Changes

*So, if the variances are equal, the ratio of the variances will be 1.

*So, if the variances are equal, the ratio of the variances will be 1.

*Let X1,...Xn and Y1...Ym be independent samples each have a Normal Distribution .  

*Let X1,...Xn and Y1...Ym be independent samples each have a Normal Distribution .  

*It's sample means: <math>\bar X=\frac{1}{n} \sum_(i=1)^n Xi</math> and  <math>\bar Y =\frac {1}{m} \sum_{i=1}^m Yi</math> .  

*It's sample means: <math>\bar X=\frac{1}{n} \sum_{i=1}^n Xi</math> and  <math>\bar Y =\frac {1}{m} \sum_{i=1}^m Yi</math> .  

*The sample variances :

*The sample variances :

  <math>SX^2=\frac{1}{n-1} \sum_{i=1}^n (Xi-\bar X)^2</math>

  <math>SX^2=\frac{1}{n-1} \sum_{i=1}^n (Xi-\bar X)^2</math>

and

and

:<math>SY^2=\frac{1}{m-1} \sum_{i=1}^m (Yi-\bar Y)^2</math>

:<math>SY^2=\frac{1}{m-1} \sum_{i=1}^m (Yi-\bar Y)^2</math>

*Then the Test Statistic = <math>\frac {Sx^2}{Sy^2}<math> has an F-distribution with <math>n−1</math> and <math>m − 1</math> degrees of freedom.

*Then the Test Statistic = <math>\frac {Sx^2}{Sy^2}<math> has an F-distribution with <math>n−1</math> and <math>m−1</math> degrees of freedom.

*In FTEST(ar1,ar2) where <math>ar1</math> is the data of  first array, <math>ar2</math> is the data of second array.  

*In FTEST(ar1,ar2) where <math>ar1</math> is the data of  first array, <math>ar2</math> is the data of second array.  

*The array may be any numbers, names, or references that contains numbers.  

*The array may be any numbers, names, or references that contains numbers.