I have a frequency list of words. This list was generated using 1,000,000 words. I want to compare how much more word 1 occurs compared to word 2.
For example,
The word "he" shows up 20000 times The word "she" shows up 6000 times
What percent does the word he occur compared to she. In other words,
"He" occurs xx% more than the word "she"
Thanks
just take numbers of "he" divide it by the number of "she" then multiple the result by 100:
let
$n1$ is how much word1 showup
$n2$ is how much word2 showup
then the percentage $p$ is:
$p=\frac{n1}{n2} \cdot 100$