And use MLE, not the two-step model.
On Tue, Nov 10, 2009 at 10:31 AM, Austin Nichols
<[email protected]> wrote:
> Steven D. Roper <[email protected]> :
> Cluster by panel; see help vce_option
>
> On Mon, Nov 9, 2009 at 9:06 PM, Steven D. Roper <[email protected]> wrote:
>> Hi all. Sorry about a second post on this subject. I just ran a Wooldridge
>> test for autocorrelation indicating that I have a problem with the panel
>> data that I am using with a two-step Heckman. What remedies are there now
>> for dealing with the auto correlation?
>>
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
