Does correction for measurement error have an effect on the structure and comparability of basic human values?

Lilleoja, Laur; Saris, Willem E.

Does correction for measurement error have an effect on the structure and comparability of basic human values?

License

Citation

Lilleoja, L, Saris, W. Does correction for measurement error have an effect on the structure and comparability of basic human values?. 2015. handle: http://hdl.handle.net/10230/30797

This citation was generated automatically.

Abstract

It is a well-known fact that survey data always contains measurement errors, which can in different ways bias the results of an analysis (Alwin, 2007). In quantitative research, this problem has usually been ignored due to lack of quality estimates and the complexity of correction procedures. However, this argument is not valid anymore, as there exists a new approach to determining the quality of any specific question based on a prediction of quality using the program SQP2 (Survey Quality Predictor 2.1), which in turn allows for the correction of measurement error by following a relatively simple procedure as described by Saris and Gallhofer (2014) and illustrated by DeCastellarnau and Saris (2014). During recent years, there has been an increasing number of studies researching the structure of basic human values (Schwartz, 1992), which has resulted in improvements to the theory and led to a new 19-factor value model (Schwartz et al., 2012; Saris, Knoppen, & Schwartz, 2013). However, none of the recent studies have concurrently taken into account random and systematic errors, which can potentially have an effect on the structure. Therefore in this paper we will try to overcome this shortcoming and will be analysing the effect of the correction for both types of measurement error on the structure of basic human values. We use the same representative data from Estonia that was used in a study by Lilleoja and Saris (2014), which enabled us to compare value structures before and after the correction for measurement error. Due to the existence of a large ethnic minority in Estonian society, the sample additionally allowed testing the equivalence of the measurements in the two subpopulations after correcting for measurement error. This study shows that the correction for measurement error provides additional support for the validity of a new value structure and it also sheds some new light on cross-cultural equivalence.