Do We Really Need Multiple-Item Measures in Service Research?

Abstract

Increasingly, marketing academics advocate the use of multiple-item measures. However, use of multiple-item measures is costly, especially for service researchers. This article investigates the incremental information of each additional item in a multiple-item scale. By applying a framework derived from the forecasting literature on correlated experts, the authors show that, even with very modest error term correlations between items, the incremental information from each additional item is extremely small. This study’s “information” (as opposed to “reliability”) approach indicates that even the second or third item contributes little to the information obtained from the first item. Furthermore, the authors present evidence that added items actually aggravate respondent behavior, inflating across-item error term correlation and undermining respondent reliability. Researchers may want to consider the issue of item information in addition to reliability. This article discusses ways in which researchers can construct scales that maximize the amount of information scale items offer without compromising measurement reliability.

Reversed item bias: An integrative model.

“…If future research were to corroborate the hypothesized effect, it would imply that researchers should refrain from using unbalanced scales, in which a few reversed items are included among many regular items (possibly to counter the criticism that all items are keyed in the same direction). In particular, reversed items should not follow a long list of regular items as this may lead respondents to overlook variation in item polarity (Drolet & Morrison, 2001). Although the empirical evidence is currently somewhat ambiguous, we believe the best option is to disperse the items measuring the focal construct across the questionnaire and to mix them with unrelated buffer items.…”

Collaboration, connectedness, and community: An examination of the factors influencing student persistence in virtual communities

“…given the correlated nature of the error terms of the lower-order factors, this was deemed acceptable (Drolet & Morrison, 2001;Hayduk & Littvay, 2012). Indicator reliability was assessed by evaluating the outer loadings of each indicator on its respective construct (see Table 2.…”

Global Consumer Innovativeness: Cross-Country Differences and Demographic Commonalities

“…Parsimony is important because extensive item redundancy puts a considerable burden on the study of consumer innovativeness across countries and categories. More important, multi-item measures may reduce the quality of respondent responses and add very little information over a single-item measure (Drolet and Morrison 2001). An extensive search of the literature on innovativeness and related concepts led us to ten key dimensions along which researchers have tried to define consumer innovativeness.…”