Thank you, Gloria! The percentages don’t total 100% because it is not an exhaustive list. There are a lot of other factors at play that are not (or cannot) be measured.

To make it even more complicated, there is some intercorrelation between variables. This means that you cannot simply ‘add’ them to come up with a total percentage that predicts turnover.

Great question, Sudeep!

The simplest test is (logistic) regression. This is most helpful in explaining drivers of turnover. More advanced tests include various survival analyses. Alternatively, you can use decision trees/random forests and other advanced machine learning algorithms that enable the prediction of turnover.

Check the following links to read more technical articles with examples:
– https://www.aihr.com/blog/applying-survival-analysis-reduce-employee-turnover-practical-case/
– https://www.aihr.com/blog/tutorial-people-analytics-r-employee-churn/

Regards,
Erik

Great read it was, indeed.

Can you share some tips on how we can predict an employee attrition? What statistical test can be used for predicting employee attrition?

Thanks in advance!

regards,
Sudeep

Hi Alyssa,
Great question! The authors do not mention this explicitly in the article but I expect the dataset to contain predominantly data on the US and Europe.

Great addition Marc, you’re spot on!

Hi David, I see I forgot to include the reference to the meta study. The study is called “A meta-analysis of antecedents and correlates of employee turnover: Update, moderator tests, and research implications for the next millennium.” by Griffeth, Hom & Gaertner. I will edit the article to include the reference.