Personal space: The conceptual and measurement implications of structural equation models.

Abstract
The stop-distance procedure for measuring personal space is investigated using maximum likelihood estimation of structural equation models. The results challenge the factor model implicitly underlying recent estimates of the reliability of the stop-distance procedure and convincingly demonstrate that stop-distance measurements are much more reliable than has been thought. For the 3 data sets considered, about 97% of the variance in observed distances arises from structural nonmeasurement-error sources. About 8% of the variance in measured distances is due to real but unifdentified sources. This variance reflects unidentified causal determinants of spacing, but it is not measurement error. There are few social science phenomena that can be measured as precisely as personal space. The repeated failures of the factor model and the repeated successes of the simplex model require a fundamental shift in our conceptualization of personal space. The failure of the factor model implies that momentary spatial preferences should not be considered as merely reflecting a stable underlying preference, nor should it be considered as a repeated and momentary construction based on stable situational features. Personal space should be considered as a dynamic process that is continually open to modification yet which in fact shows considerable stability due to the persistence of previously maintained distances.

This publication has 0 references indexed in Scilit: