Hi,
I am fitting a model with a continuous outcome and an interaction between two binary predictors on the righthand side. In addition to measuring the interaction as a departure from additivity, which is what the coefficient of the interaction term implies, I would also like to calculate the interaction effect on the multiplicative scale. VanderWeele and Knol (2014, p. 60) point out that this can be done by fitting a log-linear regression. I am wondering if, instead, such a measure can be calculated using margins and nlcom?
After margins, I ran:
nlcom ln((_b[4._at]/_b[3._at])/(_b[2._at]/_b[1._at])).
But I am not sure if this is producing the estimate I am interested in. Any advice would be much appreciated.
I should mention that the reason I do not want to run a log-linear regression (in this context, I use this term to mean taking the log of the continuous outcome) is because my outcome is a standardized scale and has negative values.
Thank you!
Robbie Dembo
Related Posts with Multiplicative interaction with a continuous outcome
standard and generalized versions of the nonlinear Heckman two-step approachHello everyone, for my Master's thesis, I am trying to build a gravity model following the approach…
regression discontinuity- panel dataHi, I am new to rd design and analysis. I am working with a household panel data with the following …
Why reg conusmes more time than reghdfe in running regression on panel data?I have two codes below Code: reg dep_var indep_var i.unit i.period and Code: reghdfe dep_var ind…
How to track how long does it take when running a "do file" or a command?Normally I have some codes taking much time and I left the machine running by itself. But it should …
Comparing the code of reg and reghdfe in a panel data ?I have two sets of code as below, I am wondering what are the differences between these two sets of …
Subscribe to:
Post Comments (Atom)
0 Response to Multiplicative interaction with a continuous outcome
Post a Comment