I ran several PSMs for my data, and stumbled upon a BACI analysis which required matching method, but the writer (Wauchoppe) suggested to do Mahalanobis matching instead of the usual PSM. And it brought me to this lecture! Thank you for the clear explanation!
I did matching to trim my control set using PSM and I saw my matches, it was really bad. This made me look at other methods and I landed here. Thanks for sharing this. This is really helpful.
Excellent. Love the energy and content explanations- question. Where can I find the model frontier website/ algorithm. Which software is it coded on. Many thanks. Loved it!!
Thank you! Great talk. When working with say 20 variables, could I do PCA first and if the first two components explained 98% of variability, then run the matching using the 2 components instead?
one-to-many is better than one-to-one if you can match without losing match quality. you just wind up with more data and so lower variance. however, if you have to sacrifice match quality it can be worse
Great and clear video, thanks a lot! Maybe you could tell me how you derive the preprocessed sample in stata? I'm using psmatch2 for nn mahalanobis matching so far - but I sadly don't know how to receive the pruned data set to apply my DiD estimation on
Hi. In stata you can use de cem function (programed by King, et al.) to do all that.The code to install cem is "ssc install cem". There is a pdf with the explanation and step by step estimation with an example in gking.harvard.edu/files/gking/files/cem-stata.pdf
Wish all stats professors were this clear and engaging. Thanks, this helped a lot.
I ran several PSMs for my data, and stumbled upon a BACI analysis which required matching method, but the writer (Wauchoppe) suggested to do Mahalanobis matching instead of the usual PSM. And it brought me to this lecture! Thank you for the clear explanation!
Extraordinary explanation and adorable clarity. Thanks a lot!!!
I did matching to trim my control set using PSM and I saw my matches, it was really bad. This made me look at other methods and I landed here. Thanks for sharing this. This is really helpful.
What a clear and succinct explanation! Thank you Prof Gary.
Repenting my sins with PSM
Thank you so much ! I fully understand PSM now!
Thank you for the good lecture :) Your video is so very helpful for me to understand a matching method.
Thank you so much! This was exactly what I needed.
I want to give this a thousand likes!
Insofar as you were worried, you should know that I laughed out loud at your product placement joke 16 minutes in.
Thank you very much!
love the product placement
I just don't understand why all the videos have the audio skewed always to the left speaker, kind of annoying but the content is very good
I switched my audio to AG mode (same as for calls), and then it worked in both headphones!
Best wishes. Prof.
Excellent. Love the energy and content explanations- question. Where can I find the model frontier website/ algorithm. Which software is it coded on. Many thanks. Loved it!!
Love it! Thank you!
Amazing explanation!! Thank you
Thank you! Great talk. When working with say 20 variables, could I do PCA first and if the first two components explained 98% of variability, then run the matching using the 2 components instead?
clear and helpfull
Thats all well and good, but how do I use MDM in SPSS?
Hello, i have a question. if i have a countinuous variable, do i need to reshape to a categorical before running cem? thank you
Prof King, could you please tell us what statistical tool was used to visualise the data (e.g. the T and C groups)? Thanks!
One question I have is about whether one-to-one matching is better than one-to-many
one-to-many is better than one-to-one if you can match without losing match quality. you just wind up with more data and so lower variance. however, if you have to sacrifice match quality it can be worse
Great and clear video, thanks a lot! Maybe you could tell me how you derive the preprocessed sample in stata? I'm using psmatch2 for nn mahalanobis matching so far - but I sadly don't know how to receive the pruned data set to apply my DiD estimation on
Hi. In stata you can use de cem function (programed by King, et al.) to do all that.The code to install cem is "ssc install cem". There is a pdf with the explanation and step by step estimation with an example in gking.harvard.edu/files/gking/files/cem-stata.pdf
@@NegroChE6 Hi Gonzalo, thanks a lot!
hi, sir, this video is really helpful! thank you so much!!! :) may i know if the pdf version is available?
See j.mp/G2001