Re: st: Interpretation of interaction term in log linear (non linear) model

[Suryadipta Roy <sroy2138@gmail.com>]

Dear David,
Thank you very much for the references! I would read them very
carefully to understand the procedures better. The papers that have
used Poisson (I referred to in the thread before) did not go into
goodness of fit. I recently came across a paper that have used the
procedure that you have mentioned, i.e. of running a separate Probit
regression to explain propensity to import. I would try to do some
residual analysis to explain goodness of fit for my paper as you have
suggested.

Best regards,
Suryadipta.

On Fri, Jun 21, 2013 at 11:16 PM, David Hoaglin <dchoaglin@gmail.com> wrote:
> Dear Suryadipta,
>
> Thank you for the compliment.  As it happens, though, I have not had
> enough information about your data and your analysis to write anything
> approaching a referee's report.
>
> Assessing the fit of a model should involve much more than calculating
> a single number such as R-squared.  One usually looks for influential
> data and makes a variety of plots of residuals.  If the papers that
> have used Poisson models used data that had a substantial percentage
> of zeros, and did not do anything special about the zeros, I suspect
> that those models did not fit very well.  Did the authors not give any
> empirical evidence on how well their models fit?
>
> If propensity to import could be treated as a binary outcome (positive
> imports versus zero imports), one part of the analysis could use
> logistic regression (or a probit model, if you prefer).
>
> If theory favors the use of a fixed effect for each trading pair, what
> does that theory say about how to handle the connections among trading
> pairs that involve the same country?
>
> The project in which we split each set of data into three parts
> produced several papers.  The first of those papers is
> Pine M, Jordan HS, Elixhauser A, et al.  Enhancement of claims data to
> improve risk adjustment of hospital mortality.  Journal of the
> American Medical Association 2007; 297:71-76.
> The chapter on model assessment and selection in the book by Hastie,
> Tibshirani, and Friedman (2009) has some discussion of splitting a
> dataset into a training set (50%), a validation set (25%), and a test
> set (25%).
>
> David Hoaglin
>
> Hastie T, Tibshirani R, Friedman J (2009).  The Elements of
> Statistical Learning.  Springer.
>
> On Tue, Jun 18, 2013 at 6:05 PM, Suryadipta Roy <sroy2138@gmail.com> wrote:
>> Dear David,
>>
>> Thank you very much for the comments and the wonderful suggestions!
>> These almost read like a referee report! I had to take some time to
>> reply to your comments since the issues that you have raised are
>> substantive. Theoretical work in the gravity model of trade literature
>> mainly suggest the importance of structural factors that prevent
>> countries from trading with each other. Some of the important papers
>> have used -heckman- selection models but that model is more suitable
>> to explain why countries export (or do not export), while my research
>> question focuses on the propensity to import. Moreover, the exclusion
>> restrictions in the selection equation are still not very well
>> founded. The papers that have used Poisson models have not reported
>> the goodness of fit. -poisson- by itself reports a pseudo-rsquare
>> which is not comparable to the linear r-square, while -xtpoisson- or
>> -xtpqml- that I have implemented does not report any r-square. The
>> cluster-robust standard errors address both the problems of
>> overdispersion and serial correlation (Cameron and Trivedi,
>> Microeconometrics using Stata, 2010). It is theory here that guides
>> the use of fixed effects, e.g. I need to incorporate 5638 trading pair
>> fixed effects (since I have 76 countries with complete data, I can
>> have a maximum of 76*75 = 5700 trading pair relationships).
>>
>> Your suggestions on model building by splitting the data have been
>> extremely illuminating. However, I was wondering if you could give me
>> a bit more concrete suggestions as to how to go about it, e.g. could
>> you kindly give me the reference to the paper where you undertook the
>> data splitting approach so that I could read a bit more about it?
>>
>> Best regards,
>> Suryadipta.
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/