Hi Statalist team,

I have detrended dataon malaria contraction rates to see the seasonal fluctuations. The patterns emerging from the de-trended data are strong, with strong peak in the rainy season as expected. However, I am not sure how to interpret the trend data itself.

I ran the following:

regress u5s_malaria_per date2
predict malaria_detrended, resid
predict malaria_trend, xb

I assumed the "malaria_trend" would just be the average across time or the sum of detrended and trended would amount to the raw data, but this is not the case. The trend data is far higher than the average. What is the appropriate way to interpret the trend?

Apologies for the no doubt obvious questions