In my previous two posts I discussed the t-test and z-test, which can be accessed here:-
- T-test:- https://medium.com/@tracyrenee61/interview-question-what-is-a-t-test-c34261aa7a99
- Z-test:- https://medium.com/@tracyrenee61/interview-question-what-is-a-z-test-04c14f6994b7
In this post I am going to discuss the f-test, which is a statistical test to determine if the variances of two samples are equal.
Named for the mathematician Ronald Fisher, the F-statistic refers to the value derived from the regression analysis of data. Regression analysis measures the relationship between two or more variables. F-statistics are used to determine whether the variance between two normal populations are similar to one another. Larger values represent greater dispersion between the two data samples.
The formula for the f-statistic is:-
If the variances of the samples are equal, the ratio of the variances will equal 1. You always test that the population variances are equal when running a f-test. In other words, you always assume that the variances are equal to 1. Therefore, the null hypothesis will always be that the variances are equal.
The null hypothesis can be described as the hypothesis in which no relationship exists between two sets of…