Dr.

Sasmita Mishra KSOM, KIIT University

An experiment is generally used to infer a causality. In an experiment, a researcher actively manipulates one or more causal variables and measures their effects on the dependent variable of interest.

CR determines the cause and effect relationships. For example, a 5% increase in price of the product will have no appreciable impact on the quantity demanded by customers.

DR is not suitable for establishing, causality. Therefore, to establish causal relationship the experiments are used.
Causal research is appropriate for understanding which variables are the cause/s (independent variables) and which variables are the effect (dependent variables) Like DR, causal research requires a planned and structured design. Causal design, in which the causal or independent variables are manipulated in a relatively controlled environment. The main method of causal research is experimentation.

To understand CRD, one must understand the scientific notion of causality.

The SNC of causality is different from the common day notion. 1) The common notion: there is a single cause of an event such that the statement X is the cause of Y implies that X is indeed the cause. The SNC holds that X would only be one of the causes/conditions. 2) CN implies a completely deterministic relationship. The SNC implies a probababilistic relationship. The SNC suggests that X can be a cause of Y if the occurrence of X makes the occurrence of Y more likely or more probable. 3) Finally, the SNC implies that we never prove that X is a cause of Y. Rather we infer, that a relationship exists. SN: causality is inferred, it is never demonstrated conclusively.

Three kinds of evidences, concomitant variation, time of occurrence of variables, and elimination of other possible causal factors.

Concomitant variation Time order of occurrence of variables Elimination ofother possible causal factors

1. Concommitment Variation:

If a statement is "X is a cause of Y" then the concomitant variation as to the validity of this statement refers to the extent of which X and Y occur together or vary together in the way predicted by the hypothesis. Suppose there is a positive relationship between the quality of dealers and market share. The hypothesis, in this connection is "The success of a companys marketing efforts is highly dealer dependent. Where the company has good dealers, it has market penetration and where the co. has poor dealers, the co. has unsatisfactory market penetration. If X is to be considered a cause of Y, one should expect to find the following

Research investigated market penetration in each sales territory Perfect evidence of CV would be provided if all good dealers have satisfactory market share and all poor dealers unsatisfactory market shares. The "pure" case will rarely be found in practice, as the other causal factors will effect some deviation from a one-to-one correspondence between X and Y.

Dealer Quality X

MARKET SHARE - Y Satisfactory Unsatisfa ctory 20(33%) 30(75%) Total 60(100%) 40(100%)

Good Poor

40(67%) 10(25%)

2. Time order of Occurrence of Variables This is conceptually simple One event cannot be cause of another if it occurs after the other event. By definition, an effect cannot be produced by an event that occurs only after the effect has taken place. However, it is possible for each term in the relationship to be both a cause and an event of the other term

3. The Elimination of other possible causes

The researcher has to eliminate any other variable or variables, which may affect the dependent variable under study. If it is not done then the causal relationship between the independent and dependent variable may not be proved. These evidences can be provided through causal research, which is carried out through controlled experiments.

Independent variables: Independent variables are also known as explanatory

variables or treatments. The levels of these variables are manipulated (changed) by researchers to measure their effect on the dependent variable.

Test units: Test units are those entities on which treatments are applied. Dependent variables: These variables measures the effect of treatments (independent variable) on the test units.

Experiment: An experiment is executed when the researcher manipulates one or more independent

variables and measures their effect on the dependent variables while controlling the effect of the extraneous variables.

Extraneous variables: These are the variables other than the independent variables which influence
the response of test units to treatments.

Examples: Store size, government policies, temperature, food intake, geographical location, etc.

Internal validity: Internal validity tries to examine whether the observed effect on a dependent variable is actually caused by the treatments (independent variables) in question. External validity: External validity refers to the generalization of the results of an experiment. The concern is whether the result of an experiment can be generalized beyond the experimental situations.

History Maturation Testing Instrumentation Statistical regression Selection bias Test unit mortality

The environment at the time of test may be different from the environment of the real world where these results are to be generalized. Population used for experimentation of the test may not be similar to the population where the results of the experiments are to be applied. Results obtained in a 56 week test may not hold in an application of 12 months. Treatment at the time of the test may be different from the treatment of the real world.

Randomization
Matching Use of experimental designs Statistical control

Laboratory Environment - In a laboratory experiment, the researcher conducts the experiment in an artificial environment constructed exclusively for the experiment. Field Environment - The field experiment is conducted in actual market conditions. There is no attempt to change the real-life nature of the environment.

Pre-experimental designs do not make use of any randomization procedures to control the extraneous variables. Therefore, the internal validity of such designs is questionable.

One-shot case study: X O One-group pre-testpost-test design: O1 X O2 Static group comparison:

Group 1 - X O1 Group 2 -

O2

In quasi-experimental design, the researcher can control when measurements are taken and on whom they are taken. However, this design lacks complete control of scheduling of treatment and also lacks the ability to randomize test units exposure to treatments.

Time series design: O1 O2 O3 O4 X O5 O6 O7 O8

Contd..

Multiple time series design:

Experimental Group: O1 O2 O3 O4 X O5 O6

O7 O8

Control Group:

O7 O8

O1 O2 O3 O4

O5 O6

In true experimental designs, researchers can randomly assign test units and treatments to an experimental group. Here, the researcher is able to eliminate the effect of extraneous variables from both the experimental and control group.

Pre-testpost-test control group: Experimental Group: R O1 X O2 Control Group: R O3 O4

Post-test only control group design:

Experimental Group: R Control Group: R

O2

O1

Solomon four-group design:

Experimental Group 1 : R Control Group 1: R Experimental Group 2: R Control Group 2: R

O1 O3

O2 O4 O5 O6

Statistical designs allow for statistical control and analysis of external variables.

Completely randomized design

Randomized block design Latin square design Factorial design

Thank You