Lars P. Syll

.                                                                                                                                  [embedded content]

[embedded content] From a theoretical perspective, Simpson’s paradox importantly shows that causality can never be reduced to a question of statistics or probabilities. To understand causality we always have to relate it to a specific causal structure. Statistical correlations are never enough. No structure, no causality. Simpson’s paradox is an interesting paradox in itself, but it can also highlight a deficiency in the traditional econometric approach towards...

Conditional exchangeability and causal inference In observational data, it is unrealistic to assume that the treatment groups are exchangeable. In other words, there is no reason to expect that the groups are the same in all relevant variables other than the treatment. However, if we control for relevant variables by conditioning, then maybe the subgroups will be exchangeable. We will clarify what the “relevant variables” are, but for now, let’s just say...

Le plan de relance français est-il déjà obsolète avant d’avoir servi ? En tout cas, sa forme et son application sont sérieusement remises en cause par le deuxième confinement qui est en train de replonger dans le rouge tous les indicateurs économiques, ragaillardis à la faveur de l’été. Il voyait pourtant loin cet ambitieux dispositif, baptisé « France Relance », le regard volontairement tourné vers 2030. C’est bien justement ce qu’on lui reproche aujourd’hui : avoir la tête...

.[embedded content] O day, arise! The atoms are dancing.Thanks to Him the universe is dancing.The souls are dancing, overcome with ecstasy.I’ll whisper in your ear where their dance is taking them.All the atoms in the air and in the desert know well, they seem insane.Every single atom, happy or miserable,Becomes enamoured of the sun, of which nothing can be said.Jalāl ad-Dīn Muhammad Rūmī (1207-1273)

Checking your statistical assumptions The assumption of additivity and linearity means that the outcome variable is, in reality, linearly related to any predictors … and that if you have several predictors then their combined effect is best described by adding their effects together …  This assumption is the most important because if it is not true then even if all other assumptions are met, your model is invalid because you have described it incorrectly....

How scientists manipulate research [embedded content]All science entails human judgment, and using statistical models doesn’t relieve us of that necessity. Working with misspecified models, the scientific value of significance testing is actually zero — even though you’re making valid statistical inferences! Statistical models and concomitant significance tests are no substitutes for doing real science. In its standard form, a significance test is not the...

.                                                                                                                           [embedded content]

Joe Biden — 46th president of US .                                                                                                                                  [embedded content]

. [embedded content]