GESIS Training Courses

Wiss. Koordination

Dr. Nora Skopek
Tel: +49 621 1246277

Administrative Koordination

Claudia O'Donovan-Bellante
Tel: +49 621 1246221

Multilevel modeling and analysis of PIAAC in Stata

Dr. Jan Paul Heisig

Datum: 03.04 - 04.04.2017 ics-Datei

Veranstaltungsort: B2,8


The first part of the workshop focuses on the analysis of PIAAC using the statistics package Stata. Emphasis is on two features of the PIAAC data that lead to challenges for the analyst: 1) the availability of multiple (10) plausible values for individual competence scores and 2) the use of jackknife replication methods for variance estimation. Different approaches to accounting for these features are presented. Participants will be introduced to the piactools package developed by the Polish PIAAC team, a convenient option that is, however, compatible only with a limited number of (regression) methods. Participants will also learn more flexible strategies for correctly estimating quantities that are not supported by piaactools (e.g., average marginal/partial effects). The second part of the workshop reviews different approaches to analyzing multilevel data (mixed models, clustered standard errors, two-step procedures), with the emphasis again being on PIAAC and thus on country comparisons. Advantages and disadvantages of the different approaches and their implementation in Stata will be discussed.


Doctoral and postdoctoral researchers interested in using PIAAC, especially if interested in using it to explore the effects of contextual factors (e.g., education systems, public policy). 


  • How to account for special features of PIAAC in Stata (plausible values, replication weights)
  • General strategies for dealing with these challenges when standard routines are not flexible enough
  • Basic understanding of alternative approaches to modeling multilevel/hierarchical data, especially mixed effects multilevel models, with a focus on identification of context effects


  • Good working knowledge of at least one statistical software package, preferably Stata
  • Good understanding of regression analysis




Weitere Informationen