Lars P. Syll

.[embedded content] A great set of lectures — but yours truly still warns his students that regression-based averages is something we have reasons to be cautious about. Suppose we want to estimate the average causal effect of a dummy variable (T) on an observed outcome variable (O). In a usual regression context one would apply an ordinary least squares estimator (OLS) in trying to get an unbiased and consistent estimate: O = α + βT + ε, where α is a constant intercept, β a...

Why data alone does not answer counterfactual questions. .[embedded content]

Your’s truly won’t have to share Keynes regret. Champagne is one of the few things in life he never says no to.

What are the key assumptions of linear regression models? In Andrew Gelman’s and Jennifer Hill’s Data Analysis Using Regression and Multilevel/Hierarchical Models the authors list the assumptions of the linear regression model. The assumptions — in decreasing order of importance — are: 1. Validity. Most importantly, the data you are analyzing should map to the research question you are trying to answer. This sounds obvious but is often overlooked or ignored...

Does smoking — really — help you fight COVID-19? .[embedded content]

Gendern? Nicht mit mir! .[embedded content]

Boken jag aldrig ger bort Just nu håller min institution på och flyttar till nya lokaler nere vid hamnbassängen i Malmö. Flyttar är bra tillfällen att passa på och göra sig av med, eller ge bort, en massa papper och böcker som med tiden bara kommit att värma tjänsterummets hyllor. Ett och annat skönlitterärt alster har också fått göra bekantskap med soplårorna. Men en bok som jag alltid haft på hedersplats i mitt rum varken slängs eller ges bort. Den boken...

Counterfactual modelling (student stuff) .[embedded content]

Challenging causal models — the low birth weight paradox .[embedded content] Lesson learned? Beware of collider bias and ‘censored’ data!

Impfgegner — Leute mit amputiertes Gehirn .[embedded content]