April 2026 - Gretl-users - gretlml.univpm.it

It is necessary to use robust standard error in random effect estimation

by Ramki S

When I run the code in the stata, the results are matching with gretl only when I specify the robust standard errors. Why is this case? xtreg ANS FDIENT FDICAP FDIAST FDITUR FDIGDP FDIROTC FDIROFA FDIROS FDIEMP FDICOM FDIWAG GDPgrowth Size, re > Random-effects GLS regression Number of obs = 434 Group variable: Id Number of groups = 62 R-squared: Obs per group: Within = 0.7754 min = 7 Between = 0.0372 avg = 7.0 Overall = 0.1280 max = 7 Wald chi2(13) = 525.11 corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000 ------------------------------------------------------------------------------ ANS | Coefficient Std. err. z P>|z| [95% conf. interval] -------------+---------------------------------------------------------------- FDIENT | .3538051 .1119847 3.16 0.002 .1343191 .5732911 FDICAP | .0560138 .0341982 1.64 0.101 -.0110135 .123041 FDIAST | -.0488365 .027242 -1.79 0.073 -.1022297 .0045567 FDITUR | -.0249275 .0195643 -1.27 0.203 -.0632728 .0134179 FDIGDP | .0761888 .0221277 3.44 0.001 .0328193 .1195583 FDIROTC | -.0140346 .0176176 -0.80 0.426 -.0485645 .0204953 FDIROFA | .0029775 .0053075 0.56 0.575 -.007425 .01338 FDIROS | -.0061958 .0053613 -1.16 0.248 -.0167037 .004312 FDIEMP | .0093037 .0294696 0.32 0.752 -.0484557 .0670631 FDICOM | -.0078266 .0252738 -0.31 0.757 -.0573623 .041709 FDIWAG | -.2533413 .3531677 -0.72 0.473 -.9455373 .4388548 GDPgrowth | .0565587 .0193329 2.93 0.003 .0186669 .0944505 Size | -12.14111 .6405544 -18.95 0.000 -13.39658 -10.88565 _cons | 69.71459 2.813264 24.78 0.000 64.2007 75.22849 -------------+---------------------------------------------------------------- sigma_u | 1.6051608 sigma_e | 1.0781735 rho | .68909913 (fraction of variance due to u_i) ------------------------------------------------------------------------------ Hausman test results are also different. Hausman test - Null hypothesis: GLS estimates are consistent Asymptotic test statistic: Chi-square(13) = 341.943 with p-value = 3.83701e-65 Stata: Test of H0: Difference in coefficients not systematic chi2(13) = (b-B)'[(V_b-V_B)^(-1)](b-B) = -918.16 Warning: chi2 < 0 ==> model fitted on these data fails to meet the asymptotic assumptions of the Hausman test; see suest for a generalized test. With sigmamore: Test of H0: Difference in coefficients not systematic chi2(13) = (b-B)'[(V_b-V_B)^(-1)](b-B) = 237.83 Prob > chi2 = 0.0000 data: https://www.dropbox.com/scl/fi/o9copqsun64if9n7vyu4r/2017035-data.dta?rlk...

15 hours, 38 minutes

4
3
0 / 0

Mixed command equivalent in gretl

by Ramki S

Hi, I am trying to replicate the results of an interesting paper by John antonakis. And they estimated a few models with mixed command of stata. Do we have ML estimator to replicate models 7 and 8. *7 MLE RE with Level 1 predictor, its cluster mean, and Level 2 predictor mixed y x x_cl z || lead_n: est store one *compare above estimate with below using likelihood ratio test mixed y x z || lead_n: est store two lrtest one two *8 ML RE with cluster-mean centered Level 1 predictor and Level 2 *predictor gen x_grp_cen = x - x_cl mixed y x_grp_cen x_cl z || lead_n: Datafile: https://www.dropbox.com/scl/fi/fqqenv2jlf5sxp1qe5a0o/antonakis_randomeffe... Paper: https://www.dropbox.com/scl/fi/zgqu5mv2doavbv66m3ako/antonakis2019_orm_ra... do file: https://www.dropbox.com/scl/fi/8aknnw6lg5qd6p425ox96/antonakis_random-eff...

1 day, 17 hours

2
1
0 / 0

Missing value handling and correlated random effects CRE model

by Ramki S

I tried to replicate the following stata webpage example in gretl by creating cwc variables for tenure and age. After running, the number of observations are different and race_1 coefficient is very different although other coefficients are comparable. Any suggestions? https://www.stata.com/stata-news/news39-4/correlated-random-effects-models/ Model 1: Random-effects (GLS), using 28522 observations Included 4699 cross-sectional units Time-series length: minimum 1, maximum 15 Dependent variable: ln_wage Standard errors clustered by unit coefficient std. error z p-value --------------------------------------------------------- const 1.07919 0.0308898 34.94 2.07e-267 *** tm_tenure 0.0586924 0.00210393 27.90 2.93e-171 *** tm_age 0.0111681 0.00113419 9.847 7.08e-023 *** Drace_1 0.131393 0.0117410 11.19 4.52e-029 *** Drace_3 0.236570 0.0592482 3.993 6.53e-05 *** Mean dependent var 1.675133 S.D. dependent var 0.478001 Sum squared resid 5607.429 S.E. of regression 0.443427 Log-likelihood −17274.26 Akaike criterion 34558.52 Schwarz criterion 34599.81 Hannan-Quinn 34571.80 rho 0.311897 Durbin-Watson 1.017081 'Between' variance = 0.106527 'Within' variance = 0.102584 mean theta = 0.577464 corr(y,yhat)^2 = 0.13988 Joint test on named regressors - Asymptotic test statistic: Chi-square(4) = 1467.73 with p-value = 0 Breusch-Pagan test - Null hypothesis: Variance of the unit-specific error = 0 Asymptotic test statistic: Chi-square(1) = 20404.8 with p-value = 0 Data: https://www.dropbox.com/scl/fi/zd5od9r00esst52obcxtm/nlsdata.dta?rlkey=nu...

1 day, 18 hours

1
1
0 / 0

Package updates (March 2026)

by Riccardo (Jack) Lucchetti

Dear all, this message is to inform the community about the activity in our function package repository: during the month of March 2026, 2 packages were updated to a new version: "CSDpanel", by Sven Schreiber and Jörg Breitung (test and estimators for panel datasets with cross-section dependence) "TVCplots", by Ekkehart Schlicht (plot time-varying series with confidence bands) As usual, update and enjoy! ------------------------------------------------------- Riccardo (Jack) Lucchetti Dipartimento di Scienze Economiche e Sociali (DiSES) Università Politecnica delle Marche (formerly known as Università di Ancona) r.lucchetti(a)univpm.it http://www2.econ.univpm.it/servizi/hpp/lucchetti -------------------------------------------------------

3 days, 14 hours

1
0
0 / 0

Grand mean centering, groupmean, cwc variable creation

by Ramki S

Hi Is there any option to create grand mean centering of a varibale x_mc, (x_i - x_bar), group mean (x_barj), centering within clustered variable x_cwc (x_i - x_barj). These are necesary functions to teach mixed models. If there are not, i request you to provide.

5 days

3
8
0 / 0

OLS Results mis-match

by Ramki S

Hi, I tried to run simple OLS but the results are not matching. The SPSS results are matching with text book results. SPSS results: Coefficients Model B Std. Error Beta t Sig. 1 (Constant) 1158559.201 360592.720 3.213 .002 Q 2026114.340 61806.945 .907 32.781 .000 PF 1.225 .104 .339 11.814 .000 LF -3065753.131 696327.318 -.136 -4.403 .000 a Dependent Variable: C GRETL: Model 2: OLS, using observations 1-90 Dependent variable: C Omitted due to exact collinearity: LF coefficient std. error t-ratio p-value ----------------------------------------------------------------- const 1.58686e+06 154259 10.29 1.05e-016 *** Q −32683.7 2587.90 −12.63 2.23e-021 *** PF 2.16835 0.205182 10.57 2.83e-017 *** Mean dependent var 1122524 S.D. dependent var 1192075 Sum squared resid 3.44e+13 S.E. of regression 628752.4 R-squared 0.728055 Adjusted R-squared 0.721803 F(2, 87) 116.4586 P-value(F) 2.51e-25 Log-likelihood −1327.813 Akaike criterion 2661.626 Schwarz criterion 2669.126 Hannan-Quinn 2664.651 https://www.dropbox.com/scl/fi/ndhl6sauxeeuufzl2wa6x/gujarati_Table16_1_a...

5 days, 13 hours

4
12
0 / 0

Add cross sectional mean is giving time series mean

by Ramki S

I loaded this data into gretl and told that this is time series stacked data. I wanted to create Y_barj varibale. but the result is different. I expected that 4, 6, 8 are the means for clusters. Did I do anything wrong here. unit year y 1 1 2 1 2 4 1 3 6 2 1 3 2 2 6 2 3 9 3 1 4 3 2 8 3 3 12 xm_y 1:1 3 1:2 6 1:3 9 2:1 3 2:2 6 2:3 9 3:1 3 3:2 6 3:3 9

5 days, 14 hours

2
1
0 / 0

Time fixed effects option

by Ramki S

What is the gretl option for the following stata code? Table 14.1, Time effects. xtreg logc logq logf lf, i(t) fe https://stats.oarc.ucla.edu/stata/examples/greene/econometric-analysis-fo...

5 days, 14 hours

2
1
0 / 0

Suggestion for stacked cross section terminology for

by Ramki S

Many of my students got confusion regarding this terminology used by gretl for importing data. Stacked time series and Stacked cross sections. Can you provide a brief description about the organization of the data like below or any other suitable name or example? The help is ok, but these options are easy to understand. Why grouped by? This is a very famous verb in dplyr R package. Stacked time series (grouped by Units) Stacked cross sections (grouped by Time)

5 days, 14 hours

1
0
0 / 0

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Gretl-users April 2026