Willem E. Saris: Correction for measurement error in the Social Sciences and Business research using SQP 2.0
Survey research is the most frequently used data collection method in the following disciplines: Sociology, Political Science, Communication, Opinion research and Marketing (Saris and Gallhofer 2007). Nearly everybody agrees that such data contains serious measurement errors, but only very few researchers try to correct for these errors.
Alwin (2007) suggests that 50% of the variance of the observed variables in survey research is error. In that case the correlations between the variables of interest will be underestimated by 50%. If the measurement errors in the different variables are not the same, the comparison of the sizes of effects of variables on each other will be wrong. If the sizes of the measurement errors are different across countries, cross national comparisons of relationships between variables cannot be made. There is ample evidence for these differences in measurements errors across variables, methods and countries (Alwin 2007, Saris and Gallhofer 2007).
There are two ways to improve the situation. The first is to try to improve the quality of the measures so that the errors will be minimal. The second is to correct for measurement errors. While many people have tried to improve the measurement in survey research one has to conclude that considerable errors will remain.
So correction for measurement errors is essential for the social sciences. The correction for measurement errors can be done in a simple way but it requires that the sizes of the error variances are known for all observed variables. So the major problem is to get good estimates of the error variances for all observed variables.
In my presentation I will show how my research groups have tried to solve this problem through the years with as a last result the program SQP2.0 which provides predictions of the quality of survey questions.