Such experiments are called two-factor, three-factor, etc.

If in an experiment a dependent variable R is determined, which is a function of several independent variables x, y, z, etc., then the design of a multivariate experiment is that all independent variables except one are assumed to be constant, and this one variable changes in the entire value interval, while the choice of the interval between the values ​​of the variable is made according to one of the rules discussed above. Next, another independent variable is changed, and all others are kept constant. Essentially, a multifactorial experiment is simply a sequence of single-factor experiments. This approach allows you to find simple functions like

R=ax n +by m

The design of a two-factor experiment, in which each factor is taken at five levels, can be schematically represented as follows:

levels of variable y

levels of re-

exchange x 3 * * * * *

The asterisk indicates combinations of independent variables in which the experiment should be carried out.

For more complex functions, such as

the above plan will be very limited and will not allow identifying these dependencies. In this case, several levels of independent variables x and y are considered, for example:

levels of variable y

levels of variable y

levels of re-

exchange x 3 * * * * *

Or you may have to fill in the entire square and run the experiment for all 25 combinations of the x and y variables.

When planning an experiment, keep in mind that it does not have to be balanced. This means that one may choose ten levels of x and only three levels of y if the dependence of R on x is thought to be more important or more complex.

In addition, other plans, more complex than those described above, are possible, focused on specific technical processes and built on the basis of a priori information about the nature of the function under study.

Psychological experiment- an experiment conducted under special conditions to obtain new scientific knowledge about psychology through the researcher’s targeted intervention in the life activity of the subject.

The concept of “psychological experiment” is interpreted ambiguously by various authors; often, an experiment in psychology is considered to be a complex of different independent empirical methods ( the experiment itself, observation, survey, testing). However, traditionally in experimental psychology, experiment is considered an independent method.

Within the framework of psychological counseling, a psychological experiment is a specially created situation designed for a more holistic (in various modalities) experience by the client of his own experience.

Specifics of a psychological experiment

In psychology, experimental research has its own specificity, which allows it to be considered separately from research in other sciences. The specificity of a psychological experiment is that:

• The psyche as a construct cannot be directly observed and its activities can only be learned based on its manifestations, for example, in the form of certain behavior.
• When studying mental processes, it is considered impossible to single out any one of them, and the impact always occurs on the psyche as a whole (or, from a modern point of view, on the body as a single indivisible system).
• In experiments with people (as well as some higher animals, for example, primates), there is active interaction between the experimenter and the subject.
• This interaction, among other things, makes it necessary for the subject to have instructions (which, obviously, is not typical for natural science experiments).

General information

In a simplified example, the independent variable can be considered as a certain relevant stimulus (St(r)), the strength of which is varied by the experimenter, while the dependent variable is the reaction ( R) of the subject, his psyche ( P) on the effect of that relevant stimulus.

However, as a rule, it is precisely the desired stability of all conditions, except for the independent variable, that is unattainable in a psychological experiment, since almost always, in addition to these two variables, there are also additional variables that are systematic irrelevant stimuli (St(1)) and random stimuli ( St(2)), leading to systematic and random errors, respectively. Thus the final schematic representation of the experimental process looks like this:

Therefore, in an experiment, three types of variables can be distinguished:

1. Additional variables (or external variables)

So, the experimenter is trying to establish a functional relationship between the dependent and independent variables, which is expressed in the function R=f( St(r)), while trying to take into account the systematic error that arose as a result of the influence of irrelevant stimuli (examples of systematic error include phases of the moon, time of day, etc.). To reduce the likelihood of the impact of random errors on the result, the researcher seeks to conduct a series of experiments (an example of a random error could be, for example, fatigue or a speck of dust getting into the subject’s eye).

The main objective of the experimental study

The general goal of psychological experiments is to establish the existence of a connection R=f( S, P) and, if possible, the type of function f (there are various types of connections - cause-and-effect, functional, correlation, etc.). In this case, R- reaction of the subject, S- the situation, and P- the personality of the subject, psyche, or “internal processes”. That is, roughly speaking, since mental processes cannot be “seen,” in a psychological experiment, based on the reaction of the subjects to stimulation regulated by the experimenter, some conclusion is made about the psyche, mental processes or personality of the subject.

Stages of the experiment

In each experiment, the following stages can be distinguished. The first stage is setting the problem and goal, as well as constructing an experimental plan. The experimental plan should be built taking into account accumulated knowledge and reflect the relevance of the problem.

The second stage is the actual process of actively influencing the world around us, as a result of which objective scientific facts accumulate. Obtaining these facts is greatly facilitated by correctly selected experimental techniques. As a rule, the experimental method is formed on the basis of those difficulties that need to be eliminated in order to solve the problems posed in the experiment. A technique developed for some experiments may be suitable for other experiments, that is, it may acquire universal significance.

Validity in a psychological experiment

As in natural science experiments, so in psychological experiments, the cornerstone is considered the concept of validity: if the experiment is valid, scientists can have some confidence that they measured exactly what they wanted to measure. Many measures are taken to ensure that all types of validity are met. However, it is impossible to be absolutely sure that in any, even the most well-thought-out study, all validity criteria can be completely met. A completely flawless experiment is unattainable.

Classifications of experiments

Depending on the conditions, there are

• Laboratory experiment - conditions are specially organized by the experimenter. The main task is to ensure high internal validity. It is typical to isolate a single independent variable. The main way to control external variables is elimination. External validity is lower than in the field experiment.
• A field or natural experiment is an experiment conducted under conditions that are not controlled by the experimenter. The main task is to ensure high external validity. Isolation of a complex independent variable is typical. The main ways to control external variables are randomization (the levels of external variables in the study exactly correspond to the levels of these variables in life, that is, outside the study) and constancy (making the level of the variable the same for all participants). Internal validity is generally lower than in laboratory experiments.

Depending on the result of exposure, they distinguish

Ascertaining experiment - the experimenter does not irreversibly change the properties of the participant, does not form new properties in him and does not develop those that already exist.

Formative experiment - the experimenter changes the participant irreversibly, forms in him such properties that did not exist before or develops those that already existed.

Pathopsychological experiment - the purpose of the experiment is to qualitatively and quantitatively assess the basic processes of thinking; the experimenter, as a rule, is not interested in the immediate results of testing, since research is carried out during the experiment way achieving results.

Depending on the level of awareness

Depending on the level of awareness, experiments can also be divided into

• those in which the subject is given full information about the goals and objectives of the study,
• those in which, for the purposes of the experiment, some information about it is hidden or distorted from the subject (for example, when it is necessary for the subject not to know about the true hypothesis of the study, he may be told a false one),
• and those in which the subject is unaware of the purpose of the experiment or even the fact of the experiment itself (for example, experiments involving children).

Organization of the experiment

A perfect experiment

Not a single experiment in any science can withstand the criticism of supporters of the “absolute” accuracy of scientific conclusions. However, as a standard of perfection, Robert Gottsdanker introduced into experimental psychology the concept of “flawless experiment” - an unattainable ideal of an experiment that fully satisfies three criteria (ideality, infinity, complete compliance), which researchers should strive to approach.

An impeccable experiment is an experimental model that cannot be implemented in practice, used by experimental psychologists as a standard. This term was introduced into experimental psychology by Robert Gottsdanker, author of the famous book “Fundamentals of Psychological Experiments,” who believed that using such a sample for comparison would lead to more effective improvement of experimental techniques and the identification of possible errors in planning and implementation psychological experiment.

Criteria for a Perfect Experiment

An impeccable experiment, according to Gottsdanker, must satisfy three criteria:

• Ideal experiment (only the independent and dependent variables change, there is no influence on it from external or additional variables)
• Endless experiment (the experiment must continue indefinitely, since there is always the possibility of the manifestation of a previously unknown factor)
• Full correspondence experiment (the experimental situation must be completely identical to how it would happen “in reality”)

Interaction between experimenter and subject

The problem of organizing the interaction between the experimenter and the subject is considered one of the main ones, generated by the specifics of psychological science. Instructions are considered the most common means of direct communication between the experimenter and the subject.

Instructions to the subject

Instructions to the subject in a psychological experiment are given in order to increase the likelihood that the subject adequately understood the experimenter's requirements, therefore it provides clear information regarding how the subject should behave and what he is asked to do. For all subjects within one experiment, the same (or equivalent) text with the same requirements is given. However, due to the individuality of each subject, in experiments the psychologist is faced with the task of ensuring an adequate understanding of the instructions by the person. Examples of differences between subjects that determine the advisability of an individual approach:

• For some subjects it is enough to read the instructions once, for others - several times,
• some subjects are nervous, while others remain cool,
• etc.

Requirements for most instructions:

• The instructions should explain the purpose and significance of the study
• It must clearly state the content, course and details of the experiment.
• It should be detailed and at the same time quite concise

Sampling problem

Another task that the researcher faces is sampling. The researcher first of all needs to determine its volume (number of subjects) and composition, while the sample must be representative, that is, the researcher must be able to extend the conclusions drawn from the results of the study of this sample to the entire population from which this sample was collected. For these purposes, there are various strategies for selecting samples and forming groups of subjects. Very often, for simple (one-factor) experiments, two groups are formed - control and experimental. In some situations, it can be quite difficult to select a group of subjects without introducing selection bias.

Stages of a psychological experiment

The general model of conducting a psychological experiment meets the requirements of the scientific method. When conducting a holistic experimental study, the following stages are distinguished:

1. Primary statement of the problem
   • Formulation of a psychological hypothesis
2. Working with scientific literature
   • Search for definitions of basic concepts
   • Compiling a bibliography on the research topic
3. Refining the hypothesis and defining variables
   • Definition of experimental hypothesis
4. Selecting an experimental tool that allows:
   • Control the independent variable
   • Log dependent variable
5. Design of a pilot study
   • Highlighting Additional Variables
   • Selecting an Experimental Design
6. Sampling and distribution of subjects into groups in accordance with the adopted plan
7. Conducting an experiment
   • Preparation of the experiment
   • Instructing and motivating subjects
   • Actually experimenting
8. Primary data processing
   • Compiling tables
   • Converting information form
   • Data checking
9. Statistical processing
   • Selection of statistical processing methods
   • Converting an experimental hypothesis into a statistical hypothesis
   • Carrying out statistical processing
10. Interpretation of results and conclusions
11. Recording the research in a scientific report, monograph, letter to the editor of a scientific journal

Advantages of experiment as a research method

We can highlight the following main advantages that the experimental method has in psychological research:

• Ability to select the start time of the event
• Repeatability of the event being studied
• Variability of results through conscious manipulation of independent variables
• Ensures high accuracy of results
• Repeated studies under similar conditions are possible

Control methods

1. Elimination method (if a certain feature is known - an additional variable, then it can be excluded).
2. Method of leveling conditions (used when one or another intervening feature is known, but it cannot be avoided).
3. Randomization method (used when the influencing factor is unknown and its influence cannot be avoided). A way to retest a hypothesis on different samples, in different places, on different categories of people, etc.

Criticism of the experimental method

Proponents of the unacceptability of the experimental method in psychology rely on the following provisions:

• Subject-subject relationship violates scientific rules
• The psyche has the property of spontaneity
• The psyche is too fickle
• The psyche is too unique
• Psyche is too complex an object of study

Psychological and pedagogical experiment

A psychological-pedagogical experiment, or a formative experiment, is a type of experiment specific exclusively to psychology, in which the active influence of the experimental situation on the subject should contribute to his mental development and personal growth.

A psychological and pedagogical experiment requires very high qualifications on the part of the experimenter, since unsuccessful and incorrect use of psychological techniques can lead to negative consequences for the subject.

Psychological and pedagogical experiment is one of the types psychological experiment.

During a psychological and pedagogical experiment, the formation of a certain quality is assumed (that is why it is also called “formative”), two groups usually participate: experimental and control. Participants in the experimental group are offered a specific task, which (in the opinion of the experimenters) will contribute to the formation of a given quality. The control group of subjects is not given this task. At the end of the experiment, the two groups are compared with each other to evaluate the results obtained.

The formative experiment as a method appeared thanks to the theory of activity (A.N. Leontiev, D.B. Elkonin, etc.), which affirms the idea of ​​​​the primacy of activity in relation to mental development. During a formative experiment, active actions are performed by both the subjects and the experimenter. A high degree of intervention and control over the main variables is required on the part of the experimenter. This distinguishes experiment from observation or examination.

Natural experiment

A natural experiment, or field experiment, in psychology is a type of experiment that is carried out in the conditions of the subject’s normal life activities with a minimum of experimenter intervention in this process.

When conducting a field experiment, it remains possible, if ethical and organizational considerations allow, to leave the subject in the dark about his role and participation in the experiment, which has the advantage that the naturalness of the subject’s behavior will not be affected by the fact of the research.

A laboratory experiment, or artificial experiment, is carried out in artificially created conditions (within a scientific laboratory) and in which, to the extent possible, the interaction of the subjects being studied is ensured only with those factors that interest the experimenter. The subjects under study are the subjects or group of subjects, and the factors of interest to the researcher are called relevant stimuli.

The specificity that distinguishes a psychological laboratory experiment from experiments in other sciences is the subject-subject nature of the relationship between the experimenter and the subject, expressed in the active interaction between them.

A laboratory experiment is performed in cases where the researcher needs to ensure the greatest possible control over the independent variable and additional variables. Additional variables are irrelevant or irrelevant and random stimuli, which are much more difficult to control in natural conditions.

Control over additional variables

To control additional variables, the researcher must: Identify all irrelevant factors that can be identified If possible, keep these factors constant during the experiment Monitor changes in irrelevant factors during the experiment

Pathopsychological experiment

A pathopsychological diagnostic experiment has specific differences from the traditional test research method in terms of the research procedure and analysis of the research results according to qualitative indicators (no time limit for completing the task, research on how to achieve the result, the possibility of using the experimenter’s help, speech and emotional reactions during the task, etc.). P.). Although the stimulus material of the techniques itself may remain classical. This is what distinguishes a pathopsychological experiment from traditional psychological and psychometric (test) research. Analysis of a pathopsychological study protocol is a special technology that requires certain skills, and the “Protocol itself is the soul of the experiment.”

One of the basic principles for constructing experimental techniques aimed at studying the psyche of patients is the principle of modeling ordinary mental activity carried out by a person in work, study, and communication. Modeling consists in isolating the basic mental acts and actions of a person and provoking or, better to say, organizing the performance of these actions in unusual, somewhat artificial conditions. The quantity and quality of this kind of models are very diverse; here there is analysis, synthesis, and the establishment of various connections between objects, combination, dissection, etc. Practically the majority of experiments consist in the fact that the patient is asked to do some kind of work, they are offered a number of practical tasks or actions “in the mind”, and then they carefully record how the patient acted, and if he made mistakes, what caused them and what type of mistakes they made

Solso R.L., Johnson H.H., Beal M.C. Experimental psychology: a practical course. - SPb.: Prime-EUROZNAK, 2001.

Gottsdanker, Robert;"Fundamentals of psychological experiment"; Publishing house: M.: MSU, 1982;

D. Campbell. Experimental models in social psychology and applied research. M., Progress 1980.

Gottsdanker R. Basics of psychological experiment. M.: MGPPIA, 1982. pp. 51-54.

Nikandrov V.V. Observation and experiment in psychology. St. Petersburg: Rech, 2002. P. 78.

When experimenting, even an experienced researcher is not guaranteed against errors and distortions of information. Some of them can be eliminated if you take a more careful approach to the design of the experiment. The other part cannot be eliminated in principle.” But taking into account this very possibility—the possibility of errors—allows us to make the necessary amendments.

First of all, something that in fact is not one can be mistakenly called an experiment. When conducting a parallel experiment, it is possible, for example, to change the wage system in one factory team, but not change it in another, and it may turn out that labor productivity has increased in the first team. However, this kind of situation will in no way be experimental unless some important characteristics of both groups are taken into account and control is established over them.

The experimental and control teams must be equal in size, type of activity, distribution of production functions, type of leadership or other characteristics important from the point of view of the hypothesis. If any important group properties cannot be equalized, you should try to somehow neutralize or fix them and take them into account when analyzing the results.

In cases where the sociologist does not do this, he is not in the mood to call the situation created experimental and to explain the change in productivity by a change in the wage system, since the change in productivity may be caused by any other random factor and not by the change; wages. Before calling a study experimental, the researcher must analyze whether he has a basis for this, in other words, whether he has created the necessary conditions and provided the necessary level of measurement and control.

When formulating a hypothesis and when transitioning from a general hypothesis to cooperational variables, errors may occur due to the logic of reasoning.

As a unifying reason when formulating a hypothesis: the identified mechanisms and connections may be erroneously identified. This usually happens when studying little-known phenomena, and then the negative results obtained in the experiment are a positive contribution to the development of a theoretical model of the object of observation, since they show that a given mechanism or connection does not determine the processes occurring.

Errors are possible when moving from the definition of a hypothetical

connection to the description of its empirical indicators. Poorly selected metrics will render an experiment of no value, no matter how carefully it was conducted. Errors are possible due to the subjective perception of the situation by both the experiment participants and the researcher. The experimenter often has a tendency to overestimate the impact of the variable under study, and this leads to the fact that he tends to interpret any ambiguous fact in the direction he desires.

Members of the experimental group also have the opportunity to subjectively interpret the situation: they can perceive certain features of the experimental situation in accordance with their own attitudes, and not in the meaning in which they appear to the experimenter. Such a discrepancy in perception, if it is not taken into account when planning an experiment, will certainly affect the analysis of the results and significantly reduce their reliability.

Weakening control and reducing the degree of “purity” of the experiment increases the possibility of the influence of additional variables or random factors, which cannot be taken into account or assessed at the end of the experiment. This, in turn, greatly reduces the reliability of the conclusions drawn.

An insufficiently experienced researcher faces dangers associated with the use of statistical methods. He may use methods that do not correspond to the research task. This possibility applies both to the construction of the experimental group and to the method of analyzing the results.

The use of experiment in sociology is associated with a number of difficulties that do not allow achieving the purity of a natural science experiment, since it is impossible to eliminate the influence of relationships that exist outside of what is being studied, it is impossible to control factors to the extent that is possible in a natural science experiment, or to repeat the course in the same form and results.

An experiment in sociology directly affects a specific person, and this also poses epic problems, naturally narrows the scope of the experiment and requires increased responsibility from the researcher.

Literature for additional reading

Lenin V. R, Great initiative. - Full. collection cit., vol. 39, p. 1-29.

Afanasyev V. G. Managing society as a sociological problem. - In the book: Scientific management of society. M.: Mysl, 1968, issue. 2, p. 218-219.

Meleva L. A., Sivokon P. E. Social experiment and its methodological foundations. M.: Znanie 1970. 48 p.

Kuznetsov V. P. Experiment as a method of transforming an object. - News. Moscow State University.

Ser. 7. Philosophy, 1975, No. 4, p. 3-10.

Kupriyan A. P. The problem of experiment in the system of social practice M. Nauka, 1981. 168 p.

Lectures on the methodology of specific social research / Ed. G. M. Andreeva. M.: Moscow State University Publishing House, 1972, p. 174-201.

Mikhailov S. Empirical sociological research. M.: Progress, 1975 p., 296-301.

Fundamentals of Marxist-Leninist sociology. M.: Progress, 1972, p. 103-108. Process of social research/Under general. ed. Yu. E. Volkova. M.: Progress 1975, sect. PD II.4.

Panto R., Grawitz M. Methods of social sciences. M.: Progress, 1972, pp. 557-562.

Richtarzhik K. Sociology on the paths of knowledge. M.: Progress, 1981, p. 89-112.

Ruzavin G. I. Methods of scientific research. M.: Mysl, 1974, p. 64-84.

Shtoff V. A. Introduction to the methodology of scientific knowledge. L.; Publishing house of Leningrad State University. 1972. 191 p.

Section four