Effect of Sample Size on Correlation and Regression Coefficients

The study was conducted to know the effect of sample size (by doubling the data) on correlation coefficient, determination coefficient (R2), F value and Beta coefficient of multiple regression. The statistical comparative method was used in the study. The sample of the study consisted of 100 (Male=50, Female=50) senior secondary students of Western Uttar Pradesh, (India), which was selected by employing multistage and stratified random sampling technique. The data was collected by administering three scales i.e. Modernization Scale (1986), Environmental Awareness Assessment Scale (1993) and Attitude towards Science Scale (2002) on the selected sample. The findings of the study revealed that: (1) the sample size was not affecting the value of correlation coefficient but it affected the level of significance for correlation coefficient. (2) There was no effect of sample size on determination coefficient R2) but the level of F value became high if the sample size was bigger. (3) There was no effect of sample size on Beta coefficient for independent variables in multiple regression. (4) The big sample size yielded small level of significance. In other words, the level of errors became less if the sample size was bigger.