Category: news

Updated forecasts for the UEFA Euro 2020 knockout stage

news

After all group stage matches at the UEFA Euro 2020 we have updated the knockout stage forecasts by re-training our hybrid random forest model on the extended data. This shows that England profits most from the realized tournament draw. Read more ›

Evaluation of the UEFA Euro 2020 group stage forecast

news

A look back on the group stage of the UEFA Euro 2020 to check whether our hybrid machine learning forecasts based were any good... Read more ›

Working paper for the UEFA Euro 2020 forecast

news

A working paper describing the data and methods used for our probabilistic UEFA Euro 2020 forecast, published earlier this week, is available now. Additionally, details on the predicted performance of all teams during the group stage are provided. Read more ›

Hybrid machine learning forecasts for the UEFA Euro 2020

news

Probabilistic forecasts for the UEFA Euro 2020 are obtained by using a hybrid model that combines data from four advanced statistical models through random forests. The favorite is France, followed by England and Spain. Read more ›

ivreg: Two-stage least-squares regression with diagnostics

news

The ivreg function for instrumental variables regression had first been introduced in the AER package but is now developed and extended in its own package of the same name. This post provides a short overview and illustration. Read more ›

Network trees: networktree 1.0.0, web page, and Psychometrika paper

news

Version 1.0.0 (and actually 1.0.1) of the R package 'networktree' with tools for recursively partitioning covariance structures is now available from CRAN, accompanied by a paper in Psychometrika, and a dedicated software web page. Read more ›

Bias reduction in Poisson and Tobit regression

news

While it is well-known that data separation can cause infinite estimates in binary regression models, the same is also true for other models with a point mass at the bounday (typically at zero) such as Poisson and Tobit. It is shown why this happens and how it can be remedied with bias-reduced estimation, along with implementations in R. Read more ›

Tools for colors and palettes: colorspace 2.0-0, web page, and JSS paper

news

Version 2.0-0 of the R package 'colorspace' with tools for manipulating and assessing colors and palettes is now available from CRAN, accompanied by an updated web page, and a paper in the Journal of Statistical Software (JSS). Read more ›

Robust covariance matrix estimation: sandwich 3.0-0, web page, JSS paper

news

Version 3.0-0 of the R package 'sandwich' for robust covariance matrix estimation (HC, HAC, clustered, panel, and bootstrap) is now available from CRAN, accompanied by a new web page and a paper in the Journal of Statistical Software (JSS). Read more ›

Structural equation model trees with partykit and lavaan

news

To capture heterogeneity in structural equation models (SEMs), the model-based recursive partitioning (MOB) algorithm from partykit can be coupled with SEM estimation from lavaan. Read more ›