threshold and moderation

[sedki zn]

Dear all,

i hope that you are doing good,

i would like to know if the threshold variable plays the same role of of the moderator variable in a linear regression ? ( the moderator variable in a linear relationship plays the same role of the threshold variable ?)

for example studding the moderating role of firm performance in the relationship between financial constraints (X) and risk taking (Y), here firm performance is the threshold variable. if we are studying the linear relationship, here firm performance is the moderator variable ? ( in other words, interaction (for linear regression) = moderation (for threshold regression) ?

Best regards
SEDKI

[sedki zn]

Dear River Huang,

i would appreciate your help

Best regards,
SEDKI

[sedki zn]

Dear Rich Goldstein,

i would appreciate your help

Best regards,
SEDKI

[River Huang]

Dear sedki, I personally agree that the threshold variable serves as a modertor in a regression.

[sedki zn]

Dear sedki, I personally agree that the threshold variable serves as a modertor in a regression.

thank you dear River for your answer.

for example , in my work i have studied the following relationships:

1. impact of financial constraints on CEO stock option using a threshold model
2. impact of CEO stock option on Risk taking using quantile regression
3. impact of financial constraints on risk taking using threshold model

then i have studied the moderated role of CEO stock option in the relationship between financial constraints and risk taking using threshold model.
( here, CEO stock options is the threshold variable). is this conceptually correct ? ( because using linear regression, mediation would be appropriated, not moderation)

[River Huang]

Dear sedki, Apart from the econometric techniques, it seems to me that what you have done is a "mediation" analysis in 1,2 and 3. The problem is that you use different nonlinear models, and then you talk about "moderation" analysis. It confuses me, and I suggest that you'd better to concentrate your work on a particular topic, whatever it is, and be consistent in using the econometric methods.

[sedki zn]

Thank you dear River Huang

Actually it is a PhD thesis of 4 chapters
in the last one I'm trying to study the moderating role because I am not aware of a nonlinear model which treats the mediation
so that's why I'm studying the moderation using threshold model. So I want to know if its somehow appropriated.
what would be your suggestion in this situation.

Best regards