Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.

# st: -robust- and -cluster- options in xtreg

 From "Narahari H.S." To statalist Subject st: -robust- and -cluster- options in xtreg Date Fri, 8 Mar 2013 19:36:34 +0800 (SGT)

Hello all,

My question is about the difference between -robust- and -cluster- options when using xtreg.

1) The stata output seems to suggest that some clustering is done in the robust option also. What is the difference in the clustering between the 2 options?
2) Under the cluster option, stata gives a blank Wald chi2. What could be causing this?

I have given the top portion of the stata output below

*******************************Using cluster option*******************************
Random-effects GLS regression          Number of obs      =      2351
Group variable: idn                             Number of groups   =       468

R-sq:  within  = 0.1830                         Obs per group: min =         1
between = 0.2300                         avg =       5.0
overall = 0.2089                            max =        18

Random effects u_i ~ Gaussian              Wald chi2(31)      =         .
corr(u_i, X)       = 0 (assumed)                Prob > chi2        =         .
(Std. Err. adjusted for 468 clusters in idn)

*******************************Using robust option*******************************

Random-effects GLS regression          Number of obs      =      2351
Group variable: idn                             Number of groups   =       468

R-sq:  within  = 0.1830                         Obs per group: min =         1
between = 0.2300                          avg =       5.0
overall = 0.2089                             max =        18

Random effects u_i ~ Gaussian                   Wald chi2(32)      =    679.48
corr(u_i, X)       = 0 (assumed)                Prob > chi2        =    0.0000
(Std. Err. adjusted for clustering on idn)

***************************************************************************************

I have detailed my regressions model below. Please let me know if further information will be helpful

I have an annual panel data of firms and am running the below regression model

xtreg depvar var1 var2 var1*var2 var3 var4 var5 var6 industrydummies

where
var1 and var2 are dummy variables (var1*var2 is their interaction)
depvar, var3-var6 are continuous variables
industrydummies are dummy variables (included to control for industry fixed effects)