LSMEANS in time series

_MooMoo — Sat, 10 Oct 2020 21:37:34 GMT

Hello!

I fitted piecewise linear regression. The model specification is as follows...

,where

Intervention was being in effect right after block 24. Through this model, my ultimate goal is to check whether the rate has changed from pre-intervention to post-intervention. The reason why I chose piecewise model is because I also wanted to check how rate change overtime before and after intervention.

To check the ultimate goal, I ran following code...

proc glm data=X;

class intervention;

model rate=intervention block spline;

lsmeans intervention/cl;

run;

However, LSMEANS statement wouldn't give me the answer I want. Actually, LSMEANS statement would give me pre-intervention and post-intervention rate when block variable and spline variable were set to its mean value. This is not what I wanted.

Does anyone has an idea how to output the mean rate of pre-intervention and mean rate of post-intervention from the model?

Thank in advance!

Re: LSMEANS in time series

SteveDenham — Tue, 13 Oct 2020 13:50:49 GMT

Question 1: What is 'spline' doing here?

Question 2: Isn't 'intervention' completely confounded with Block (i.e., Intervention=pre when Block<24, intervention=post when Block >=24?

Perhaps you could fit the segmented model without 'intervention' in the model. Then when you get to the GLM phase, use an ESTIMATE or LSMESTIMATE to get the marginal means for intervention pre and intervention post. I still don't know how to get around the spline issue - perhaps an AT option could be used in the LSMESTIMATE statement.

SteveDenham

topic LSMEANS in time series in Statistical Procedures

LSMEANS in time series

Re: LSMEANS in time series