Abstract
Data collection procedures can influence respondents' self-disclosure, accuracy and motivation to complete the interview. In comparing research results across different studies, it is important to use robust measuring instruments. The ‘De Jong-Gierveld Loneliness Scale’ was developed to measure loneliness among different populations and in studies with different designs. Data on this loneliness scale were re-analyzed to investigate the robustness of the scale. The data were from six Dutch surveys. Different interview modes were used for data collection: three surveys with self-administered paper questionnaires, two surveys with face-to-face interviews, and one telephone survey. In order to compare the properties of the loneliness scale, a relatively homogeneous category of respondents was selected: single women between the ages of 25 and 65. An examination of the scale with regard to five aspects of robustness showed in very few cases that it was affected. No evidence was found for the assumption that the use of a self-administered questionnaire would lead to high item non-response, any higher than using other data collection procedures. It was also assumed that in self-administered questionnaires or telephone interviews, a better inter-item homogeneity and a better person scalability would be found in studies with face-to-face interviews. The results sustained this hypothesis. Further, it was believed that the absence of an interviewer would result in greater self-disclosure and therefore in higher scale means. We found on evidence to support this. In general the results showed that the loneliness scale met the psychometric requirements of items non-response, scale homogenity and person scalability. After testing the robustness of the scale, we conclude that it is questionable on two aspects: the inter-item homogeneity and the person scalability.

This publication has 0 references indexed in Scilit: