Dear all,
I�m estimating a Poisson model, which includes an interaction term as follows:
(ln)Y=a+b1x1+b2x2+b12x1*x2
and I need to compute the impact (marginal effect) of x1 on lnY.
I have found on SJ an article �Computing interaction effects and standard
errors in Logit and Probit models�, by Norton, Wang and Ai (2004), who warn
that for nonlinear models:� First, the interaction effect could be nonzero even
if b12 = 0. (�) Second, the statistical significance of the interaction effect
cannot be tested with a simple t-test on the coefficient of the interaction
term b12. Thirdly, the interaction effect is conditional on the independent
variables, unlike the interaction effect in linear models. (It is well known
that the marginal effect of a single uninteracted variable in a nonlinear model
is conditional on the independent variables). Fourthly, the interaction effect
may have different signs for different values of covariates. Therefore, the
sign of b12 does not necessarily indicate the sign of the interaction effect�
(page 156).
Please notice that my interest is computing the effect of x1 on lnY , I�m
not interested in the marginal effect of the interaction term, nor in the
effect of x1 on E(Y), because my dependent variable is not a count.
Since there is the interaction I cannot conclude that the impact of x1 on lnY
is just b1.
In a linear model I could apply the following formula:
marginal effect of x1= b1+ b12*x2,
and compute the relative standard errors sqrt(varb1+var b12*x22+2x2covb1b12)
However, according to Norton et al. (2004), I cannot employ the STATA
estimates in this way, as the interaction effect may have different signs for
different values of covariates.
How can I then compute (and possibly graph) the impact of x1 across the values
of x2 using STATA?
I would really appreciate any assistance with this issue
Maria
-------------------------------------------------
This mail sent through IMP: http://horde.org/imp/
*
* 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/
