My first impression is to follow Cameron and Worswick (1999), because Cameron sounds as a surname worthing trust. However, you may have more serious evaluation of their method by other Statalist members if you provide a complete reference.
I also have a second-best solution. If I understand correctly, you have income as a dependent variable, and two endogenous term, the interaction effects of crop loss and labour supply with farm assets. You can use -ivreg- and search in Statalist archivers for how to deal with interacted endogenous variables. I have readen something about it but I can't recall exactly where.
Nicola
At 02.33 09/10/2007 -0400, "fmodena" wrote:
>Dear all,
>
>I am looking at the effects of a crop loss and the labour supply response to
>the crop loss on household income in rural Indonesia. The household income
>is regressed on the dummy crop loss (CL) interacted with the value of farm
>assets and on the dummy labour supply as a response to the crop loss (LS)
>interacted with the value of farm assets. Note that LS (labour supply
>response) is observed only for those who had the crop loss (CL=1), but I
>replaced LS=0 if CL=0.
>The estimated crop loss effect and labour supply effect are then included in
>the expenditure equation, to test weather households reduce consumption in
>the face of a crop loss, and weather the labour supply response to the shock
>influences the decisions to cut expenditure.
>
>The labour supply response to a crop loss may be endogenous in the income
>equation (least squares estimation may lead to biased estimates of the
>parameter). I cannot use a treatment effect model (treatreg) to control for
>the endogeneity of the labour supply because the dummy LS is interacted with
>the farm assets (which is a continuous variable). Hence I followed the
>procedure proposed by Cameron and Worswick (1999). The authors employ a
>switching regression model with endogenous switching. This method involves a
>two stage procedure:
>1) estimate a probit equation with the dummy LS as dependent variable
>(using the sub-sample for which CL=1). Then calculate the two selection
>terms (inverse Mills's ratio) for labour supply respondent (LS=1) and for
>non labour supply respondents (LS=0)
>2) the two selection terms are included into the income equation (using
>the entire sample)
>
>I am not completely satisfied by that procedure (the two selection terms
>seem not able to capture the endogeneity of LS in the income equation). I am
>also wondering weather the movestay command could help me (instead of using
>the two stage approach).
>
>Any assistance will be appreciated
>Francesca
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
