RECSM Deputy Directors Wiebke Weber and Melanie Revilla present a poster about Improvements in the Survey Quality Predictor (SQP) software: from SQP2 to SQP3 in the Eutopia Science Fair 2021.

There is no measurement without errors. In particular, it is well-known that survey questions suffer from measurement errors. However, survey questions are used in a huge amount of research, across many different disciplines, from social sciences to health science. Nevertheless, most of this research ignores these measurement errors in the analyses. As a consequence, results can be biased. It is thus crucial to develop tools that provide information about the size of measurement errors for survey questions in a way that is accessible to most researchers.

This poster presents such a tool: the Survey Quality Predictor (SQP) software, a survey quality prediction system for questions used in survey research available for free at sqp.upf.edu. SQP is also a database of questions with measurement quality predictions, where measurement quality is defined in the frame of the True Score model (Saris and Andrews, 1991) as the variance in the observed answers explained by the latent concept of interest. Thus, measurement quality is the complement of measurement errors. Said differently, measurement errors = 1 – measurement quality. Measurement quality can be computed as the product of reliability and validity.

Check it out: https://eutopia-university.eu/5-opinions-and-society/