Hi everyone,
Someone, kindly clarify the below for me.
1). Should one check for optimal lag per variable or all of the variable combined? example: varsoc ln_inc or example: varsoc ln_inc ln_inv ln_consump
2). Combine lag selection (example: varsoc ln_inc ln_inv ln_consump) gives equal lags for all of the variable while individual lag selection may give equal or different lag for variables. Is this a problem? Which one is best.
3). What is the maxlag() value to specify when check for optimal lag for daily, weekly, monthly, quarterly, and yearly
4). Should one check for serial correlation and heteroskedasticity before optimal lag specification or after running the regression. Which one is more appropriate? My understanding is that in presence of heteroskedasticity and serial correlation, there could be problem with optimal lag selection.
Thanks
Related Posts with Please Help
How to minimize identical successive observations ?Dear all, I'm working on a social policy for a job center. We are sending job recommendations to jo…
Individual class membership of latent class analysis via lclogitHello I have 3 questions concerning a latent class analysis via lclogit: 1) I ran a latent class m…
eventstudy2 updatedDear Members of the Statalist, A new version of eventstudy2 is available on SSC: NEW IN THIS VERSI…
Outline totals within Tab of 2 variables Hi there, I have a dataset where I`m looking at stores and the products in these stores. The stor…
interaction termim trying to measure the impact of child's health (height for age) on their school enrollment (0/1) …
Subscribe to:
Post Comments (Atom)
0 Response to Please Help
Post a Comment