PANEL Procedure
Functional Summary
The statements and options available in the PANEL procedure are summarized in Table 1.
Table 1: Functional Summary
| Description | Statement | Option |
|---|---|---|
| Data Set Options | ||
| Includes correlations in the OUTEST= data set | PROC PANEL | CORROUT |
| Includes covariances in the OUTEST= data set | PROC PANEL | COVOUT |
| Specifies the input data set | PROC PANEL | DATA= |
| Specifies variables to keep but not transform | FLATDATA | KEEP= |
| Specifies the output data set for the CLASS statement | CLASS | OUT= |
| Specifies the output data set | FLATDATA | OUT= |
| Specifies the name of an output SAS data set | OUTPUT | OUT= |
| Writes parameter estimates to an output data set | PROC PANEL | OUTEST= |
| Writes the transformed series to an output data set | PROC PANEL | OUTTRANS= |
| Requests that the procedure produce graphics via the Output Delivery System | PROC PANEL | PLOTS |
| Declaring the Role of Variables | ||
| Specifies BY-group processing | BY | |
| Specifies the classification variables | CLASS | |
| Converts the data to uncompressed form | FLATDATA | |
| Specifies the cross-sectional and time ID variables | ID | |
| Declares instrumental variables | INSTRUMENTS | |
| Lag Generation | ||
| Specifies output data set for lags whose missing values are replaced by the cross-sectional mean | CLAG | OUT= |
| Specifies output data set for lags that leave missing values unchanged | LAG | OUT= |
| Specifies output data set for lags whose missing values are replaced by the time period mean | SLAG | OUT= |
| Specifies output data set for lags whose missing values are replaced by the overall mean | XLAG | OUT= |
| Specifies output data set for lags whose missing values are replaced by zero | ZLAG | OUT= |
| Printing Control Options | ||
| Prints correlations of the estimates | MODEL | CORRB |
| Prints covariances of the estimates | MODEL | COVB |
| Suppresses printed output | MODEL | NOPRINT |
| Requests that the procedure produce graphics via the Output Delivery System | MODEL | PLOTS |
| Prints fixed effects | MODEL | PRINTFIXED |
| Performs tests of linear hypotheses | TEST | |
| Model Estimation Options | ||
| Specifies the Amemiya-MaCurdy model | MODEL | AMACURDY |
Requests the  statistic for serial correlation under fixed effects | MODEL | BFN |
| Requests the Baltagi and Li joint Lagrange multiplier (LM) test for serial correlation and random cross-sectional effects | MODEL | BL91 |
| Requests the Baltagi and Li LM test for first-order correlation under fixed effects | MODEL | BL95 |
| Requests the Breusch-Pagan test for one-way random effects | MODEL | BP |
| Requests the Breusch-Pagan test for two-way random effects | MODEL | BP2 |
| Requests the Bera, Sosa Escudero, and Yoon modified Rao’s score test | MODEL | BSY |
| Specifies the between-groups model | MODEL | BTWNG |
| Specifies the between-time-periods model | MODEL | BTWNT |
| Requests the Berenblut-Webb statistic for serial correlation under fixed effects | MODEL | BW |
| Requests cross-sectional dependence tests | MODEL | CDTEST |
| Requests the clustered HCCME estimator for the covariance matrix | MODEL | CLUSTER |
| Specifies the Da Silva method | MODEL | DASILVA |
| Requests the Durbin-Watson statistic for serial correlation under fixed effects | MODEL | DW |
| Specifies the first-differences dynamic panel model | MODEL | DYNDIFF |
| Specifies the system dynamic panel model | MODEL | DYNSYS |
| Specifies the one-way fixed-effects model | MODEL | FIXONE |
| Specifies the one-way fixed-effects model with respect to time | MODEL | FIXONETIME |
| Specifies the two-way fixed-effects model | MODEL | FIXTWO |
| Specifies the first-difference models for one-way models | MODEL | FDONE |
| Specifies the first-difference models for one-way models with respect to time | MODEL | FDONETIME |
| Specifies the first-difference models for two-way models | MODEL | FDTWO |
| Specifies the Moore-Penrose generalized inverse | MODEL | GINV=G4 |
| Requests the Gourieroux, Holly, and Monfort test for two-way random effects | MODEL | GHM |
| Requests the HAC estimator for the variance-covariance matrix | MODEL | HAC |
| Requests the HCCME estimator for the covariance matrix | MODEL | HCCME= |
| Requests the Honda test for one-way random effects | MODEL | HONDA |
| Requests the Honda test for two-way random effects | MODEL | HONDA2 |
| Specifies the Hausman-Taylor model | MODEL | HTAYLOR |
| Requests the King and Wu test for two-way random effects | MODEL | KW |
| Specifies the order of the moving average error process for the Da Silva method | MODEL | M= |
| Suppresses the intercept term | MODEL | NOINT |
| Specifies the Parks method | MODEL | PARKS |
Prints the  matrix for the Parks method | MODEL | PHI |
| Specifies the pooled model | MODEL | POOLED |
| Requests poolability tests for one-way fixed effects and the pooled model | MODEL | POOLTEST |
| Specifies the one-way random-effects model | MODEL | RANONE |
| Specifies the two-way random-effects model | MODEL | RANTWO |
| Prints autocorrelation coefficients for the Parks method | MODEL | RHO |
| Controls the check for singularity | MODEL | SINGULAR= |
| Specifies the method for the panel unit root/stationarity test | MODEL | UROOTTEST= |
| Specifies the method for the variance components estimator | MODEL | VCOMP= |
| Specifies linear equality restrictions on the parameters | RESTRICT | |
| Performs tests of linear hypotheses | TEST | WALD, LM, LR |
| Requests the Wooldridge (2002) test for the presence of unobserved effects | MODEL | WOOLDRIDGE02 |
| Comparing Models | ||
| Create tables that display side-by-side model comparisons | COMPARE |
Last updated: June 19, 2025