ECO 231W

Undergraduate Econometrics

Change to handling project time

Because the McKenzie lecture will be this Friday at 4pm, we had to modify the timing to hand the project. The project is due at 3 pm on Friday (instead at 5 pm, as it was originally announced). Please see the post Handing the Project for details.

Handing the Project

You must hand the project on Friday 12/11 at 5 pm at Harkness 116G. The project TA Cristian will stay there until 5:45 pm. Notice that the due time is 5 pm, so Cristian will stay there longer only as a courtesy. If you arrive after 5:45 pm you may not find him anymore, you will have missed the deadline and severe penalties will apply.

Replicatuion Dataset Published

Find it in the Downloads page.

Further project consultation meetings

You can now sign up for up to two more slots to meet with the Project TA. Remember: only your earliest meeting counts for extra points.

If you haven’t signed up for any meeting yet, you should do this soon. If we run out of slots you will not be able to take advantage of this resource and the free points. Even of someone else has 3 meetings scheduled and you have none, we will not open further slots to accommodate you.

Project Consultation Meetings

It is time to start thinking about the final project. Don’t worry, you can have your rest next week, but you have to give this topic a bit of thought. To incentivize this, and also to help you form your project idea, we will be offering a special set of meetings. Here is how they work:

From Monday 11/30 until Friday 12/04, the project TA (Cristian) will be holding special consultation meetings. The meetings are 10 minutes long, but you should leave about 20 minutes open for this activity.

The meetings are individual. You will bring your idea about which critique point you will pursue for the project, and the strategy you are planning (evidence you are intending to use, data sets you plan to explore, etc.) to the meeting. Cristian will hear you out, and help you as much as he can given how much you prepared, and the path you decided to take. In some cases, he may tell you that your idea is not very good, so you should pursue another, or he may help you modify or refine the idea you are already thinking of defending. Use the project instructions that I published in the previous announcement as a guide for choosing your idea.

The meetings are not mandatory. However, we want to incentivize you to come. The project is worth 100 points. If you simply show up to a meeting, you will get 1 point over your final project grade. Then, depending on how prepared you are for the meeting (quality of the idea, how much you thought about the evidence sources, etc.) you can get up to 5 points over the project grade.

Sign up for meetings using
this link. Right now you can sign up for only one meeting. If we see two appointments from you we will cancel both without warning. However, starting Monday 11/30 you can sign up for up to two further meetings if you would like to get more help. Only your earliest meeting counts for extra points. Once we run out of slots this is it, so sign up soon if you want to make sure you take advantage of this resource.

If you want to reschedule your appointment, cancel the one you already have, and then make a new one. You can cancel your appointment up to 24 hours in advance. You can schedule an appointment up to 6 hours in advance. If you miss your appointment without having cancelled it, you can schedule a new appointment, but you will not receive the bonus points. Contact the Project TA if you have questions about the appointments.

You must check in at HARK 207 at or before your scheduled meeting time.

The Final Project

The project is due on 12/11/15. See details about the time and location where you will hand it in the calendar page. It must be handed in paper (print and staple it).

The final project is a critique of this semester’s paper. The critique will be based in 1 point. It means that, although you may know several things that are wrong with the paper, your project will discuss only one. Of course, choose the best one you can.

The project begins with an introduction, where you explain the paper in broad lines: the question, the methodology, the results, and the conclusion. Then you introduce the point which will be the basis of your critique. You have to explain what your point is, then you have to provide evidence for this point, and finally you have to describe the consequences for the results of overlooking your critique point. For example, if you are defending that there is an omitted variable, you must explain what is the consequence of this omission: is the bias positive or negative? What is the consequence of this for society? Finally, you must have a conclusion. Don’t forget the bibliography, if applicable. It must follow a standard academic style. Any style is fine, as long as it is the same for all entries. Turabian (also known as Chicago style) is a good choice, very well accepted in Social Sciences.

The critique point must be specific. Is it omitted variable bias? Then you must defend that 1 specific variable was omitted. Which is it? Is it measurement error? Then which variable has measurement error? Is it sample selection? Then are you concerned with selection in which specific way? You must provide evidence, and you can go as far as you want there. You can use pure logic, you can use newspaper sources. However, the royal evidence comes from actual research papers. If you want to really impress, you can bring outside datasets. There is no limit to the creativity you can put into the evidence for your point. Moreover, if you can solve the problem, then you should. It is not necessary to do this, and historically only 2 students per year manage to provide full solutions to the problems they suggest, but it certainly increases the level of impressiveness of your project to a whole new level.

The project has strict formatting rules. The paper cannot have more than 10 pages counting everything (except the cover page). It must be written in single-space, Times New Roman font size 12. The document must leave 1 inch of space in all margins, no more, no less. Pages must be numbered. Include a cover page with your name, student ID, and class time. Don’t try to fumble with the editing rules, because we have way too many examples to compare. You have a bit of freedom within reason in how you format and space the section titles, as well as figures and tables, if you have some. Here are some guidelines (not obligatory) to help you write the paper: a typical critique has a 2 page long introduction, then the critique itself is introduced in general lines in about half a page. The body of the critique is very free, and the conclusion is usually at most one page long.

The project is graded based on many things. First, the introduction where you summarize the paper. There we are looking for an excellent understanding of what truly matters in this year’s paper. The words about which you should think are conciseness, precision, and readability. To help you write this section, read question 2 in all midterms again. Many items there were designed to make you extract the essence of the paper arguments in a few lines.

The body of the paper is, of course, the most important part. We are looking for a good critique point, which is defended using excellent evidence. The critique must clearly delineate what are the consequences of the problem you are raising. We reward creativity very highly. You can defend the same critique point as many of your colleagues, but then you are in direct comparison with them. If you choose an unexplored critique point, you will be evaluated on your own, which is a good thing. Moreover, when we see a novel critique point, we imagine that you thought about, but rejected, several more common ideas. Hence, we will reward you directly. We also reward the quality of the evidence. Not all evidence has the same strength and reliability. It goes like this: straight from data>>research papers>>online verifiable journalistic sources>>logical argument. This is not written in stone, but it’s a decent guideline. We reward effort and creativity involved in choosing, searching, and using the evidence. We also reward the strength of your whole argument. Is it easy to understand? Are you convincing?

You can make up for things. For example, you may not be defending the most creative critique point, but you can make up for it with a brilliant evidence source, or even (wow!) a direct solution. Additionally, this is an essay, so your language counts a lot. We establish just a few points for style and grammar, but don’t underestimate the power of a well written piece. An argument that develops fluidly, a paper that is not boring, a paragraph that is so well structured that the mind just cruises through it, all of those end up reflecting on your final grade. We punish pretty severely when your arguments are not clear, when we have to re-read things many times to get the point.

This project is not about doing everything right. Your paper may defend a correct critique point, use good evidence, and be sufficiently clear, and it will still not garner the maximum grade. You can always choose to break free from mediocrity. You can choose to be ambitious, to risk, and we will reward that.

Final note: you can get help with grammar and style. Check out this link to the
College Writing Program. They can read your essay over, they can help edit it. You should take advantage of this resource, it will serve you well for when you are writing other essays in the future. Do you see how journalists write? This style is very persuasive. I’ve seen students that could write this smoothly, and we couldn’t help but give them a better grade. Never underestimate the importance of presentation, be it in person or in paper.

Replication

You will replicate the project paper (the same one of question 2 in the Midterm). This means that you will get the data and clean it according to the descriptions in the paper. You can find the data and the codebook in the Download page. Then you will generate the same variables that the authors say they do, and run the same regressions. Finally, you will make sure that your code presents all the values in the table in a format that is very easy to see. You need to reproduce Tables 1 and 2.

The code must be clean and organized. You have a good measure of freedom in deciding how you will organize your code. The point is to use comments to create sections for each different part of the replication. You should also use comments to explain what the commands are doing. The way you should approach this is as someone who is writing a code that will be used by others. Could they run it if they had the same data set? Could they understand it with minimum effort?

As with the homeworks, this assignment is a .do file. One .do file. You are graded on the correctness of what you did, on how close you get to the results, on how clean and elegant is your code, and on how easy it is to understand. Think that you are working with a coauthor, or with colleagues in a company. You don’t want to explain so much that it is tiresome to read, but you must make sure that the reader doesn’t spend time figuring out what you intended with this or that command.

The replication is usually a challenging assignment. The hard truth is that you can very seldom replicate exactly the same results of a paper. Sometimes papers have mistakes, but even when they don’t, the authors may have done something with the data that they didn’t describe in the paper, perhaps by distraction, perhaps intentionally. So, you won’t get the same results that they did. How close can you get? As you try to figure this out you will gain a very deep understanding of the paper.

Usually this process is very time consuming. Don’t play with this, you never replicated a paper before, you don’t know what it is like. You will run into coding problems, you may need to learn a Stata trick, you may have to start again. Even when you get it to run, you may not be getting results that are close enough, what are you doing differently? You will need time to go to office hours and experiment until you figure it out.

Alon is the specialist in the replication. The undergrad TAs have done replications of their own when they took this course, so they can help as well. However, on this particular assignment, try to get Alon’s help if you can.

The replication is due on Friday 11/06 at 5:00 pm. You must upload the replication file in the upload page. For details on how to upload it, read this. The password is still the same as for the homeworks. The replication is graded out of 10 points, and it is worth 10% of the grade.
 

PENALTIES IF THE FILE DOESN’T RUN
If your .do file doesn’t run, the TA will request that you fix it, and give you a deadline (usually until the next day). Each time he has to request a correction for the file to run, you lose 2 points. If you fail to make the deadline of a correction request, your replication won’t be accepted anymore. You choose which email we will use to contact you when you upload the file. Make sure that it is one you check often.

LATENESS PENALTIES
Every hour past the due time, your replication loses 10 points. Here is a breakdown:

Received before 5:00 pm until 5:59: no penalty
Received between 6:00 and 6:59: -2
Received between 7:00 and 7:59: -4


and so on until 10 pm, at which time we will not accept your replication any longer. Read the policy on late assignments here.

NOTICE: the replication is due before or at 5:00 pm. We only start discounting points at 6:00 pm to allow for internet delays, browser reloading or any other unpleasant things that may happen. We will not accept any excuse related to technology. If you can’t rely on your connection, or your browser, then take measures to upload your homework earlier, or even better, the night before.

Think that there are way too many rules to follow in this course? Read this.

Introducing Fall 2015's Paper

The paper we will be using this semester is

Mathematical College Majors and the Gender Gap in Wages

by Catherine J. Weinberger. It was published in 1999 by the journal Industrial Relations.

We will be using this paper in the midterm questions, in the replication, and in the project.

How to hand the Project

As you know, we won’t have class on Wednesday. To hand the project, you have to show up at one of the following times and locations:

- Wed 04/29 12:30-12:45 pm at HUTCH 473
- Wed 04/29 3:25-3:40 pm at B&L 109

Notice that you only have a 15 minute window while the TA will be at the room to collect the projects. You can hand your project at any of these times, it does not matter if you normally attend it or not. Someone else may hand the project for you. Make sure that you follow the instructions for formatting, or you may lose points. Make sure that your project is stapled. Good luck!

About sharing material for the project

I would like to clarify that it is ok to help other students with their project. Sharing material consensually is allowed in this course unless I expressly forbid it (for example, I expressly forbid it during the exams, or homework answers in the forum). I am writing this for the following reason: many students did not do so well in the replication. Now they want to do well in the project but need help to run regressions, since their own codes are not great. I want to make sure that all of you know that if you are willing to share your code with another student (or all students, even in the forum) you can do so at this point. Of course, your code belongs to you, and you are in no way required to do this. I also want to remind all students that it is not necessary to have regressions at all in the project. It is possible to write a brilliant piece without touching data at all.

Project Consultation Meetings

Now that you handed the replication, it is time to start thinking about the final project. Don’t worry, you can have your rest next week, but you have to give this topic a bit of thought. To incentivize this, and also to help you form your project idea, we will be offering a special set of meetings. Here is how they work:

From Wednesday of this coming week until Tuesday of the next week, the project TA (Olamide) will be holding special consultation meetings. The meetings are 10 minutes long, but you should leave about 20 minutes open for this activity.

The meetings are individual. You will bring your idea about which critique point you will pursue for the project, and the strategy you are planning (evidence you are intending to use, data sets you plan to explore, etc.) to the meeting. Olamide will hear you out, and help you as much as he can given how much you prepared, and the path you decided to take. In some cases, he may tell you that your idea is not very good, so you should pursue another, or he may help you modify or refine the idea you are already thinking of defending. Use the project instructions that I published in the previous announcement as a guide for choosing your idea.

The meetings are not mandatory. However, we want to incentivize you to come. The project is worth 100 points. If you simply show up to a meeting, you will get 1 point over your final project grade. Then, depending on how prepared you are for the meeting (quality of the idea, how much you thought about the evidence sources, etc.) you can get up to 5 points over the project grade. You can only attend 1 meeting.

On Monday evening I will post a link where you will be able to sign up to a specific time slot.

Deadline of Replication Extended

I am extending the deadline of the replication to Tuesday March 31st at 5 pm. All the other rules are the same, just adapted for the new deadline date. This will give you 4 more days to complete the replication. Use the time wisely!

Problems opening the replication data set

Some students were not able to open the data set because it was not compatible with older versions of Stata. I uploaded a new data set version which should now be compatible. Please let us know in the forum if you are still having trouble.

Replication

You will replicate the project paper (the same one of question 2 in the Midterm). This means that you will get the data and clean it according to the descriptions in the paper. You can find the data, the codebook, a link to the interactive codebook online and a small document with some recommendations about the replication in the Project part of the Download page. Then you will generate the same variables that the authors say they do, and run the same regressions. Finally, you will make sure that your code presents all the values in the table in a format that is very easy to see. You need to reproduce Tables 1 and 2 (no need to reproduce Table 3).

The code must be clean and organized. You have a good measure of freedom in deciding how you will organize your code. The point is to use comments to create sections for each different part of the replication. You should also use comments to explain what the commands are doing. The way you should approach this is as someone who is writing a code that will be used by others. Could they run it if they had the same data set? Could they understand it with minimum effort?

As with the homeworks, this assignment is a .do file. One .do file. You are graded on the correctness of what you did, on how close you get to the results, on how clean and elegant is your code, and on how easy it is to understand. Think that you are working with a coauthor, or with colleagues in a company. You don’t want to explain so much that it is tiresome to read, but you must make sure that the reader doesn’t spend time figuring out what you intended with this or that command.

The replication is usually a challenging assignment. The hard truth is that you can very seldom replicate exactly the same results of a paper. Sometimes papers have mistakes, but even when they don’t, the authors may have done something with the data that they didn’t describe in the paper, perhaps by distraction, perhaps intentionally. So, you won’t get the same results that they did. How close can you get? As you try to figure this out you will gain a very deep understanding of the paper.

Usually this process is very time consuming. Don’t play with this, you never replicated a paper before, you don’t know what it is like. You will run into coding problems, you may need to learn a Stata trick, you may have to start again. Even when you get it to run, you may not be getting results that are close enough, what are you doing differently? You will need time to go to office hours and experiment until you figure it out.

Alon is the specialist in the replication. He will hold grading office hours for Homework 3, but you can come and ask him questions about the replication as well. David can definitely help you, though he will have to figure things out with you. The undergrad TAs have done replications of their own when they took this course, so they can help as well. However, on this particular assignment, try to get the grad TAs to help you if you can.

The replication is due on Friday 03/27 at 5:00 pm. You must upload the replication file in the upload page. For details on how to upload it, read this. The password is still the same as for the homeworks. The replication is graded out of 50 points, and it is worth 10% of the grade.
 

PENALTIES IF THE FILE DOESN’T RUN
If your .do file doesn’t run, the TA will request that you fix it, and give you a deadline (usually until the next day). Each time he has to request a correction for the file to run, you lose 10 points. If you fail to make the deadline of a correction request, your replication won’t be accepted anymore. You choose which email we will use to contact you when you upload the file. Make sure that it is one you check often.

LATENESS PENALTIES
Every hour past the due time, your replication loses 10 points. Here is a breakdown:

Received before 5:00 pm until 5:59: no penalty
Received between 6:00 and 6:59: -10
Received between 7:00 and 7:59: -20


and so on until 10 pm, at which time we will not accept your replication any longer. Read the policy on late assignments here.

NOTICE: the replication is due before or at 5:00 pm. We only start discounting points at 6:00 pm to allow for internet delays, browser reloading or any other unpleasant things that may happen. We will not accept any excuse related to technology. If you can’t rely on your connection, or your browser, then take measures to upload your homework earlier, or even better, the night before.

Think that there are way too many rules to follow in this course? Read this.

Introducing this semester's paper!

The paper we will be using this semester is

Gender Differences in the Effect of Education on the Slope of Experience-Earnings Profiles

by Kevin C. Duncan. It was published in 1996 by the American Journal of Economics and Socioloy.

This is a classic topic in Economics. There exist a large literature on earning gaps due to gender (and also racial, height, beauty, etc.) differences. The issue is whether this is due to discrimination or actual productivity differences.

We will be using this paper in the midterm questions, in the replication, and in the project.

The Final Project

The final project is a critique of this semester’s paper. The critique will be based in 1 point. It means that, although you may know several things that are wrong with the paper, your project will discuss only one. Of course, choose the best one you can.

The project begins with an introduction, where you explain the paper in broad lines: the question, the methodology, the results, and the conclusion. Then you introduce the point which will be the basis of your critique. You have to explain what your point is, then you have to provide evidence for this point, and finally you have to describe the consequences for the results of overlooking your critique point. For example, if you are defending that there is an omitted variable, you must explain what is the consequence of this omission: is the bias positive or negative? What is the consequence of this for society? Finally, you must have a conclusion. Don’t forget the bibliography, if applicable. It must follow a standard academic style. Any style is fine, as long as it is the same for all entries. Turabian (also known as Chicago style) is a good choice, very well accepted in Social Sciences.

The critique point must be specific. Is it omitted variable bias? Then you must defend that 1 specific variable was omitted. Which is it? Is it measurement error? Then which variable has measurement error? Is it sample selection? Then are you concerned with selection in which specific way? You must provide evidence, and you can go as far as you want there. You can use pure logic, you can use newspaper sources. However, the royal evidence comes from actual research papers. If you want to really impress, you can bring outside datasets. There is no limit to the creativity you can put into the evidence for your point. Moreover, if you can solve the problem, then you should. It is not necessary to do this, and historically only 2 students per year manage to provide full solutions to the problems they suggest, but it certainly increases the level of impressiveness of your project to a whole new level.

The project has strict formatting rules. The paper cannot have more than 10 pages counting everything (except the cover page). It must be written in single-space, Times New Roman font size 12. The document must leave 1 inch of space in all margins, no more, no less. Pages must be numbered. Include a cover page with your name, student ID, and class time. Don’t try to fumble with the editing rules, because we have way too many examples to compare. You have a bit of freedom within reason in how you format and space the section titles, as well as figures and tables, if you have some. Here are some guidelines (not obligatory) to help you write the paper: a typical critique has a 2 page long introduction, then the critique itself is introduced in general lines in about half a page. The body of the critique is very free, and the conclusion is usually at most one page long.

The project is graded based on many things. First, the introduction where you summarize the paper. There we are looking for an excellent understanding of what truly matters in this year’s paper. The words about which you should think are conciseness, precision, and readability. To help you write this section, read question 2 in all midterms again. Many items there were designed to make you extract the essence of the paper arguments in a few lines.

The body of the paper is, of course, the most important part. We are looking for a good critique point, which is defended using excellent evidence. The critique must clearly delineate what are the consequences of the problem you are raising. We reward creativity very highly. You can defend the same critique point as many of your colleagues, but then you are in direct comparison with them. If you choose an unexplored critique point, you will be evaluated on your own, which is a good thing. Moreover, when we see a novel critique point, we imagine that you thought about, but rejected, several more common ideas. Hence, we will reward you directly. We also reward the quality of the evidence. Not all evidence has the same strength and reliability. It goes like this: straight from data>>research papers>>online verifiable journalistic sources>>logical argument. This is not written in stone, but it’s a decent guideline. We reward effort and creativity involved in choosing, searching, and using the evidence. We also reward the strength of your whole argument. Is it easy to understand? Are you convincing?

You can make up for things. For example, you may not be defending the most creative critique point, but you can make up for it with a brilliant evidence source, or even (wow!) a direct solution. Additionally, this is an essay, so your language counts a lot. We establish just a few points for style and grammar, but don’t underestimate the power of a well written piece. An argument that develops fluidly, a paper that is not boring, a paragraph that is so well structured that the mind just cruises through it, all of those end up reflecting in your final grade. We punish pretty severely when your arguments are not clear, when we have to re-read things many times to get the point.

This project is not about doing everything right. Your paper may defend a correct critique point, use good evidence, and be sufficiently clear, and it will still not garner the maximum grade. You can always choose to break free from mediocrity. You can choose to be ambitious, to risk, and we will reward that.

Final note: you can get help with grammar and style. Check out this link to the
College Writing Program. They can read your essay over, they can help edit it. You should take advantage of this resource, it will serve you well for when you are writing other essays in the future. Do you see how journalists write? This style is very persuasive. I’ve seen undergrad students that could write this smoothly, and we couldn’t help but give them a better grade. Never underestimate the importance of presentation, be it in person or in paper.

The project is due on 04/29/15 in class. It must be handed in paper (print and staple it).

Replication Update

There was a misunderstanding in the replication instructions. I will update them to correct this.

When you write your code, it should output the results in the table, but not necessarily with the same formatting. That said, you should make it as easy as possible for the reader to see where the numbers are: you are graded on this. For example, if you run a regression, write the variables in a similar order to the way they show up in the table, and then point out what we should look at in the comments. Even better, you could program Stata to output only the numbers which are in the table.

Replication

It’s time to begin thinking about the paper replication. You will replicate the QES column in table 2, and all of table 3 in the paper. This means that you will get the data (you can find it under “Project” in the download page) and clean it according to the descriptions in the paper. Then you will generate the same variables that the authors say they do, and run the same regressions. Finally, you will make sure that your code presents all the values in the table in a format that is very easy to see.

The code must be clean and organized. You have a good measure of freedom in deciding how you will organize your code. The point is to use comments to create sections for each different part of the replication. You should also use comments to explain what the commands are doing. The way you should approach this is as someone who is writing a code that will be used by others. Could they run it if they had the same data set? Could they understand it with minimum effort?

As with the homeworks, this assignment is a .do file. One .do file. You are graded in the correctness of what you did, on how close you get to the results, on how clean and elegant is your code, and on how easy it is to understand. Think that you are working with a coauthor, or with colleagues in a company. You don’t want to explain so much that it is tiresome to read, but you must make sure that the reader doesn’t spend time figuring out what you intended with this or that command.

The replication is usually a challenging assignment. The hard truth is that you can very seldom replicate exactly the same results of a paper. Sometimes papers have mistakes, but even when they don’t, the authors may have done something with the data that they didn’t describe in the paper, perhaps for distraction, perhaps intentionally. So, you won’t get the same results that they did. How close can you get? As you try to figure this out you will gain a very deep understanding of the paper.

Usually this process is very time consuming. Don’t play with this, you never replicated a paper before, you don’t know what it is like. You will run into coding problems, you may need to learn a Stata trick, you may have to start again. Even when you get it to run, you may not be getting results that are close enough, what are you doing differently? You will need time to go to office hours and experiment until you figure it out.

Umair is the specialist in the replication. His office hours will be the most useful for this particular application. He will hold special office hours the week before it is due, but you can also find him at the homework grading office hours, and ask your questions. Check the
calendar. David can definitely help you, though he will have to figure things out with you. The undergrad TAs have done replications of their own when they took this course, so they can help as well. However, on this particular assignment, try to get the grad TAs to help you if you can.


The replication is due on Friday 11/16 at 12:00 pm. You must upload the replication file in the upload page. For details on how to upload it, read this. The password is still the same as in the homeworks. The replication is graded out of 50 points, and it is worth 10% of the grade.


PENALTIES IF THE FILE DOESN’T RUN

If your .do file doesn’t run, the TA will request that you fix it, and give you a deadline (usually until the next day). Each time he has to request a correction for the file to run, you lose 5 points. If you fail to make the deadline of a correction request, your replication won’t be accepted anymore. You choose which email we will use to contact you when you upload the file. Make sure that it is one you check often.

LATENESS PENALTIES

Every hour past the due time, your replication loses 10 points. Here is a breakdown:

Received before 12:00 until 12:59: no penalty
Received between 1:00 and 1:59: -10
Received between 2:00 and 2:59: -20


and so on until 5 pm, at which time we will not accept your replication any longer. Read the policy on late assignments
here.

NOTICE: the replication is due before or at 12:00 pm. We only start discounting points at 1:00 pm to allow for internet delays, browser reloading or any other unpleasant things that may happen. We will not accept any excuse related to technology. If you can’t rely on your connection, or your browser, then take measures to upload your homework earlier, or even better, the night before.

Think that there are way too many rules to follow in this course? Read
this.




Presenting this semester's paper

The paper we will be using this semester is

Beauty and the Labor Market

by Hamermesh and Biddle. It was published in 1994 by the American Economic Review, which is the journal with the highest impact in the economics profession.

The topic is a lot of fun. It speaks about an unusual form of discrimination in the labor market: that in favor of beautiful people. Did you ever consider that? Has it ever crossed your mind that more beautiful people can be earning more money just because of their looks? We are not talking about fashion models, we are talking about desk jobs too! Well, this is what this paper claims.

We will be using this paper in the midterm questions, in the replication, and in the project.

Project is graded

The project is graded, and will be in the class boxes in Harkness. The grades correspond to the percentile where your project falls in comparison with your colleagues. There were some pretty impressive approaches. Well done!

Final project is posted

The final project explanations and rules are posted. Find them in the Assignments page.

The project is a written essay. The quality of the writing counts towards your grade. In fact, it counts even more than the amount of points we assign it. We are human, and a well written piece will have us reading it with more pleasure, with a more positive attitude. Hence, the easiest way to increase your grade is to have your essay revised by an editor. It’s a true arbitrage opportunity, with minimal effort you can get very high rewards. This is even more important if English is not your native language. The university provides many editing services for free. Read about them in the Resources section in the About page.

You must have a plan about how you will organize your assignments in the coming weeks. Check the calendar. If you only start homework 4 after Thanksgiving, you may have difficulty completing the project in time. Go ahead and simply think about how you will approach your studies in the coming weeks.

Hints for paper replication

The Applied TA Tuo has been so kind to write a document with further suggestions that can help you complete the paper replication. You can download it here. I must reiterate the need for you to start this replication soon.

Paper replication

The information for the paper replication is published in the assignments page. It is due on Wednesday 11/16. The Applied TA is holding extra office hours in the coming 2 weeks. Check the calendar.

Introducing Spring 2017's Paper

The paper we will be using this semester is

Occupational differences in the wage penalty for obese women

by Ronald DeBeaumont. It was published in 2009 by the Journal of Socio-Economics.

We will be using this paper in the midterm questions, in the replication, and in the project.

Replication

You will replicate the project paper (the same one of question 2 in the Midterm). This means that you will get the data and clean it according to the descriptions in the paper. You can find the data and the codebook in the Download page. Then you will generate the same variables that the authors say they do, and run the same regressions. Finally, you will make sure that your code presents all the values in the table in a format that is very easy to see. You need to reproduce Tables 2, 3 and 4.

The code must be clean and organized. You have a good measure of freedom in deciding how you will organize your code. The point is to use comments to create sections for each different part of the replication. You should also use comments to explain what the commands are doing. The way you should approach this is as someone who is writing a code that will be used by others. Could they run it if they had the same data set? Could they understand it with minimum effort?

As with the homeworks, this assignment is a .do file. One .do file. You are graded on the correctness of what you did, on how close you get to the results, on how clean and elegant is your code, and on how easy it is to understand. Think that you are working with a coauthor, or with colleagues in a company. You don’t want to explain so much that it is tiresome to read, but you must make sure that the reader doesn’t spend time figuring out what you intended with this or that command.

The replication is usually a challenging assignment. The hard truth is that you can very seldom replicate exactly the same results of a paper. Sometimes papers have mistakes, but even when they don’t, the authors may have done something with the data that they didn’t describe in the paper, perhaps by distraction, perhaps intentionally. So, you won’t get the same results that they did. How close can you get? As you try to figure this out you will gain a very deep understanding of the paper.

Usually this process is very time consuming. Don’t play with this, you never replicated a paper before, you don’t know what it is like. You will run into coding problems, you may need to learn a Stata trick, you may have to start again. Even when you get it to run, you may not be getting results that are close enough, what are you doing differently? You will need time to go to office hours and experiment until you figure it out.

Youngmin is the specialist in the replication. The undergrad TAs have done replications of their own when they took this course, so they can help as well. However, on this particular assignment, try to get Youngmin’s help if you can.

The replication is due on Friday 03/31 at 5:00 pm. You must upload the replication file in the upload page. For details on how to upload it, read this. The password is still the same as for the homeworks. The replication is graded out of 10 points, and it is worth 10% of the grade.
 

PENALTIES IF THE FILE DOESN’T RUN
If your .do file doesn’t run, the TA will request that you fix it, and give you a deadline (usually until the next day). Each time he has to request a correction for the file to run, you lose 2 points. If you fail to make the deadline of a correction request, your replication won’t be accepted anymore. You choose which email we will use to contact you when you upload the file. Make sure that it is one you check often.

LATENESS PENALTIES
Every hour past the due time, your replication loses 10 points. Here is a breakdown:

Received before 5:00 pm until 5:59: no penalty
Received between 6:00 and 6:59: -2
Received between 7:00 and 7:59: -4


and so on until 10 pm, at which time we will not accept your replication any longer. Read the policy on late assignments here.

NOTICE: the replication is due before or at 5:00 pm. We only start discounting points at 6:00 pm to allow for internet delays, browser reloading or any other unpleasant things that may happen. We will not accept any excuse related to technology. If you can’t rely on your connection, or your browser, then take measures to upload your homework earlier, or even better, the night before.

Think that there are way too many rules to follow in this course? Read this.

Project Consultation Meetings

It is time to start thinking about the final project. To incentivize this, and also to help you form your project idea, we will be offering a special set of meetings. Here is how they work:

From Monday 04/24 until Friday 05/03, the project TA (Alexis) will be holding special consultation meetings. The meetings are 10 minutes long, but you should leave about 20 minutes open for this activity.

The meetings are individual. You will bring your idea about which critique point you will pursue for the project, and the strategy you are planning (evidence you are intending to use, data sets you plan to explore, etc.) to the meeting. Cristian will hear you out, and help you as much as he can given how much you prepared, and the path you decided to take. In some cases, he may tell you that your idea is not very good, so you should pursue another, or he may help you modify or refine the idea you are already thinking of defending. Use the project instructions that I published in the previous announcement as a guide for choosing your idea.

The meetings are not mandatory. However, we want to incentivize you to come. The project is worth 100 points. If you simply show up to a meeting, you will get 1 point over your final project grade. Then, depending on how prepared you are for the meeting (quality of the idea, how much you thought about the evidence sources, etc.) you can get up to 5 points over the project grade.

Sign up for meetings using
this link. Right now you can sign up for only one meeting. If we see two appointments from you we will cancel both without warning. However, starting Monday 04/24 you can sign up for up to two further meetings if you would like to get more help. Only your earliest meeting counts for extra points. Once we run out of slots this is it, so sign up soon if you want to make sure you take advantage of this resource.

If you want to reschedule your appointment, cancel the one you already have, and then make a new one. You can cancel your appointment up to 24 hours in advance. You can schedule an appointment up to 6 hours in advance. If you miss your appointment without having cancelled it, you can schedule a new appointment, but you will not receive the bonus points. Contact the Project TA if you have questions about the appointments.

Handing the Project

You must hand the project on Friday 05/05 at 3 pm at Harkness 116G. The project TA Alexis will stay there until 3:45 pm. Notice that the due time is 3 pm, so Alexis will stay there longer only as a courtesy. If you arrive after 3:45 pm you may not find him anymore, you will have missed the deadline and severe penalties will apply.

The Final Project

The final project is a critique of this semester’s paper. The critique will be based in 1 point. It means that, although you may know several things that are wrong with the paper, your project will discuss only one. Of course, choose the best one you can.

The project begins with an introduction, where you explain the paper in broad lines: the question, the methodology, the results, and the conclusion. Then you introduce the point which will be the basis of your critique. You have to explain what your point is, then you have to provide evidence for this point, and finally you have to describe the consequences for the results of overlooking your critique point. For example, if you are defending that there is an omitted variable, you must explain what is the consequence of this omission: is the bias positive or negative? What is the consequence of this for society? Finally, you must have a conclusion. Don’t forget the bibliography, if applicable. It must follow a standard academic style. Any style is fine, as long as it is the same for all entries. Turabian (also known as Chicago style) is a good choice, very well accepted in Social Sciences.

The critique point must be specific. Is it omitted variable bias? Then you must defend that 1 specific variable was omitted. Which is it? Is it measurement error? Then which variable has measurement error? Is it sample selection? Then are you concerned with selection in which specific way? You must provide evidence, and you can go as far as you want there. You can use pure logic, you can use newspaper sources. However, the royal evidence comes from actual research papers. If you want to really impress, you can bring outside datasets. There is no limit to the creativity you can put into the evidence for your point. Moreover, if you can solve the problem, then you should. It is not necessary to do this, and historically only 2 students per year manage to provide full solutions to the problems they suggest, but it certainly increases the level of impressiveness of your project to a whole new level.

The project has strict formatting rules. The paper cannot have more than 10 pages counting everything (except the cover page). It must be written in single-space, Times New Roman font size 12. The document must leave 1 inch of space in all margins, no more, no less. Pages must be numbered. Include a cover page with your name, student ID, and class time. Don’t try to fumble with the editing rules, because we have way too many examples to compare. You have a bit of freedom within reason in how you format and space the section titles, as well as figures and tables, if you have some. Here are some guidelines (not obligatory) to help you write the paper: a typical critique has a 2 page long introduction, then the critique itself is introduced in general lines in about half a page. The body of the critique is very free, and the conclusion is usually at most one page long.

The project is graded based on many things. First, the introduction where you summarize the paper. There we are looking for an excellent understanding of what truly matters in this year’s paper. The words about which you should think are conciseness, precision, and readability. To help you write this section, read question 2 in all midterms again. Many items there were designed to make you extract the essence of the paper arguments in a few lines.

The body of the paper is, of course, the most important part. We are looking for a good critique point, which is defended using excellent evidence. The critique must clearly delineate what are the consequences of the problem you are raising. We reward creativity very highly. You can defend the same critique point as many of your colleagues, but then you are in direct comparison with them. If you choose an unexplored critique point, you will be evaluated on your own, which is a good thing. Moreover, when we see a novel critique point, we imagine that you thought about, but rejected, several more common ideas. Hence, we will reward you directly. We also reward the quality of the evidence. Not all evidence has the same strength and reliability. It goes like this: straight from data>>research papers>>online verifiable journalistic sources>>logical argument. This is not written in stone, but it’s a decent guideline. We reward effort and creativity involved in choosing, searching, and using the evidence. We also reward the strength of your whole argument. Is it easy to understand? Are you convincing?

You can make up for things. For example, you may not be defending the most creative critique point, but you can make up for it with a brilliant evidence source, or even (wow!) a direct solution. Additionally, this is an essay, so your language counts a lot. We establish just a few points for style and grammar, but don’t underestimate the power of a well written piece. An argument that develops fluidly, a paper that is not boring, a paragraph that is so well structured that the mind just cruises through it, all of those end up reflecting in your final grade. We punish pretty severely when your arguments are not clear, when we have to re-read things many times to get the point.

This project is not about doing everything right. Your paper may defend a correct critique point, use good evidence, and be sufficiently clear, and it will still not garner the maximum grade. You can always choose to break free from mediocrity. You can choose to be ambitious, to risk, and we will reward that.

Final note: you can get help with grammar and style. Check out this link to the
College Writing Program. They can read your essay over, they can help edit it. You should take advantage of this resource, it will serve you well for when you are writing other essays in the future. Do you see how journalists write? This style is very persuasive. I’ve seen undergrad students that could write this smoothly, and we couldn’t help but give them a better grade. Never underestimate the importance of presentation, be it in person or in paper.

The project is due on 05/05. It must be handed in paper (print and staple it). We will announce the location.