AIAS Lunch Seminar 14 June: Annamaria Bianchi, Stephanie Steinmetz & Kea Tijdens

Challenges and pitfalls of measuring wages via web surveys – some explorations

Annamaria Bianchi (AIAS Guest, University of Bergamo)
Stephanie Steinmetz (AIAS, assistant professor of Sociology at the University of Amsterdam)
Kea Tijdens (Research coordinator AIAS)

Day: Thursday 14 June 2012
Time: 12.15 – 13.15 hrs.
Location: AIAS, 3rd floor, M building, Plantage Muidergracht 12, Amsterdam
Registration: Please send an email, preferably before Tuesday 12 June 12.00 hrs, to register.
A sandwich will then be provided.


Collecting data on wages is central for socio-economic research. However, besides high rates of people who do not answer wage-related questions, measurement issues are also relevant especially for country comparisons. Most data from official statistics are too aggregated to allow for detailed individual level analyses which are crucial for supporting manager decisions and encouraging innovative political-economic ideas in the long run. In this context, web surveys seem to offer a lot of advantages, such as worldwide coverage, cost benefits and a fast data collection process. Especially for sensitive questions, like income, they might also provide more reliable results as the often observed social desirability effects can be eliminated. Although, web surveys could represent a good integration to official statistics data, they encompass many methodological challenges. A core problem is related to the representativeness of the data as the sub-population with Internet access might be quite specific. Against this background, the driving research question is whether web surveys related to wages are representative and if not how representativeness can be achieved. For the analyses two different Dutch web surveys are used focusing on labor markets in 2009 (WageIndicator and the LISS panel). Their characteristics are compared with reference data from official statistics measuring the bias. For a selection of core variables adjustment models, such as simple weighting, propensity score adjustment and the MaxEnt approach, are applied. The results will offer a detailed bias descriptions of wages and other wage-related core variables. Furthermore, they will explore the potentials and constrains of different adjustment methods for probability and non-probability web surveys.

Click here for an overview of all lunch seminars from January – July 2012

| More