The aim of any researcher when conducting an experiment is to show causal relationship between two or more variables. Variable of interest to researcher are normally influenced by several variables. It is impossible for the researcher to include all these variables. The researcher, therefore, needs to eliminate the effect of extraneous variable on the experiment. The success of an experiment is measured by its internal validity because it indicates the reliability of the experiment’s results.
Internal validity refers to an inductive estimate of the degree to which an experiment’s results concerning causal relationships are likely to be true with regard to the measures used, setting of the research and the research design. The degree to which the researcher is able to eliminate the impact of extraneous variable is referred to as internal validity.
How SPSS can help with determining internal validity
SPSS has several tools that can determine internal validity. The first one is the goodness of fit (R-square). R-square is obtained in the summary of output table after running a regression analysis using SPSS. R-square gives the explanatory power of the model. For example, R-square of 90 percent implies that 90 percent of variations in the independent variable are explained by the model.
Analysis of covariance (ANCOVA) is another statistical tool in SPSS that can be used to measure internal validity. It assesses the joint significance of predictors or variables on a continuous outcome using a general linear model approach. The ANCOVA can be interpreted as allowing for test of treatment after adjusting posttest scores for pretest scores. The researcher can then use the ANCOVA results to determine the extent of internal validity.
References
Jackson, S. L. (2011). Research Methods and Statistics: A Critical Thinking Approach (4 ed.). London: Cengage Learning.
Klugh, H. E. (2009). Statistics: the essentials for research (6, illustrated ed.). New York: Wiley.