The dirty data index – assessing the quality of survey data in international comparison

Abstract

In 2012, Blasius and Thiessen developed the dirty data index (DDI) as an index for measuring the quality of survey data. The DDI is based on the quantifications from categorical principal component analysis which works on item batteries of ordered categorical data such as five-point Likert-scaled items. This is an ongoing work where we further develop the index for application in international comparison. As an example we use data from the International Social Survey Programme 2012, Family and Changing Gender Roles, including 36 countries with a total of more than 56,000 cases