PISA data-Repest

[Elcin Tuzel]

Hello,

I am working with PISA data, I have appended 2009, 2012 and 2015 PISA waves and I added variable for years for each wave. I want to run country fixed effect by adding dummy variables for years. However when I used the below code it kept giving me error message of debugging the command within the estimate option. I have used similar code only with 2015 (without year dummy) and it worked fine.

I used below code:

repest PISA, estimate(stata: areg pv@math d_gender stu_age i.immig pared hisei d_lang_at_home i.books d_homecomputer d_homeinternet schtype fund_gov num_teachers i.location_school schsize schsize2 clsize clsize2 i.year, absorb(cntryid)) results(add(N r2)) svyparms(final_weight_name(w_fstuwt) rep_weight_name(w_fsturwt) NREP(80) variancefactor(1/20))

Error message:

_pooled.....
There were no successful estimates for = _pooled.
Consider debugging the command within the estimate option:
areg pv5math d_gender stu_age i.immig pared hisei d_lang_at_home i.books d_homecomputer d_homeinternet schtype fund_gov num_tea
> chers i.location_school schsize schsize2 clsize clsize2 i.year [aw = w_fstuwt] , absorb(cntryid)
no observations

Could you please advice if it is because of my panel structure.

Thanking in advance

Elcin

[Daniel Foster]

Hi Eclin, I was wondering if this issue was ever resolved? Furthermore, I was wondering if you could share a bit about how you structured your data when appending multiple PISA waves. I have also appended 2000, 2003, 2006...2018 PISA waves, and added a variable for the year of each wave (titled "pisa_cylce). However, when I try to compute basic statistics like the mean, I get an error that reads "2015.....post __00000Z not found" and "2018.....post __00000Z not found", signalling that there is an issue with the 2015 and 2018 PISA data.

I recognize that there are 10 as opposed to 5 plausible values in the 2015 and 2018 waves. Also, the names for the replicant weights differ between the 2000-2012 waves and 2015-2018 waves, as well as the primary sampling unit (i.e., schlid vs. cntschoolid).

Could you please advise how you handle appending multiple PISA waves?