I am trying to create a linear regression model containing two predictors and 1 response variable. My response variable has a short term pattern, i.e. surge during weekdays and slump during weekends and I suspect this pattern is a result of two things: 1) A natural trend - people are more active on weekdays and 2) Partially related to my independent variables which follows a similar pattern.
There is also lagged cross-correlation between predictor and response.
Should I take some steps to normalize the data before running a linear regression? I've been reading about detrending time series, ARIMA, moving averages etc. but am a little lost on the right approach. Attached below are are time series plots of the predictor and response and the lagged cross correlation.
