#publicstatistics — Public Fediverse posts

Dealing with Censored Earnings in Register Data https://d.repec.org/n?u=RePEc:hal:journl:hal-05084494&r=&r=eur
"… In many register #data worldwide a relevant part of earnings and wealth is top-coded (right-censored), , can severely undermine its usefulness. For instance, how can #inequality and top earnings be credibly studied if the right tail of the earnings distribution is missing? Taking a distributional approach that is based on the semi-parametric modelling of the right tail being Pareto-like, we show how the missing tail can be successfully estimated using the administrative censored data.
… The presented distributional approach should not be confused with individuallevel imputations of #censoredData. The latter requires, in addition to the Pareto parameter, the assignment of a rank of to each censored observation. Due to the censoring, these ranks are unobserved… "
#Econometrics #PublicStatistics #economics

BAD DATA
An informative and apolitical new book reminds us that statistics are not always what they seem.

How Do They Know This?

Important insights about #statistics that the public, all scientists and all politicians should know about !!

https://quillette.com/2022/12/08/how-do-they-know-this​

#sociology #sociologist @sociology #politicalscience #econometricians #publicstatistics #PolicyResearch #psychology #policymaking #data #bigdata #baddata @politicalscience #indicators #policyindicators #socialindicators

BAD DATA
An informative and apolitical new book reminds us that statistics are not always what they seem.

How Do They Know This?

Important insights about #statistics that the public, all scientists and all politicians should know about !!

https://quillette.com/2022/12/08/how-do-they-know-this

#sociology #sociologist #politicalscience #econometricians #statistics #publicstatistics #PolicyResearch #psychology #policymaking #data #bigdata #baddata @politicalscience #indicators #policyindicators #socialindicators @sociology