Dimitri Liakhovitski
2010-Jun-18 17:32 UTC
[R] pcse package - is it OK to use it when my regression is weighted by each subgroup's mean
Hello! Just would like to make sure I am not doing something wrong. I am running an OLS regression. I have several subgroups in the data set (locations) - and in each location I have weekly data for 2 years - on my DV and on all predictors. Looks like this: location week DV Predictor1 Predictor 2 location1 week1 xxx xxxxxxx xxxxxxxxx location1 week2 xxx xxxxxxx xxxxxxxxx . . . location2 week1 xxx xxxxxxx xxxxxxxxx location2 week2 xxx xxxxxxx xxxxxxxxx My DV variable was mean-centered - for each location and I am using this mean-centered DV as the DV in lm. Also, I am using the mean of each location as a weight when I run this regression. Would it still be correct to calculate pcse for this regression? I am not sure because pcse uses the group identifier - so am I not somehow double-counting things? Thank you very much! -- Dimitri Liakhovitski Ninah Consulting ninah.com
Reasonably Related Threads
- pcse package - clarifying question about arguments groupN and groupT
- Significance of interaction depends on factor reference level - lmer/AIC model averaging
- dynamic aggregation of many variables
- Does dsync handle client-side deletions?
- using csv file for stacked bar plot, rows to columns