Marginal Effects/Elasticities

[abhaylidbe]

@arteagac Very much thankful to you for this wonderful package. Is there a way to get the marginal effects or elasticities of the model variables?

[arteagac]

Hi @abhaylidbe. Thank you for your kind comments.
Unfortunately, the current version of xlogit does not support computation of marginal effects or elasticities. This is something I have in my to-do list, but I haven't had the chance to implement it yet.

[abhaylidbe]

Cristian, Thanks for the reply. ME/Elasticities are very important for our work. I wish you can implement it soon. At least, is there a way to manually derive it once we have the model results? If so, would like to discuss it with you. LMK. Abhay D. Lidbe | Associate Research Engineer

…

---------------------------------------------------------------- Alabama Transportation Institute The University of Alabama<https://www.ua.edu/> 3051, Cyber Hall Box 870288 248 Kirkbride Lane,Tuscaloosa, AL 35487 Mobile 205-393-4031<tel:205-393-4031> | Fax 205-348-6862<tel:(205)%20348-6862> ***@***.******@***.***> | http://ati.ua.edu<http://ati.ua.edu/>

---------------------------------------------------------------- From: Cristian ***@***.***> Sent: Thursday, October 20, 2022 10:49 PM To: ***@***.***> Cc: Abhay ***@***.***>; ***@***.***> Subject: [EXTERNAL] Re: [arteagac/xlogit] Marginal Effects/Elasticities (Issue #13) Hi @abhaylidbe<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgit.luolix.top%2Fabhaylidbe&data=05%7C01%7Cadlidbe%40ua.edu%7C365fbfbe4a024b591cfe08dab3174381%7C2a00728ef0d040b4a4e8ce433f3fbca7%7C0%7C0%7C638019209757817435%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=2%2Bt1BSqrotjPNaSMaAtSK5dCR3tQleHdQXxOdlneOAU%3D&reserved=0>. Thank you for your kind comments. Unfortunately, the current version of xlogit does not support computation of marginal effects or elasticities. This is something I have in my to-do list, but I haven't had the chance to implement it yet. — Reply to this email directly, view it on GitHub<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgit.luolix.top%2Farteagac%2Fxlogit%2Fissues%2F13%23issuecomment-1286422004&data=05%7C01%7Cadlidbe%40ua.edu%7C365fbfbe4a024b591cfe08dab3174381%7C2a00728ef0d040b4a4e8ce433f3fbca7%7C0%7C0%7C638019209757817435%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=jeI56heMHhvrzeGXHti7UH6apPJiUZIB4i2o%2BoI43ak%3D&reserved=0>, or unsubscribe<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgit.luolix.top%2Fnotifications%2Funsubscribe-auth%2FAFLP4YGV6UNNM5FJ5QWNGULWEIHEXANCNFSM6AAAAAARKUU6OE&data=05%7C01%7Cadlidbe%40ua.edu%7C365fbfbe4a024b591cfe08dab3174381%7C2a00728ef0d040b4a4e8ce433f3fbca7%7C0%7C0%7C638019209757817435%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=vlFtr7VGi8LzycUYC0FNGlbrLYzv%2BSDEn2r8YiaXpIo%3D&reserved=0>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[arteagac]

Hi @abhaylidbe, Sure. Let me think about a potential implementation timeline and I will let you know.

[arteagac]

Dear Abhay, After estimating the effort involved in this implementation, I anticipate it would take at least a couple of months for completion given that my time is very limited right now. In case you know some Python programming and want to give this implementation a try, I would be happy to provide any necessary guidance on the internal functions inxlogit that you would need to modify.

[abhaylidbe]

Hello Cristian, Hope you are doing well. I'm reaching out to you to check if you were able to add marginal effects/elasticities to XLOGIT. If not, can you please guide me in deriving the effects in Python. Regards, Abhay D. Lidbe | Associate Research Engineer

…

---------------------------------------------------------------- Alabama Transportation Institute 3013, Cyber Hall Box 870288 248 Kirkbride Lane,Tuscaloosa, AL 35487 Mobile 205-393-4031<tel:205-393-4031> | Fax 205-348-6862<tel:(205)%20348-6862> ***@***.******@***.***> | http://ati.ua.edu<http://ati.ua.edu/>

----------------------------------------------------------------

________________________________ From: Cristian Arteaga ***@***.***> Sent: Saturday, October 29, 2022 1:23 PM To: arteagac/xlogit ***@***.***> Cc: Abhay Lidbe ***@***.***>; Mention ***@***.***> Subject: [EXTERNAL] Re: [arteagac/xlogit] Marginal Effects/Elasticities (Issue #13) Dear Abhay, After estimating the effort involved in this implementation, I anticipate it would take at least a couple of months for completion given that my time is very limited right now. In case you know some Python programming and want to give this implementation a try, I would be happy to provide any necessary guidance on the internal functions inxlogit that you would need to modify. — Reply to this email directly, view it on GitHub<#13 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AFLP4YEEH233FJFBMIG7XQ3WFVTTNANCNFSM6AAAAAARKUU6OE>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[arteagac]

Hi @abhaylidbe,

I truly apologize for my delayed response. The margin effects/elasticities is a very desirable implementation for xlogit, but unfortunately time is a bit constrained right now, and I don't think I will be able to complete it in the nearby future. In case you want to give this implementation a shot and you are clear about the formulas and concepts involved, I could happily guide you with the Python programming part.