@chadh712 wrote:
I don’t have a background in data science, I am an HR guy who was just pushed into a role of taking our HR data and turning it into something meaningful. I am not totally worthless, I have a good handle on statistics and have dabbled a little in R. That being said, I am totally stumped on where to do with a project I am working on.
We currently have all of our employees rate their day, everyday. They will give it a ‘good’, ‘neutral’, or ‘bad’ rating. The problem I am running into is what one person calls a ‘good’ day is another person’s ‘neutral’ day. And then, some use a ‘good’ rating as their baseline and go down while others use ‘neutral’ and go up or down from there. Because of all this variability I don’t know if it makes sense to look at this from a global perspective, so I have been trying to analyze from an individual perspective. What I am ultimately trying to get to is to give managers a heads up on any of their direct reports that could be at risk for attrition based on their daily rating.
I have been trying to use a Shewhart control chart, using a moving average of the past 10 days as the data points and using a 2 month look back for the UCL and LCL. But, since there is so much variability in the way everyone answers I can’t get the math to work correctly for a high percentage of people.
What are some suggested approaches I can take here? I am just at a loss for what to try next. Any help would be appreciated!
Posts: 1
Participants: 1