04-02-2018 06:24 PM - edited 04-02-2018 06:30 PM
Hello SAS Support Communities,
I received an error while running proc panel. I used the following code:
proc panel data=dissert1.restatements70;
id cik1 fyear;
model average_delay = negative_effect income_statement_restatement n_exincome_statement_restatement
pyceoltpercent npyceoltpercent pycfoltpercent npycfoltpercent inst_investors audit_committee_fin_exp auditor_change
nauditor_change restatement_impact periods fraud repeat_restater lev roa earn_var mb logta big4 sec_investigation
qtr_1 earnings_news company_age cik1 fyear / fixtwo hccme=4;
I received the following error:
ERROR: There is only one cross section or time series observation. Computations will be terminated.
I'm using company (cik1) and fiscal year (fyear) fixed effects in my model. I have observations from 2009 through 2015 in my sample. Ideally, I want two steps:
1. Run the model and figure out which variables have significant heteroskedasticity p-values.
2. Run the model with all the variables and use the hccme = 4 code for only the significant values from step one.
How do I correct my error? How should I run my model?
God bless, best regards, and thank you so much for your help,