I have collected employee turnover rates over the year. The attrition rates are as such:
I'm comparing these attrition rates to the industry benchmark rate of 1.44% by using a One-Sample t-test.
Is this correct, and if not, what is the best way to confirm if the Mean Attrition Rate in this year is significantly higher or lower than the industry benchmark?
I need to be able to make a statement and say that: "Year XXX has an employee attrition rate of X.X%, and this is (not) significantly higher/lower that the industry benchmark of X.X%"
In addition, if I were to compare Mean attrition rate of this year versus the previous year, is it correct for me to do a paired samples t-test, or should I do an Independent 2 Sample T-Test?
After giving this more thought, I'm thinking that if I were to test the means of percentages using the the t-test, what I am comparing is effectively the proportion, between 0 to 1, as a whole whether the proportions are significantly different...
However if I tested just the actual turnover headcount figures, I would be comparing the mean turnover headcount of a group of months vs (let's say for example) the mean turnover headcount vs a previous month... This would be a more direct measure of turnover, but because it's not a proportion, it's less meaningful because it's not based on any thing. I wanted to compare turnover rates because turnover rates = Leavers / Total Employees. The denominator here plays a significant role in moderating the turnover rate.