model recommendation

[KIM SUJIN]

dear statlist,

I do appreciate your help all the time!


I do regress with 'Heckman gravity model'

I hope to regress the impact of SPS measure and Regionalization (dummy variable)

SPS= trade ban, when there are diseases
Regionalization = diseases free area

Regionalization is only possible when SPS is 1

SPS = 1 Regionalization =1

SPS = 1 Regionalization =0


if SPS is 0, Regionalization is always 0

I regressed these two variables as separate variables, however, it actually has a relationship, so I wonder which model or correction I need.




T= G_i +G_j +D_ij + SPS_ij + Regionalization _ij


sps , regionalziaotn =1 when it is applied
G_i = GDP_i
G_j = GDP_j
D_ij = distance _ij

T= trade value _ij
i= import country
j=export country

panel data


Any one help??

11!!!
Thank you so much!!

[Phil Bromiley]

You didn't get a quick answer. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

In general, there is not a problem with having the two dummies. You could alternatively make a three valued indicator 1 if S=0, 2 if S=1 R=1, 3 if S=1 R=0, and then include i.indicator in the regression. You're then estimating different dummies for each of the three conditions in your data.