Consider the following data generating process: set.seed(1) n = 100000 x = rnorm(n) eta1 = rnorm(n) # measurement error1 noisy1 = x + eta1 eta2 = rnorm(n) # measurement error2 noisy2 = x + eta2 u = rnorm(n) beta0=0; beta1 = 1 y = beta0+beta1*x + u ... [Read more...]

[Read more...]

During the financial crisis and great recession from 2007 to 2009 the US lost 8.6 million jobs. We know that a lot of things happened in the crisis, like a crisis of trust in the financial system including the collapse of Lehman Brothers. Another relat... [Read more...]

Difference-in-Difference (DID) estimation is a very intuitive and popular approach to estimate causal effects (see here for my take on teaching it). If you know about DID and want to directly know how to create a plot to assess the parallel trends assu... [Read more...]

Assume you are an incumbent local politician that can exert certain control on your local public savings bank. Would you try to increase lending before local elections to polish economic performance? In their great article Electoral Cycles in Savings ... [Read more...]

This is just a short update to my previous post. Bundestag elections are over and according to the preliminary official results the new Bundestag will have 735 members. That’s 32 more than the previous 703 members, but at least far from 841 members pre... [Read more...]

On Sunday (26th of September), we will have the main parliamentary elections in Germany. The deepl translation of the election law states: §1 (1) Subject to the deviations resulting from this Act, the German Bundestag shall consist of 598 Members o... [Read more...]

Finally an RTutor problem set about insurance! It is about time given that Ulm University is ranked worldwide as the 2nd best non-business school for research in Risk, Management and Insurance and Actuarial Sciences: Source: The UNL Global Resear... [Read more...]

An earlier post described the impressive collection of US data that Chetty et al. made available to illuminate the economic impacts of Covid and accompanying policy measures. As part of her Master thesis at Ulm university Alexandra Aehle has created a... [Read more...]

I wrote my new R package xglue because for a recent working paper, we needed to generate several customized Latex tables, like the following excerpt: While all the data can be easily merged into a data frame in R, creating this fairly customized L... [Read more...]

[Read more...]

I was very impressed when watching Raj Chetty’s video presentation in the AEA panel “The Economic Impact and Policy Response to the Pandemic: What Happened in 2020 and What is Ahead?”. He is part of a group (Chetty, Friedman, Hendren, Stepner, and the ... [Read more...]

Over the years I have written several Shiny apps that rely on SQLite databases. One example is my shiny app to find reproducible economic articles with data supplement: https://ejd.econ.mathematik.uni-ulm.de. The underlying data is stored in a SQLite d... [Read more...]

Chapter 5 of my course Empirical Economics with R covers instrumental variable (IV) estimation. While being one of the most popular methods in academic economic papers for estimating causal effects (see e.g. the statistics here), I was not sure whethe... [Read more...]

Many EU citizens (including me) are frustrated that due to lower supply, vaccinations in EU countries currently proceed substantially slower than in the US or the UK. In this post I make some simple economic arguments (illustrated with R) for how the common approach of the EU members might have ... [Read more...]

RStudio version 1.4 brought many great enhancements. My favorite feature is the new visual markdown editing mode. This allows to solve interactive RTutor problem sets with a shiny look directly in the RStudio editor. Here is a screenshot: The exam... [Read more...]

Chapter 4 of my course Empirical Economics with R covers a popular strategy to estimate causal effects: difference-in-differences estimation. Inspired by Matt Taddy’s textbook example, the main application is to estimate the causal effects of search en... [Read more...]

The estimated vaccine efficacies from the phase III clinical trials provide good information of how strongly a Covid-19 vaccine reduces the probability of a symptomatic Covid-19 infection in the vaccinated individual, e. g. 95% for the Biontech/Pfizer vaccine. However, the probability that a vaccinated person still becomes infected without symptoms ... [Read more...]

[This is a duplicate of the previous post, which was not detected by all blog aggregators.] Chapter 3 of my course Empirical Economics with R mainly dives into the difficulties of estimating causal effects. (See the previous post for an overview of th... [Read more...]

This semester I teach a new course: Empirical Economics with R. All material is online available, including video lectures with quizzes and interactive RTutor problem sets, which are perhaps the most important part of the course. One goal when designing the course was to motivate most concepts with one or ... [Read more...]