Econometrics Messages

<< back to the main page

message board

Organizing Information

(posted: 01 Dec 2017)

I want you to learn econometrics and the best way to learn econometrics is to do it. But more broadly, I hope that conducting an econometric analysis will teach you how to organize information.

In the specific case here, each column in your spreadsheet represents a variable and each row represents an observation, so your task is to properly align the information that spreadsheet.

If you carefully construct that initial spreadsheet from reliable sources of data (and if you choose a good set of variables to test your null hypothesis), you should observe some clear trends in your data. Your task then is to explain those trends, test your null hypothesis and report your findings.

Gretl, of course, will help you run regressions and calculate statistics for your analysis. But Gretl is a tool. It is not the tool that is important. It is the quality of your input that is important.

That initial spreadsheet is what's important. How you organize information is what's important.

In a more general case, your information might not be the numeric data that we work with in econometrics. It might be names, addresses or whole documents and files. Your data might not even fit into a spreadsheet at all.

But some principles, like functions and variables, will remain the same. And, once again, what will be important is how you organize information.

For example, consider a different problem. Suppose you want to know what words are most commonly used to describe a product that you are selling or a stock in your portfolio.

Here, you must conduct a statistical analysis of words. To conduct such a statistical analysis of non-numeric data, what will be important is how you organize information.

Since the domain of our functions will be a word (not a number), we must define our words. Just as real numbers may be integers, rational numbers, irrational numbers, etc., our words may be nouns, verbs, adverbs, adjectives, etc.

That's why I am annotating the Sicilian language. Using that index, I can define most of the language in a very short amount of time. And with all of those definitions, we can conduct a statistical analysis. (e.g. of Sicilian Wikipedia).

Which words are the most commonly used words? Which words are the most common objects of a particular verb or of a particular preposition? Which adjectives are most frequently used to describe a particular noun? Which adverbs ... ?

How do the words used to describe a stock affect its price? How much do they affect its price?

We can find the answers to these questions, if we organize our information.


Course Project

(posted: 20 Nov 2017)

I know that some students are making good progress on the course project. And I know that the course project is giving some students a lot of stress. This is a difficult assignment. Stress is normal. If you are feeling stressed, please tell me how I can help you.

If you are struggling to assemble a dataset, please consider using the USA state panel with employment rates (from BLS) and minimum wage rates (from Vaghul and Zipperer).

If you use the USA state panel for your analysis, first try to reproduce the regression results that I provide in the documentation. Then look for other ways to test the null hypothesis that the minimum wage rate does not affect the employment rate.

Most importantly, please tell me how I can help you.


December Sessions

(posted: 20 Nov 2017)

When we return from Thanksgiving break, we will wrap up our discussion of probability models. To prepare for that discussion, please read Stock-Watson chap. 9 and Kennedy chap. 16.

Finally, we will discuss time-series. To prepare for that discussion, please read Stock-Watson chaps. 12, 13 and 14 and Kennedy chaps. 10 and 19.


Thanksgiving Break

(posted: 20 Nov 2017)

Queens College will be closed from Thu 23 to Sun 26 Nov.   No classes will meet.

Enjoy the break!   Have a Happy Thanksgiving!


Employment Rates

(posted: 03 Nov 2017)

Employment Rate: Males age 25-54 in the United States
Employment Rate: Females age 25-54 in the United States


WLS and the Logit Model

(posted: 31 Oct 2017)

As a follow-up to our discussions of weighted least squares, I have prepared some notes on:   heteroskedascity in the logit model.


Gauss-Markov Assumptions

(posted: 30 Oct 2017)

W.H. Greene's Econometric Analysis has an excellent summary of the Gauss-Markov assumptions:


Violations of Gauss-Markov

(posted: 24 Oct 2017)

Now that we have finished our discussion of the classic linear regression model, which assumes that Gauss-Markov assumptions are satisfied, we will begin exploring violations of the Gauss-Markov assumptions. For theoretical background, please read Kennedy chaps. 5, 6 and 7.


Midterm and Project Proposal

(posted: 24 Oct 2017)

Having passed the midpoint of the semester, I now want you to compile your notes on the topics that we have discussed so far. For that purpose, I would like you all to submit handwritten notes on the midterm exam questions listed at the end of the syllabus.

The best way to learn econometrics is to conduct an econometric analysis, so I am looking forward to reading your project proposals. And I hope that you are looking forward to conducting the analysis because this is fun.

For the project proposal, I would like you to submit a written description of the null hypothesis that you wish to test and the dataset that you plan to test it with. More details are listed at the end of the syllabus.

If possible, I would like you to submit the midterm and the proposal on Sun. 05 Nov. and Tues. 07 Nov. I will happily grant extensions to that deadline if necessary, but let's all try to submit them on those dates.


Hypothesis Testing

(posted: 02 Oct 2017)

We will finish our discussion of the problem set during Sunday's session (01 Oct) and Tuesday's session (03 Oct). Then during the next sessions (on Sun 08 Oct and Tue 10 Oct), we will discuss hypothesis testing.

For theoretical background on hypothesis testing, please read Kennedy chap. 4. Please also read either Stock-Watson chaps. 5 and 7 or equivalent chapters in a better textbook. Two alternatives that you might consider are the Hill, Griffiths and Lim textbook and the Studenmund textbook.

And for an empirical example of hypothesis testing, please read my Analysis of the "Biagi Law". Because I will frequently use those datasets in examples of several different econometric topics, you should also read my note about teaching with the "Biagi Law" data.


Next Class Sessions

(posted: 21 Sept 2017)

During our next class sessions -- on Sun 24 Sept and Tue 26 Sept -- we will continue our discussion of the problem set with problems #2 and #3, which are designed to help you understand maximum likelihood and hypothesis testing. For background on those topics, please read Kennedy chaps. 1-4.


On Textbooks

(posted: 21 Sept 2017)

It is important for students to purchase copies of both textbooks and read them both. In practice, it is easy to convince students to read the Kennedy textbook, but it is difficult to convince students to read the Stock-Watson textbook.

So maybe we should replace the Stock-Watson textbook?

If you're interested in exploring some alternatives, check out the one by Hill, Griffiths and Lim and its Gretl companion by Lee Adkins (PDF). Or check out the Studenmund textbook. And as you search for alternatives, compare reviews. Readers give better reviews to the Hill-Griffiths-Lim textbook and the Studenmund textbook than they do to the Stock-Watson textbook.

Finally, please share your thoughts on these textbooks with me, so that I can design a better course. Thank you!


Problem Set and Reading

(updated: 06 Sept 2017)

On Tuesday (05 Sept), I introduced the problem set. I will introduce it to the Sunday group when we next meet (10 Sept). The problem set will help you understand the material in chaps. 1-5 in the Stock-Watson textbook. So please read those chapters and please work on the problem set.

For econometric examples, you know that I like to use the question of how labor market regulations affect employment outcomes, so please also read Schmitt's discussion of those effects and please read my Analysis of the "Biagi Law". I have also prepared some documentation of the datasets used in class, so please look at that one too.


Employment Rates and the Minimum Wage

(updated: 05 Sept 2017)

update: I have posted an unfinished draft of a paper that documents the labor market data that I collected, summarizes the statistics that I calculated from that data and reports a few of my findings.


As a follow-up to our discussion of the effect that the minimum wage has on employment rates, I combined Vaghul and Zipperer's (WCEG, 2016) minimum wage data with the BLS employment status by state data.

The combined data is available as a CSV file and as Gretl data. I have also made available the R script that I wrote to analyze the combined data.

While examining the data, I noticed that 9 of the 11 states that joined the Confederacy had the lowest minimum wage rates in the country (and the other two weren't much higher), so I grouped the states by Civil War status and obtained the following weighted averages for the period 2001-2016:

Free States 61.0% $7.06 $48,306
Border States 60.7% $6.47 $42,012
Confederacy 59.6% $6.43 $41,738
New States 62.6% $6.91 $41,427

To be fair, some Free States do have a low minimum wage rate, but all of the Confederate States have low minimum wage rates. The Free States also tend to have higher employment rates than the Confederate States.

And overall, states that have higher minimum wage rates tend to have higher employment rates.


First Assignments

(posted: 29 August 2017)

As a follow-up to Sunday's session and a preview of Tuesday's session, I would like to continue our discussion of statistics and probability and then introduce ordinary least squares. To prepare for those sessions, please read chaps. 1-5 in the Stock-Watson textbook. And please take first look at the problem set.

For econometric examples, I like to use labor market data and I'm particularly interested in the question of how labor market regulations affect employment outcomes. For theoretical background, please review my minimum wage and monopsonist problem and then read Schmitt's discussion of the effects of the minimum wage on employment and my Analysis of the "Biagi Law".

Finally, please be aware that the minimum wage in St. Louis fell from $10 to $7.70 yesterday.


Calendar Notes

(posted: 29 August 2017)

Please note that Sunday's group will not meet on 03 Sept (in celebration of Labor Day) and Tuesday's group will not meet on 19 Sept (in celebration of the Jewish new year).

For a complete information, please see the Queens College Calendar.


Welcome to Econometrics

(posted: 26 August 2017)

Welcome to the course website. This site helps me organize the course. I hope you find it helpful.

I have posted a copy of the syllabus. Please review it and please look at the notes and course materials that I have posted below. I have also prepared a problem set for you. We will discuss the solutions to these problems in class.

Please acquire a copy of the Stock and Watson textbook and the Kennedy textbook as soon as possible. To begin the course, I would like to start with a review of statistics and probability, so please read chaps. 1, 2 and 3 in the Stock and Watson textbook before our next class session. To refresh your memory of statistics, you may want to look at my statistics course.


You must do econometrics to learn econometrics. A textbook is helpful, but not sufficient. To learn econometrics, you must actively explore a dataset.

The best dataset to give you is the dataset that I am most passionate about. I want to know how employment protections affect the employment opportunities available to workers.

This is a personal issue for me, but it's also an issue that affects you, your family and your friends, so together let's explore the data and find out how labor law shapes the career opportunities available to you.

So as a starting point for discussion and as an introduction to econometrics, please read my "Analysis of the 'Biagi Law.'" It tests an important null hypothesis and the dataset that the paper explores is one of the datasets that we will explore together this semester.

Then to place the discussion in an American context, please read John Schmitt's (2013) paper on why the minimum wage has no discernible effect on employment.

Having identified an avenue of inquiry, we must place it in a theoretical context to, so please read the wikipedia article on the minimum wage and please study my "minimum wage and the monopsonist" problem.

With theory and data in hand, we will then test the null hypothesis that the minimum wage does not have a significant effect on employment rates.


To conduct a statistical analysis (like the one just described), you will need to install a few (open source) statistical and mathematical software programs on your computer.

Gretl is a great statistical software package for learning econometrics. It has an simple interface and ships with sample datasets. It's a great learning tool and I highly recommend it. As you get better at data analysis, you will want a more flexible tool. I use the R language, which (as the name suggests) is a programming language. For mathematics, I use wxMaxima, which provides a graphical interface to Maxima, a computer algebra system that specializes in symbolic operations (as opposed to numerical computing).

Over the course of the semester, I will provide datasets for you to work with in Gretl. I will avoid asking you to write your own computer code, but to push you in the right direction, I will provide R scripts and wxMaxima notebooks for you to review (and tinker with).

take your time

Finally, please remember that we will cover these topics over the course of the semester. So please begin reading, but please do not rush through the reading. Take the time to understand what you are reading. And enjoy it because econometrics is a lot of fun.

I'm looking forward to working with you this semester.

- Eryk Wdowiak


<< back to the main page