Recent Posts

Pages: 1 2 [3] 4 5 ... 10
Paper Replication and Project / Omitted variable bias
« Last post by Azmeena Sayeed on May 03, 2017, 04:17:36 PM »
Hi, I am doing my project on omitted variable bias. To show that there is omitted variable bias I have used proxy variables and have run a regression to show the change in my estimates due to the omitted variable. How much change should there be in my estimates for me to state that there is omitted variable bias?
Paper Replication and Project / Improved Replication
« Last post by Jasonb4165 on May 03, 2017, 03:20:19 PM »
I am using my replication from earlier in the semester as part of my argument in my paper, and while I got a very high grade on my replication, it is still not perfect with regards to the coefficients and the statistical significance levels. How can I make my statistical significance levels and coefficients closer to what they are in the paper?

Now that the replications are graded, can someone give tips to improve my replication?
Paper Replication and Project / Re: Difficulties with getting results
« Last post by Jasonb4165 on May 03, 2017, 03:16:18 PM »

Thank you for this answer, but I do not believe you are addressing my questions.

My main question is, "what happens if I cannot get a result?" As of right now I have a mostly written paper, with research supporting my position, and a stata replication to support my point. How do I know when my stata replication is good enough? Do Debeaumont's coefficients need to be reduced by a lot, or is a few percent reduction in the relevant beta coefficients enough to argue omitted variable bias.
A student sent me an email today using the form in the website. When I replied, I received an email from the system saying that they could not deliver my email because the "user was not found." If you send me an email, make sure that the email that you write down is one that actually works. Otherwise, although I will receive your email and read it, there is no way that you can get an answer.
Administrative / Submitting the Project
« Last post by Spc on May 03, 2017, 01:40:25 PM »

Due to a college sponsored activity, I am not able to hand in the project at 3pm in Harkness 116G. What time range on Friday will you be in the location to collect projects? Is there an option to submit before 12pm noon?

Thank you in advance!
Paper Replication and Project / Handing in the paper
« Last post by ctaschman on May 03, 2017, 10:47:06 AM »
Is it possible to hand in the paper earlier than 3 pm on Friday, or will Alexis only be available starting at 3? I have an appt then, so should I have someone hand mine in for me?
Thank you!
Paper Replication and Project / Re: How to merge
« Last post by Thomas VanDer Straaten on May 02, 2017, 09:19:19 PM »
Do you mean by "additional information," you want to combine two datasets? I would just load the original dataset, merge on the new dataset, and then save the combined dataset. Then I would load the saved combined dataset and then run the replication (make sure you add in commands so you don't lose the new information you want to add, as perhaps your replication currently only keeps the directly relevant variables).
Material / Re: Past Final Questions
« Last post by Shenxiong on May 02, 2017, 07:55:33 PM »
Ok, thank you so much! That makes a lot of sense to me.!
Paper Replication and Project / How to merge
« Last post by ReidZ on May 02, 2017, 07:51:48 PM »
I have a file that has additional information in it that I would like to include on my replication assignment.  I know I have to use some form of the command "merge," but it's not working.  Say the original set we were given is A, my replication is B, and the additional information is C.  I am trying to do, after loading my replication homework, "merge 1:1 variable using C" This says that it can't find the variable even though I have A, B, and C all on my desktop.  What's the correct arrangement of A, B, and C to it to merge correctly?
Paper Replication and Project / Re: Replication usage in paper
« Last post by Thomas VanDer Straaten on May 02, 2017, 06:57:24 PM »
I would ask the project TA about the preferences surrounding this - this may be dependent on how you did on the replication and how dependent your evidence/solution is on the results changing. If your replication's regression results are within a reasonable margin of error, my guess is that you shouldn't need to 'fix' your replication.
Pages: 1 2 [3] 4 5 ... 10