Designing The Experiment PDF

DESIGNING THE EXPERIMENT EXPERIMENTAL APPROACH Experimental research is designed to establish causal relationships. It begins with a question concerning the relationship between two or more variables. Simultaneously, the researcher develops one or more hypotheses to stat...

DESIGNING THE EXPERIMENT EXPERIMENTAL APPROACH Experimental research is designed to establish causal relationships. It begins with a question concerning the relationship between two or more variables. Simultaneously, the researcher develops one or more hypotheses to state the nature of the expected relationship. The experiment is the event planned and carried out by the researcher trying to get evidence. The application of experimental methods yielded better results in Physical Sciences. Therefore this method was soon applied to other sciences such as biological science and medicine. In it's simplest form, an experiment has three following characteristics ; 1. An independent variable is manipulated. 2. All other variables except for independent variables are held constant. 3. The effect of manipulation of the independent variable is observed on the dependent variable. The variable upon which the effects of changes are observed is called the dependent variable, which is observed but not manipulated by the experimenter. The dependent variable is so named because its value is hypothesised to depend upon and vary with the value of the independent variable. THREE CHARACTERISTICS OF EXPERIMENTAL RESEARCH 1. MANIPULATION : Manipulation is defined as the first feature of experimental design. Manipulated conditions can also be termed as the treatment or intervention. Manipulation of an independent variable must involve the active intervention of the researcher. 2. CONTROL : It is again control of variables. Variables other than IV and DV are extraneous to the study. They should be randomised across the participants so that groups are equal. This effort helps in preventing outside factors to impact the outcome. 3. RANDOM ASSIGNMENT : Random assignment intends to produce equivalent groups. It ensures group similarity. It means each participant has an equal chance of being selected in a group and they are independent of selection of other participants. Reflexivity refers to the circular relationships between cause and effect. A reflexive relationship is bidirectional with both the cause and the effect affecting one another in a relationship in which neither can be assigned as causes or effects. For example, poverty is the main cause of unemployment and unemployment is the main cause of poverty. MEANING AND TYPES OF VARIABLES A variable, as the name implies, is something which varies. This is the simplest and the broadest way of defining a variable. However, a behavioural scientist attempts to define a variable more precisely and specifically. From his point of view, variables may be defined as those attributes of objects, events, things and beings which can be measured. In other words, variables are the characteristics or conditions that are manipulated, controlled or observed by the experimental. Intelligence, anxiety, aptitude income, education achievement etc are examples of variables commonly employed in Psychology, Sociology and Education.  DESIGNING THE EXPERIMENT Variables have been classified in three different ways. 1. From the viewpoint of causation. 2. From the viewpoint of design of the study. 3. From the viewpoint of the unit of measurement. DEPENDENT VARIABLE, INDEPENDENT VARIABLE & INTERVENING VARIABLE From the viewpoint of causation or attempt to investigate a causal relationship or association 4 sets of variables usually operate in the study. Change Variables : Which are responsible for bringing change in the phenomenon. Outcome Variables : Which are the effects of the change variable. Unmeasured Variables : which affect the link between cause and effect variable. Connecting Variables : which in certain situations are considered essential for completing the relationship between cause and effect variables. In the terminology of research methodology, the change variables are called as independent variables, the outcome variables are called dependent variables, the unmeasured variables that affect the link between cause and effect relationship are called as extraneous variable and the variables that link a cause and effect relationship are called intervening variable or sometimes confounding variables. (Grinnell 1993). The terms dependent variable and independent variable have been borrowed from the field of mathematics in behavioural research. The classification of variables into dependent and independent is frequently employed in experimental research. The DV (Dependent Variable) is defined as one about which the experimenter makes a prediction. The IV (Independent Variable) is defined as the one which is manipulated, measured and selected by the experimenter for the purpose of producing observable changes in the DV. In other words, the independent variable is the variable on the basis of which the prediction about the DV is made. Suppose the experimenter wants to study the effect of teaching methods upon the classroom achievement of pupils. For this purpose, he may employ three methods of teaching, say A, B and C and may teach the same group of pupils by these three methods and subsequently, the achievement may be measured or predicted. Teaching methods constitute the example of IV and the classroom achievement constitutes the example of DV. Sometimes in the experiment, a variable is left uncontrolled and is unintentionally allowed to vary with independent variable. Such a variable is called a confounding variable. For example, suppose the researcher is to assess the effectiveness of the lecture method vs. laboratory demonstration method in acquiring knowledge of statistics. There may be two equivalent groups of students. One group is lectured by Professor A and the other group with laboratory demonstration is taught by Professor B. Subsequently, both groups receive the same final examination and their performance is compared. Statistical analysis reveals that students taught by Professor B excel in their performance as compared to the students taught by Professor A. Can the researcher conclude that the method of laboratory demonstration is better than the method of lecture? The answer is no. The method of instruction is not the only way the groups differ in terms of how they have been treated. The instructor (Professor) was allowed to vary along with the method of instruction. It might be that Professor B is a better  DESIGNING THE EXPERIMENT instructor, motivates students properly and can explain concepts in understandable terms. This is an example of a confounding variable and when a study is confounded it is impossible to arrive at meaningful conclusions about the results. One important thing related to the selection and measurement of dependent variable is that of floor and ceiling effect. A floor effect is said to have occurred where a null result occurs because majority of subjects score at the very bottom end of the scale. Such an effect usually emerges when the task is too difficult for the subjects. For example, if in any experiment the purpose is to compare people's sensitivity to lights of different colours but all the colours are below thresholds, no meaningful data will be obtained. This illustrated floor effect. Ceiling effects are the opposite of floor effects and are said to have occurred when subjects score too close to the top of the scale simply because the task was too easy. Continuing with the same example, if all the coloured lights are clearly visible because they are bright, the task would be too easy for the subjects and therefore, ceiling effect would occur. As it has been said above, the IV is manipulated by the experimenter and it's effect is examined upon the DV. Some experts, depending upon the mode of manipulation, have tried to divide the IV into Type - E Independent Variable and Type - S Independent Variable. Type E IV is one which is directly manipulated by the experimenter, and Type S IV is one which is manipulated through the process of selection only. The independent variable (IV) may also be classified on the basis of the nature of the variables. Thus, depending upon the nature of the variables, the independent variable is classified into three categories : Task Variables, Environmental Variables and Subject Variables. 1. TASK VARIABLES : The task variables refer to those characteristics which are associated with a behavioural task presented to the subject. It includes the physical characteristics of the apparatus as well as many features of the task procedures. When, for example, the number of wrong paths in a maze is increased, the process of learning the maze will be a difficult task for the subject. 2. ENVIRONMENTAL VARIABLES : Environmental Variables refer to those characteristics which are not the physical parts of the task as such, but tend to produce changes in the behavioural measures. Noise, temperature, levels of illumination and time of the day are examples of environmental variables. Suppose for example, that the investigator wants to study how reading speed is influenced by the degree of vagueness in handwriting. It is likely that apart from the degree of vagueness, the reading speed may be influenced by the levels of illumination and noise occurring at the time of reading the materials. Therefore, these constitute the examples of environmental variables. SUBJECT VARIABLES : Subject Variables refer to those characteristics of the subjects which are likely to produce changes in the behavioural measures. Subject Variables can be divided into two types : The Natural Subject Variable and The Induced Subject Variable. The Natural Subject Variables are those variables which the subjects carry within themselves before the start of the experiment. Age, sex, intelligence and anxiety are examples of natural subject variables. Induced subject variables, also known as instructional variables, are those subject Variables which are induced by the experimenter's instructions.  DESIGNING THE EXPERIMENT Sometimes, the experimenter manipulates a variable only for the sake of controlling it's unwanted effect upon the experimental results. Such a variable is not an independent variable. Thus, for a variable to be called an independent variable, it must be manipulated for the sole purpose of producing its effect upon the dependent variable, otherwise it will not be an independent variable. In experimental situations those variables which are controlled by the experimenter because they are not of direct interest but are likely to produce changes in the behavioural measures are known as relevant variables or control variables. Control variables are also known as extraneous variables. There are some variables which have no discernible effect upon the dependent variable. These are known as irrelevant variables. Extraneous variables are of three types which must be controlled in any experiment. 1. SUBJECT RELEVANT VARIABLES : Subject relevant variables are those variables which constitute the characteristics of the subject and are controlled by the experimenter because he does not want to study their effect upon the dependent variable. Thus, age, intelligence, race, aptitude, personality classification, etc are the examples of subject relevant variables. The students should note carefully that the same variable may act as an independent variable in one experimental situation and as a relevant variable in another experimental situation. 2. SITUATIONAL RELEVANT VARIABLES : The situational relevant variables refer to those environmental and task variables whose effects are controlled by the experimental because they are likely to produce unwanted changes in the DV. 3. SEQUENCE RELEVANT VARIABLES : The sequence relevant variables are those variables which arise from the different ordinal positions that the conditions of the experimental occupy in a sequence. For example, when the same subjects are exposed to two or more than two conditions of the experiment, factors like practise, fatigue, adaptation are likely to influence the DV. Thus, sequence relevant variables are usually controlled with the help of counterbalancing. From the point of view of measurement, there are two important ways of classifying variables. 1. Whether the unit of measurement is categorical or continuous in nature. 2. Whether it is qualitative or quantitative in nature. Variables thus classified on the basis of unit of measurement are called qualitative and quantitative variables, and categorical and continuous variables. there is very little difference between qualitative and categorical, and continuous and quantitative variables. QUALITATIVE VARIABLES & QUANTITATIVE VARIABLES The qualitative variables refer to those variables which consist of categories that cannot be ordered in magnitude. The qualitative variables comprise the categories which do not have a quantitative relationship among themselves. Sex, race and religion are examples of qualitative variables because they cannot be ordered in magnitude. The quantitative variables refer to those variables which are composed of categories that can be ordered in magnitude. We can say, for example, that, category A possesses greater magnitude of the variable than category B. Intelligence, age, levels of illumination, intensity of sound, etc., are examples of quantitative variables.  DESIGNING THE EXPERIMENT CONTINUOUS VARIABLES & DISCRETE VARIABLES Quantitative variables are further divided into two categories, namely, continuous variables and discrete variables. A continuous variable is one which is capable of being measured in any arbitrary degree of exactness. Age, height, intelligence, reaction time, etc are some examples of a continuous variable. Thus, all such variables which can be measured in the smallest degree of fineness are examples of continuous variables. The discrete variables (also known as categorical variables) are those variables which are not capable of being measured in any arbitrary degree of exactness because the variables contain a clear gap. For example, the number of members in a family constitute an example of a discrete variable. EXPERIMENTAL DESIGNS Campbell and Stanley have discussed 16 designs ranging from the poorest to very strong ones which have proved very useful in psychological and educational research. Campbell and Stanley have used some symbols with which a reader is expected to be acquainted. R : Random selection of subjects or random assignment of treatment to experimental groups. X : Treatment or experimental variable which is manipulated. O : Observation or measurement or test. When one or more X and O occur in the same row they indicate that these are being applied to the same persons. The left to right dimensions in which X and O occur indicate temporal order and when X and O occur in vertical order to each other, they indicate that these two are simultaneous. The parallel rows of symbols unseparated by a dash line indicate that groups have been equated by randomisation and when separated by dashed lines they indicate that groups have not been equated by randomisation. PRE EXPERIMENTAL DESIGN (NONDESIGNS) There are three designs which actually do not qualify for the experimental designs because they do not provide a control group or the equivalent of a control group. Such designs do not control the extraneous variables in an appropriate manner. Therefore, these designs are called pre experimental designs or non designs because they incorporate the least basic elements of an experimental design. The following are the different types of pre experimental designs. 1. ONE SHOT CASE STUDY The one shot case study may be diagrammed as XO As its name implies, in a one shot case study the treatment X is given to a single group and subsequently, an observation O is made to assess the effects of treatment upon the group. This design has two important limitations. One is that it does not provide a control group and another is that it does not give any information regarding the members who are given the treatment. In view of these limitations there is little justification for concluding that X caused O. Suppose the principal of a college introduces the practice of giving monetary reward to students who regularly attend their classes (X). After this practice has been in operation for a year, the principal observes that the students attend their classes regularly and disruptive activities in the classroom are minimised (O). On this basis the principal concludes that with  DESIGNING THE EXPERIMENT the practice of giving monetary reward, the absenteeism and the disruptive activities in the classroom are reduced. This conclusion is, however, dubious because the principal does not know whether or not factors other than monetary reward have contributed to the observed change in behaviour and whether there was a real change in the observed behaviour relative to their past behaviour. 2. ONE GROUP PRETEST POSTTEST DESIGN This design is an improvement over the above design because the effects of treatment (X) are judged by making a comparison between the pretest and post test scores. However, no control group is used in this design. O1 X O2 For example, suppose the principal of a college wants to study the effect of movies (X) in changing the attitude of a group of students. He first obtained some initial measures of attitude (O1) and then, for an hour the students may be asked to see the film which intends to bring a change in attitude. Subsequently, a measure of attitude change may be obtained (O2). This design provides some information about the extraneous variables which are likely to endanger the internal validity of the experiment. However, the extraneous variables such as history, maturation etc are not controlled by this design. 3. STATIC GROUP COMPARISON (INTACT GROUP COMPARISON) In this design, two groups are taken. One group (O1) experiences the treatment (X) and another group does not experience the experimental treatment. Subsequently, these two groups are then compared. X O1 —— O2 In this design, a control group (the group receiving no treatment) is used as a source of comparison for the treatment receiving group or the experimental group. The dashed line indicates that the groups have not been selected through randomisation. TRUE EXPERIMENTAL DESIGNS There are three experimental designs, which are called true experimental designs. In these designs the control group and the experimental groups are formed and their equivalence is established through randomisation. These designs are called true experimental design because the majority of the factors are controlled. 1. POSTTEST ONLY, EQUIVALENT GROUP DESIGN This design is the most effective and useful true experimental design. The diagram can be given as follows. R X O1 R O2 In the above design, there are two groups. One group is given the treatment(X), usually called the experimental group, and the other group is not given any treatment called the control group. Both groups are formed on the basis of random assignment of the subjects. Let us take an example. Suppose the experimenter, with the help of the table of Random numbers selects 50 students out of a total of 500 students. Subsequently, these 50 students are  DESIGNING THE EXPERIMENT randomly assigned to groups. The experimenter is interested in evaluating the effect of punishment over retention of a verbal task. The hypothesis is that punishment enhances the retention score. One group is given punishment (X) while learning a task, and another group receives no such punishment while learning a task. Subsequently, both groups are given the test of retention. 2. PRETEST POSTTEST CONTROL GROUP DESIGN This design is similar to the previous one except for the fact that it also makes a provision for pretest for both groups before experimental and control treatments are administered. RO1 X. O2 R03. O4 The very element of pretest however introduces one basic limitation. In this design there is no control over the gain on the post test due to the experience on the pretest. this is called as testing effect, which may reduce the internal validity of the experiment. 3. SOLOMON FOUR GROUP DESIGN The Solomon four group design developed by Solomon is really a combination of the two equivalent groups design described above, namely the posttest only design and pretest posttest design. In this design, subjects are randomly assigned to two control groups and 2 experimental groups. Only one experimental group and one control group receives a pretest. All four groups received a post test. R O1. X. O2 R. O3. O4 R. X. O5 R. O6 This design makes it possible to evaluate the main effects of testing, thus increasing the generalizability of the experiment. 4. LATIN SQUARE DESIGN This experimental design is used to examine whether the order or sequence in which subjects or participants receive multiple versions of the treatment has an effect upon the dependent variable. Thus, when a researcher is interested in how several treatments given in different sequences or time orders affect a dependent variable, a Latin square design is used. For example, suppose a teacher of Geography has three fundamental units to teach the students : how to use a compass, map reading and longitude latitude(LL) system. These units may be taught in any order but the teacher may be interested in knowing which order proves to be most beneficial to the students for learning. In one class the order may be - map reading, then using compass and then the LL system. In another class the order may be using compass, map reading and then the LL system. Still in other class the order may be LL system, then compass usage and then map reading. The teacher then take examination after each unit and students take a comprehensive examination at the end of the entire term. Since the students are randomly assigned to three classes, the teacher can easily determine whether or not presenting Units in specific order resulted in improved learning.  DESIGNING THE EXPERIMENT QUASI EXPERIMENTAL DESIGNS A Quasi experiment is one that applies an experimental interpretation to results that do not meet all the requirements of a true experiment. It means when the situation is such that the experimenter has some control over the manipulation of Independent variables but fails to arrange for the other basic requirement of a true experimental that is creating equivalent groups. Thus, there is no randomisation in quasi experiments. Thus, a quasi experiment is basically an attempt to simulate the true experiment and, therefore, has also been called a compromise design. The Quasi experimental designs provide control over when and whom the measurement is applied but as subjects are not randomly assigned to the experimental and the control group the equivalence of the groups is not maintained. Instead, subjects are assigned to a particular condition because they already qualify for that condition due to some inherent characteristics. Age, sex, race, background experience or personality characteristics are some of the examples of Quasi independent variables. Types of quasi experimental designs are as follows, 1. TIME SERIES DESIGN Sometimes it happens that a control group or a comparison group cannot be included in an experiment because of the situation in which the experiment is being conducted. Still, the experimenter wants to have a design which may exercise better control over the extraneous variables. The time series design is one such design which can be followed in the situation described above. The diagrammatic representation can be given as follows, O1O2O3O4. X. O5O6O7O8 It is obvious from the above diagram that a series of pretests are given to the group. Subsequently, the treatment is given and a series of post tests are given to the same group. This design differs from the single group pretest posttest design because instead of giving a single pretest and post test a series of pretest and post tests are given. 2. EQUIVALENT TIME SAMPLES DESIGN The equivalent time samples design is an extension of the time series design with the repeated introduction of the treatment or the experimental variable. Like the time series design, in equivalent time samples design a single group is used and the group is exposed to repeated treatments in a systematic manner. The design may be represented as follows, X1O1 X0O2 X1O3. X0O4 It is clear from the above diagram that in the equivalent time samples design the treatment (X1), instead of being given for a single time is introduced and reintroduced with some other experience(X0), which is available in the absence of the treatment. For example, suppose the experimenter wants to study the effect of showing a 25 minute Pro nationalisation film on the attitude towards nationalisation for a group of grade 9 students. The experimenter shows the film to a group of students(X1). After that, he administers the measure of the attitude change towards nationalisation (O1). After a few days, the experimenter briefly discusses the general usefulness of nationalisation with them in their class (X0). Again, the measure of their attitude can be made (O2). After a few days, the group witnesses the same film (X1) and the measure of the attitude may be obtained (O3). Following this, the experimenter discusses in detail every aspect of nationalisation (X0).  DESIGNING THE EXPERIMENT Their attitude towards nationalisation is again measured (O4). The statistical comparison of O1 and O3 with O2 and O4 helps the experimenter to compare the two experiences. 3. NON EQUIVALENT CONTROL GROUP In Psychological and educational research, often the experimenter is faced with a situation in which he has to work with intact groups, that is, groups whose membership is prefixed and cannot be altered by the experimental. For example, the teacher may provide the experimenter 2 classes of Geography but he may not agree with the latter in reconstituting them for experimental purposes. In such a situation, the experimenter has to accept them as intact groups. In working with such intact non equivalent groups the non equivalent control group design is recommended. O1. X O2 __________ O3. O4 The above design is similar to pretest posttest control group design except that it does not bear the subscript R. This means that in this design random assignment does not take place. Consider an example to illustrate this design. Suppose the experimenter wants to know the effect of a week's training intended to improve the map drawing skill among students of a Geography class. For this purpose, the principal of a school provides the experimenter with two classes of Geography, each consisting of 20 students. The principal does not permit reconstitution of these two groups in any way and requests the experimenter to handle them as intact groups. Which of these two groups would act as a control group and as an experimental group was decided randomly by flipping a coin by the experimenter. Both the groups were administered the map drawing test as pretest measures. Subsequently, the experimental group was given training in map drawing work and the control group was given no such training. After that, both groups were re administered the map drawing ( O2 & O4) 4. COUNTERBALANCED DESIGN In counter balanced designs, the experimental control is achieved by randomly applying experimental treatments. Such designs are called crossover designs, switch over designs and rotation experimentals. The name counterbalanced designs was, however, given by Underwood. For Counter balancing the treatments generally, the Latin square management in which each treatment appears once and only once in each column and in each row is made. A counterbalancing design in which four treatments have been randomly given to four groups on four different occasions is diagrammed below. Group A X1O X2O. X3O. X4O Group B X2O X4O. X1O. X3O Group C. X3O. X1O X4O. X2O Group D. X4O. X3O. X2O. X1O 5. SEPARATE SAMPLE PRETEST POSTTEST DESIGN The separate sample pretest posttest design is specially suited to those situations in which the experimenter cannot assign treatments to all subjects at a time. Hence, he is forced to select a sample and administer the treatment. Then, again another sample is taken and the same treatment is repeated.  DESIGNING THE EXPERIMENT Consider a situation in which there are 2000 persons who are to be trained but the experimenter cannot train more than 200 persons at a time. In such a situation the training program has to run continuously each time with the new set of persons and at the same time the experimenter cannot withhold treatment from any person. Consequently, he cannot assign persons to training conditions and non training conditions. As such, no true experiment design can be applied here. O1. X O2 ___________________________ O3. X. O4 6. PATCHED UP DESIGN In a patched up design the experimenter starts with an inadequate design and then adds some features so that recurrent factors producing in validity may be maximally controlled. The patched up design below is a combination of two different pre experimental designs, neither of which is adequate in itself, but which become adequate when combined. For example, let us take two pre experimental designs, namely one group pretest posttest design and the static group design. These two designs are inadequate in themselves because they fail to control many extraneous variables. However, the patched up design may be built on the basis of these two designs so that the mutual limitations may be overcome. CLASS A. X. O1 CLASS B. O2. X. O3 In the above diagram, the O3 and O2 comparison represents the one group pretest posttest comparison. Likewise, an O2 and O1 comparison is an intact group design. In a patched up design every subject gets the treatment and therefore the experimenter cannot withhold treatment by assigning some subjects to the control group. Apart from the above Quasi design there are also other Quasi independent variables that have been widely studied. One very widely studied Quasi independent variable in psychology is the passage of time. The field of development psychology is built around age focusing on how it relates to various kinds of development in social, emotional, and cognitive behaviour. Passage of time is also widely studied in different other settings where we compare experienced with inexperienced workers or study changes in memory abilities with advancement in age. These are quasi independent variables because the experimenter cannot randomly assign people to be of a certain age or to experience only a certain amount of work. There are three general designs for studying the passage of time : Longitudinal Study, Cross Sectional Study, & Cohort Study. LONGITUDINAL DESIGN Longitudinal design is a research method commonly used in psychology and other fields to study changes over time. In a longitudinal study, researchers observe and gather data from the same group of participants repeatedly at multiple points in time. This allows them to track  DESIGNING THE EXPERIMENT and analyze how certain variables or behaviors evolve, develop, or change over an extended period. The main advantage of a longitudinal design is its ability to capture individual and group changes over time, providing insights into developmental trajectories, patterns of growth, and stability or change in various aspects of human behavior, cognition, or emotion. However, longitudinal studies can be resource-intensive, time-consuming, and can suffer from issues like participant attrition or practice effects. In summary, longitudinal design in psychology involves studying the same individuals or groups over a period of time to understand how behaviors, traits, or phenomena change and develop. CROSS SECTIONAL DESIGN Cross-sectional design is a research method commonly used in psychology and other fields to gather data from a diverse group of participants at a single point in time. In a cross-sectional study, researchers collect information from individuals of different ages, backgrounds, or groups, all at once. The goal is to examine and compare differences or patterns that exist between these groups at that specific moment. This design is particularly useful for quickly gathering data and exploring relationships between variables in a snapshot of time. It can provide insights into differences between groups, prevalence of certain traits or behaviors, and potential correlations among variables. However, one limitation of cross-sectional studies is that they don't capture changes or developments over time, as longitudinal studies do. This means researchers cannot establish causal relationships or determine the direction of cause and effect. COHORT DESIGN Cohort design is a research method commonly used in longitudinal studies to examine changes and developments over time within specific groups or cohorts of individuals who share a common characteristic or experience. These cohorts are followed and compared at different points in time to understand how they change or differ as they age or experience certain events. In cohort design, researchers select a group of participants who were born or experienced a significant event within a certain time frame. For example, they might choose individuals born in the same year, individuals who started a particular job at the same time, or those who lived through a particular historical event. This group forms a cohort. The researchers then collect data from this cohort at different intervals over a period of time. By comparing data from each wave of data collection, they can analyze how the cohort changes as they age or as they go through shared life experiences. This design allows researchers to study how factors like societal changes, technological advancements, or other influences affect different generations or groups. Cohort design is particularly useful for studying generational differences, cultural shifts, and the impact of specific historical events on people's lives. It can provide valuable insights into trends, patterns, and changes that occur within distinct groups over time. EX POST FACTO DESIGN  DESIGNING THE EXPERIMENT An ex post facto research is one in which the investigators attempt to trace an effect which has already occurred to its probable causes. Thus, the term ex post facto research means that the researcher has conducted the study after the events have occurred. The phrase ex post facto means after the fact. Thus, in ex post facto research the manifestation of independent variables occurs first and then its effects become obvious to the investigator. Since the independent variables have already occurred, the investigator has no direct control over such variables. A simple definition of ex post facto research may be formulated as given below Ex post facto research is that empirical investigation in which the investigator draws the inference regarding the relationship between variables on the basis of independent variables whose manifestations have already occurred. In this type of research, the investigator has no direct control over the independent variables because they occur much prior to producing their effects. Suppose the investigator takes a case of lung cancer and then goes back to explore the causes of it. He may find that cigarette smoking and chronic cough are most commonly associated with lung cancer. Here, lung cancer is the dependent variable and cigarette smoking and chronic cough are examples of independent variables. These two independent variables have already occurred and therefore are beyond the direct control of the investigator. The two most common types of ex post facto design are, namely, correlational design and criterion group design.