Dear Stata Expert,
I have a question related to interpretation of interaction terms in a Probit model.
In my analysis, I have typed the following command:
probit crime foreign econ_stat foreign#c.econ_stat i.country, cl(country)
My intent is to estimate the combined impact of being a foreign-born with a lowering of the economic status (for instance being materially deprived) on committing a crime.
The dependent variable crime is binary variable taking value 1 if the individual has committed a crime and 0 otherwise, foreign is a dummy variable taking value 1 if the individual is foreign-born, econ_stat is a level variable, the higher this variable, the worse the socio-economic status of the individual.
Say that the coefficient is -0.02, can I interpret it in the following way: "for a given socio-economic status, being foreign born reduces the possibility of committing a crime by 0.02 times or by 2 percentage points" (as if the probability is defined as a percentage from 0 to 100)? Alternatively, can I also conclude that "worsening the socio-economic status is associated with lower than average probability of committing a crime when the individual is foreign-born"?
I hope that my question is enough clear.
Many thanks.
Gianluca
Related Posts with Interaction terms in Probit Regression
Error reshaping from wide to longI am getting an error message as 'variable id does not uniquely identify the observations' while res…
Wonder how I should set my control and my treatment groups for a diff-in-diff regression?Hello! I'm looking to run my first diff-in-diff regression for my research project that talks about…
How to keep only the observations that are not repeated on a single string variable?Hello, I have a database that has repeated observations on a single variable. The problem is that t…
command pbalchk with fator variablesHello, I am trying t use the command pbalchk to examine the balance of covariates with ipw weights. …
Criteria for xtregar or xtglsHi Dear, As xtregar and xtgls are recommended for the panel dimensions when T>N, what is the cri…
Subscribe to:
Post Comments (Atom)
0 Response to Interaction terms in Probit Regression
Post a Comment