1
$\begingroup$

I have been writing some lecture notes about basic concepts of econometrics for a group of engineers. I would like to use free data sources where I could use without a specific permission but only citing the original paper (or other papers that have also used it) that used it.

I also would like to use representative data from the field. I would like to spend some time exploring the importance of the dataset and in some extent to provide a kind of validation of the available work that uses the dataset. In addition, I want to introduce the concept and provide the econometric exercises, but the students may by their own investigate more about the data (and possible extensions) in the associated papers.

The notes I am writing include most important concepts of econometrics, such as OLS, FGLS, Instrumental Variables, GMM, Panel data (fixed effects, random effects, dynamic panels), and time series (ARMA, ARIMA, VAR, Cointegration).

I have alread find this link about instrumental variables Open access datasets for teaching IV regression. I think they are really good suggestions. Thus, I do not need extra suggestions about this topic.

People usually refer to the amazing Wooldridge datasets, but I understand that I cannot freely use them.

Can you suggest me some sources?

$\endgroup$

1 Answer 1

2
$\begingroup$

If you are looking purely for educational datasets, then R has large number of 'built in' datasts that can be freely shared.

Even if you do not want to teach R because you want to use other language or program for students you can easily take R built in dataset and export it into csv or excel and use it in any other language or program of your choice.

Here is a short article about how to access these datasets. There is enough variety of datasets to teach all standard econometrics models.

$\endgroup$
4
  • $\begingroup$ This data seems to be very interesting. I didn't know them since I am a Python user. I will take a look carefully, but it seems that they do not have the reference papers. $\endgroup$ Apr 28, 2023 at 22:22
  • 1
    $\begingroup$ generally speaking, in R, the dataset is associated with an R package. So, you need to figure out which package the data set is from. Then, you can go to "packages" at www.cran.r-project.org ( I hope that I spelled that correctly ) and download the pdf ( also called a help file ) that explains the various functions being used in the package. But it usually will explain the data set also. If you want to get into R, there are so many books. I'm not even sure what the latest and greatest are. My recommendation is "Advanced R" by Hadley Wickham unless you have very little programming experience. $\endgroup$
    – mark leeds
    Apr 29, 2023 at 2:55
  • 1
    $\begingroup$ Note that the recommendation above is meant personally for you. It's not meant to recommend that you use it for teaching your class. That's an altogether different issue because there are so many intro books. I was thinking more of a recommendation for someone who has programmed a decent amount and wants to get into R in serious depth. $\endgroup$
    – mark leeds
    Apr 29, 2023 at 3:00
  • 1
    $\begingroup$ If you use python and compute econometric models, you are most likely aware of the statsmodels package, which contains the r datasets as well. The syntax also follows the R syntax in the package. $\endgroup$
    – AKdemy
    Apr 29, 2023 at 9:14

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.