Are reflective models appropriate for very short scales? Proofs of concept of formative models using the Ten-Item Personality Inventory.

Abstract

Because of their length and objective of broad content coverage, very short scales can show limited internal consistency and structural validity. We argue that it is because their objectives may be better aligned with formative investigations than with reflective measurement methods that capitalize on content overlap. As proofs of concept of formative investigations of short scales, we investigate the Ten-Item Personality Inventory (TIPI). In Study 1, we administered the TIPI and the Big Five Inventory (BFI) to 938 adults and fitted a formative Multiple Indicators Multiple Causes model, which consisted of the TIPI items forming five latent variables, which in turn predicted the five BFI scores. These results were replicated in Study 2 on a sample of 759 adults, but this time with the Revised NEO Personality Inventory (NEO-PI-R) as the external criterion. The models fit the data adequately, and moderate to strong significant effects (.37 < |β| < .69, all ps < .001) of all five latent formative variables on their corresponding BFI and NEO-PI-R scores were observed. This study presents a formative approach that we propose to be more consistent with the aims of scales with broad content and short length like the TIPI.