This channel provides information for people who are mainly interested to learn coding skills in different software, such as ArcGIS, Eviews, Excel, LaTex, MATLAB, Python, R, R Studio, SPSS, STATA, etc. However, this channel does have some entertainment, travel, and events videos in our everyday life.
Growing up in a rural village in Bangladesh (BD), We understand that technology is an important medium for learning nowadays. We started learning STATA from our undergraduate degrees in Economics in BD. Coming to the Ph.D. program in Economics at the University of New Mexico, we have an opportunity to learn a lot of software and use them in our research areas.
To get more coding videos, please subscribe to our channel. Stay tuned !! Happy Learning !!
Vedio is very helpful for beginners. I have one doubt that is have health insurance or have not health insurance, taken for which period (before or after) in your study? In DiD outcome variable, which period considered?
Hi, Thank you very much for your video. I tried exactly same thing but my stata will not plot the graph, after *eventdd asmrs pcinc asmrh cases i.year i.stfips, timevar(timeToTreat) ci(rcap) /// cluster(stfips) graph_op(ytitle("Suicide") xlabel(-20 (5) 25)) * command, Is there alternative way to plot it? (mine only shows the Linear regression result...)
Oh my Gosh you are AWESOME dude!!! I was looking at so many other methods to convert from Long to Wide and this by far..... by far the easiest way to do it! Thank you!
Hello! Thank you very much, the video was very helpful so I subscribed to your channel! I just have one question - the graph_op command doesn't work for me and I cannot install it either. How can I get such a nice graph like you?:) All the best
Thank you so much for your support for our channel. Did you install "eventdd" command in your stata? If not, please install it following my video 2:23. If yes, you can try again by reinstalling the command using the command line I have mentioned 2:23 in my video. Please let me know if that solves your problem. Thank you again.
@@Learn-Coding-with-Us I had a bug in the dataset, now it gives me the graph automatically, just like it should. Thanks for your help! All the best, Fabian
@@fabiangodelitz7307 Hi Fabian, Mine also didn't show the graph. What kind of bug do you have? Please give me a clue so that I can clean up my data. Thx!
hello madam, I noticed you removed the treatment and post dummy variables from the regression. I assume its because of collinearity. But does STATA not do this automatically, or do we have to do it manually?
Great video! I´m working on similar data but I get the message "no baseline found". What could be the reason for this? I have tried to xtreg my data... but I still get the same error
Hi! Thanks for the video, it is really helpful. I would like to perform a Difference in difference combined with inverse probability weighting IPW. I estimated the probit of treatment on the baseline year and obtained the propensity score weights. Now I want to weight the DiD with the inverse of the propensity score (IPW), that is, to estimate the treatment effect between the treated units and their matched control units. Any suggestions for the stata codes? Thank you :)
Hi, Thank you very much for your video. Do you think that similar analysis could be used to conduct an event study analysis on the impact of 9/11 on airline stocks for my undergraduate dissertation?
Hello Mam, I just wanted to ask a general empirical question. Why when you control for state fixed effects there is no state1 included in the regression?
Hi Yan, Thank you so much for your comment and subscribe to our channel. Can you write a little bit details? I will explain to you if I know the method.
Thank you so much for watching this video. We are glad that you found it helpful. Please like this video. Share with your friends. Subscribe to our channel! Please stay tuned!
Can you use "help egen" for confirmation of what kind of function you can use with "egen" command? Please do that. To my knowledge, "egen" can not do with the std() function. You need to use the basic variance formula: sigma^2 = E(x^2) - [E(x)]^2 to find the standard deviation. Please use "help egen" command to learn more. Thank you so much for watching our videos. Please like the video, share it with your friends, and subscribe to our channel. Stay tuned!
Thank you so much for your video! :) I am currently trying to do my own event study for an university seminar & I struggle a bit with it. But your video definitely helps!! But one question: Why don't we use the treatment dummy "post" in the regression? I think it is really important in order to account for differences before&after the new law has passed? Can you please explain why you don't include it in the regression. Thank you! :)
Hello Michelle, I am so sorry for the late reply. An event study model is an advantageous tool in estimating the treatment effects of the pre-and post-treatment periods. However, since treatment can be staggered - where the treatment group are treated at different time periods in states, I create a new variable in this video, called "timeToTreat" to address this issue, and run the regression with this variable instead of treatment dummy "post" in the regression. I hope you understand. Thank you so much for watching our videos. Please like the video, share it with your friends. Thanks again.
Great video. Are those stars added to variables we wish to keep?? I have tried but I get an error message that I have attempted to create an a matrix with too many rows.
Hey, thank you for the video. But can you put a subtitle on it? Cause english is not my first language, and I have some trouble to understand even when it comes from natives.
Hi Polliany, you are most welcome, and thank you for your valuable comments. I have added the subtitle for you. Please visit the video. I think it will be very helpful for you now. Please like the video, share it with your friends. Thanks again.
Hi Bruno, you are most welcome. You can follow this paper: deepblue.lib.umich.edu/bitstream/handle/2027.42/108834/tbyker_1.pdf?sequence=1#:~:text=Triple%2Ddifference%20event%2Dstudy%20estimates,Page%2012%204%20paid%20leave I think you need to jointly test the triple difference estimate.