Dear Statalisters,
I’m running a regression model of the form below. The data consists of the values of a hormone for pregnant women measured at 3 time points.
Log (crh) = b0 + b1*time + b2*(time*time) + b3*group1 + b4*(group1*time)
In the model, group1 is 0 if the women had normal birth outcomes, 1 if the women had preterm birth outcomes. From the output I can get the equation for predicting crh for the normal birth outcomes as :
Log (crh) = b0 + b1*time + b2*(time*time)
and the equation for the preterm group as
Log (crh) = b0 + b1*time + b2*(time*time) + b3*group1 + b4*(group1*time)
Consider a second regression model of the form below:
Log (crh) = b0 + b1*time + b2*(time*time) + b3*group2 + b4*(group2*time)
In this model, group2 is 0 if the women had normal birth outcomes and 1 if they had healthy birth outcomes but had an Infection. The normal, preterm and the infection groups are mutually exclusive. In the second model, the equation to predict values of crh for the normal group would be:
Log (crh) = b0 + b1*time + b2*(time*time)
Since in both models the normal group has the same people, can the values of b0, b1 and b2 be the same for both models?
Thanks,
Leny
*
* 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/
