0
$\begingroup$

I am currently working on an analysis project where I wish to predict sickness levels of employees in different offices for a company for the remainder of 2017.

In the past, I have made predictions based purely on predictors and also just purely on the time series. For this project, I feel I need to combine the 2 types of forecasting for the must accurate results.

I have the following data available:

  • The past 4 years sickness data measured in hours per day per office.
  • The number of people working in the company in each office for each day of the year for the last 4 years.

I feel that combining these 2 measurements will lead to reasonably accurate forecasts. I can see that that the time series data has a seasonal element to it and a slowly declining trend. My problem is combining the employee numbers per office with historical sickness data per office.

Any help on this is much appreciated. I am attempting to do this in R but any theoretical advice is appreciated too or a book/website reccomendations for learning this kind of methodology. Thanks!

$\endgroup$
  • $\begingroup$ Please search on "user:3382 DAILY" for other posts/responses in this area and also post your data. You can incorporate (merge) predictor variables and time series structure including Intervention Detection schemes. It is called a Transfer Function . $\endgroup$ – IrishStat Jan 9 '17 at 20:43
  • $\begingroup$ a TF is also referred to as as a Dynamic Regression. Note that unless you incorporate daily effects including holidays etc your test of significance will be downwards biased based upon the bloated error sums of squares from an insufficient model. $\endgroup$ – IrishStat Jan 10 '17 at 15:33
2
$\begingroup$

This is called Dynamic regression and is described very well, with examples, in Hyndman & Athana­sopou­los (2016) chapter 9.1.

$\endgroup$
2
$\begingroup$

You can include exogenous time series, such as the number of employees, in an ARIMA forecast using the xreg argument in forecast::Arima or stats::arima. There is lots of guidance on this site if you search xreg or ARIMA with exogenous regressors.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.