Purpose – The purpose of this research is to investigate whether the participants in an employee survey who do not answer one or more demographic items differ systematically from those who fill out all demographic items. Design/methodology/approach – Logistic regression, with affective commitment, job satisfaction, and attitude towards leadership as predictors of responding to demographic items is used to analyze the data of an employee survey in a German company. Findings – Survey participants with low commitment, poor job satisfaction, and negative attitudes towards leadership are more likely not to provide demographic information, while highly committed participants tend to answer all demographic items. Non‐respondents are also more concerned that their skills become obsolete, and they feel that employees do not have enough say. Research limitations/implications – The paper does not distinguish among demographic item non‐respondents on the basis of how many and which items are omitted. Future research should take a closer look at the different sensitivity of the demographic items. Practical implications – Managers should be aware that it is likely that the results of an employee survey for their organizational subunits tend to be biased and show a picture that is too optimistic as compared to company‐wide results. Originality/value – The value of the paper lies in demonstrating a systematic and practically important bias in employee survey statistics that has been overlooked so far.
International Journal of Manpower – Emerald Publishing
Published: May 9, 2008
Keywords: Employees; Demographics; Job satisfaction; Surveys; Germany