THE INFLUENCE OF DATA-COLLECTION METHOD ON STRUCTURAL MODELS - A COMPARISON OF A MAIL, A TELEPHONE, AND A FACE-TO-FACE SURVEY

In survey data, four potential sources of measurement error can jeopar dize the results: the respondents, the interviewers, the questions, an d the data collection method In the past two decades, a shift has occu rred in the way survey data are collected; telephone surveys and to a lesser degree, mail surveys are now more extensively used. This has st imulated empirical research on the influence of the data collection me thod on data quality. Most of these mode comparisons used univariate c riteria. In this study we concentrate on she potential influence of th e data collection method on two substantive structural models. A contr olled field experiment was conducted in which a mail, a telephone, and a face-to-face survey were compared Using multigroup comparison, two substantive structural equation models (one for loneliness and one for general well-being) were compared across she different data collectio n methods. The different data collection methods turned our to produce significantly different covariance matrices. Subsequent analyses show ed that structural models, based on these covariance matrices, also di ffered.