Essential terminology Null hypothesis The null hypothesis states that there is no association between the predictor and outcome variables in the population. Alternative hypothesis The proposition that there is an association is called the alternative hypothesis. The alternative hypothesis cannot be tested directly; it is accepted by default if the test of statistical significance rejects the null hypothesis.

Abstract

Background and Aim: Investigators use correlation study to determine the extent to which two or more variables are related among a single group of people. One big question frequently encountered by investigators is How to calculate sample size? After data collection, it is essential to test the data statistically. Hence, we planned to provide hands-on guide for sample size calculation and statistical analysis of data in Microsoft Excel ® 2010 commonly needed for a correlation study. Methods: An example of a correlation study of body mass index and peak expiratory flow rate was taken. Its execution process from sample size calculation to statistical analysis of data has been explained step by step in Excel ® 2010. All formula and functions were tested in Excel ® 2007. Conclusion: Excel ® as a tool for statistical analysis of data would facilitate researchers to do all statistical analyses in a single file. Along with correlation study, analysis by t-test and ANOVA was also provided. With this discussion, new investigators would get a fair knowledge about sample size calculation and data analysis of correlation study in Excel ® and can use it for their future studies.