Experimental Design

Unformatted text preview:

TABLE OF CONTENTS3.0 ADVANTATES & DISADVANTAGES OF THE EXPERIMENTAL DESIGNINTRODUCTIONAny researcher who is about to test a hypothesis faces fundamental problems that must be solved before the research project can be started. Research design is a blue print that enables the investigator to come up with solution to these fundamental problems. Once the research objectives have been determined the hypothesis explained and the variables defined the researcher confronts the problem of constructing a research design that will make it possible to test the hypothesis. Research design is therefore the program that guides the investigator in the process of collecting analyzing and interpreting observations. It allows the researcher to draw inferences concerning causal relations amount the variables and defines the domain of generalisability.STRUCTURE OF THE CLASSICAL EXPERIMENTAL DESIGNAdvantages of experimental researchThe classic experimental design is usually associated with research in the natural sciencesTABLE OF CONTENTS1.0 INTRODUCTION2.0 STRUCTURE OF THE CLASSICAL EXPERIMENTAL DESIGNSTEPS INVOLVED IN CONDUCTIONG AN EXPERIMENTAL STUDY3.0 ADVANTATES & DISADVANTAGES OF THE EXPERIMENTAL DESIGN4.0 WAYS OF MAKING THE EXPERIMENTAL DESIGN MORE EFFECTIVE5.0 CONCLUSIONINTRODUCTIONAny researcher who is about to test a hypothesis faces fundamental problems that must be solved before the research project can be started. Research design is a blueprint that enables the investigator to come up with solution to these fundamental problems. Once the research objectives have been determined the hypothesis explained and the variables defined the researcher confronts the problem of constructing a research design that will make it possible to test the hypothesis. Research design is therefore the program that guides the investigator in the processof collecting analyzing and interpreting observations. It allows the researcher to draw inferences concerning causal relations amount the variables and defines the domain of generalisability.An experimental design can be viewed as that concerned with identifying the sources of variation in an experiment. The aim of this research design is todetermine the effect that a change in one variable has upon the other. Experimentalresearch design is a planned interference in the natural order of events by the researcher which is more than just careful observations. Scientific knowledge indeed has been derived from actively manipulating or interfering with the stream of events information without ambiguity The purpose of experimental research design is therefore it rule out alternative cause leaving only the actual facts the real cause. Essentially you want to assess the proposition:If X, Then YUnfortunately it is not enough to just to show that when X occurs, Y also happens. That’s because there may be lots of reasons, other than the occurrence of X for why Y happened. To really show that there is a causal relationship; one has to simultaneously address the two propositions.I X then Y AND IF NOT x THEN yThe fundamental requirement of experimental research design is that the researcherhas control over variation on the independent variable and is able to control the influence of other variables. That is the researcher should control all factors but leave only one to be the influencing factor.STRUCTURE OF THE CLASSICAL EXPERIMENTAL DESIGNThe classical experimental research consist of two comparable groupsa) Experimental groupb) Control groupThese two groups are equivalent except that the experimental group is exposed to the independent variable (or treatment) and the control group is not. Cases arerandomly assigned to either the control group or experimental group. To assess the effect of the treatment, researchers take measurement on the dependent variable/score twice from each group. The first measurement, the pre-test, is taken for all cases prior to the introduction of the treatment to the experimental group. A second measurement, the post-test, is taken for all cases after the experiment grouphas been exposed to the independent variable. The difference in measurements, between pre-test and post-test is compared between the two groups. If the difference in the experimental group is significantly larger than the control group, it is inferred that the independent variable is causally related to the dependent variable.The classical research design consists of four components.a) Comparisonb) Manipulationc) Controld) GeneralizationComparison is an operation that enables researchers to demonstrate that independent and dependent variables are related. Manipulation involves some formof control over the introduction of the independent variable, so that the investigatorcan determine the time order of the variables. The control component allows researchers to rule out other factors as rival explanations of the observed associations between the independent and dependent variables. Generalization requires that the findings of research be applicable to the natural settings and populations the researcher is investigating.EXPERIMENTAL STUDY PROCESS (STEPS)1) Identify and define the problem.2) Formulate hypothesis and deduce their consequences.3) Construct an experimental design that represents all the elements, conditions and relations of the consequences. The steps specific to an experimental research design are:a) Select two groups/units from the population.These two groups must be as similar as possible. Example, two mediums sized organizations.b) Determine the dependant variable and the independent variable and their measurement units.c) Select one of the groups to be the control/comparison group and the other to be the experimental group (treatment group). The experimental group is exposed to the conditions under investigation.d) Matching takes place. This is associated with Quasi, that is, as if or almost a true experiment. Pre-test the dependent variable to develop a statistical baseline.e) Measure the dependent variable for the two groups before and after exposure.f) Because the two groups are as alike as possible in all other aspects save for the exposure to the condition under investigation, any difference between the groups isattributed to the independent variable.4) Compile raw data and reduce to usable form.5) Apply any appropriate significance test.The process of control is related to the internal validity of the research design. To establish internal


View Full Document

Experimental Design

Download Experimental Design
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Experimental Design and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Experimental Design 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?