Publications by Economics and R - R posts
Lasso and the Methods of Causality
An exciting, quite new branch of econometrics studies how machine learning techniques can be adapted to consistently estimate causal effects. For example, the widely cited article by Belloni, Chernozhukov and Hansen (2014) introduces a post double selection method where one first runs two lasso regressions to select suitable control variables for...
18965 sym R (7766 sym/23 pcs) 6 img
RTutor: The Causal Effects of Sweden’s CO2 Tax
Most economists agree that putting a price on greenhouse gas emmissions either in form of emission certificates or a carbon tax should be the main instrument to combat climate change in a cost-efficient manner. Sweden has introduced a steadily increasing Carbon tax in 1991 which reached in 2020 a level of 110 Euro per ton CO2, which makes it the ...
3859 sym 6 img
RTutor: How do competition policy and industrial policy affect economic development?
Competition authorities regularly decide (and often defend in legal courts) whether to allow or forbid a merger, what fines to impose for illegal collusion, whether to restrict certain business practices of firms that have achieved a dominant position, and particularly in the EU, whether certain forms of state aid distort competition in the commo...
3973 sym 4 img
About confidence intervals for the Biontech/Pfizer Covid-19 vaccine candidate
Probably, many of you have read the positive news from the Biontech/Pfizer press release from November 9th: “Vaccine candidate was found to be more than 90% effective in preventing COVID-19 in participants without evidence of prior SARS-CoV-2 infection in the first interim efficacy analysis” Not being a biostatistician, I was curious how va...
4196 sym R (1120 sym/4 pcs) 2 img
A look at Biontech/Pfizer’s Bayesian analysis of their Covid-19 vaccine trial
Let’s take again a look at Biontech / Pfizers vaccine candiate for which a press release stated more than 90% efficacy. As noted in my previous post Biontech/Pfizer actually use a Bayesian approach to assess the efficacy of their vaccine candiate. In their study plan we find the following relatively short descriptions: “The criteria for succ...
6136 sym R (1747 sym/8 pcs) 10 img
More on Biontech/Pfizer’s Covid-19 vaccine trial: Adjusting for interim testing in the Bayesian analysis
Here is one more post about Biontech/Pfizer’s vaccine trial. That is because my previous two posts (here and here) have so far ignored one interesting topic: How do Biontech/Pfizer statistically account for interim analyses? Studying this topic gives us also general insights into how adaptive trial designs with multiple success conditions can b...
11203 sym R (3632 sym/9 pcs) 8 img
To peek or not to peek after 32 cases? Exploring that question in Biontech/Pfizer’s vaccine trial
This is my 4th post about Biontech/Pfizer’s Covid-19 vaccine trial. If you are missing background, please first look at my 2nd post and 3rd post. Biontech/Pfizer originally planed to analyze the vaccine efficacy at 5 stages: after 32, 62, 92, 120 and finally 164 Covid-19 cases have been observed among the 43538 study participants that consisted...
17981 sym R (4026 sym/8 pcs) 4 img
Reverse Engineering AstraZeneca’s Vaccine Trial Press Release
In their press release AstraZeneca provide the following information about an interim analysis of their vaccine trial: One dosing regimen (first a half dose and at least a month later a full dose) with 2741 participants showed 90% efficacy Another dosing regimen (two full doses at least one month apart) with 8896 participants showed 62% efficac...
7940 sym R (1812 sym/5 pcs) 4 img
What to do if a package you need is no longer on CRAN?
Currently, I am teaching a new course Empirical Economics with R. The RTutor problem set for the chapter on Difference-in-Difference estimation uses the great package lfe. I consider it an essential package to convince Stata users (still most empirical economists) to move to R, because it allows to combine with a single function call fast fixed e...
4281 sym R (127 sym/1 pcs) 4 img 1 tbl
A quiz about a 95% CI interpretation in the FDA Covid vaccine meeting
Personally, I think it was a great decision of the FDA to make the material of their important meeting for the Emergency Use Authorization of the Biontech/Pfizer vaccine publicly available. In particular, they published the whole meeting as a YouTube video, which contains very interesting presentations. (I hope the EMA will, perhaps later in less...
3688 sym R (379 sym/1 pcs) 2 img