The Structure of the Narcissistic Personality Inventory With Binary and Rating Scale Items

Abstract

Narcissistic Personality Inventory (NPI) items typically have a forced-choice format, comprising a narcissistic and a nonnarcissistic statement. Recently, some have presented the narcissistic statements and asked individuals to either indicate whether they agree or disagree that the statements are self-descriptive (i.e., a binary response format) or to rate the extent to which they agree or disagree that these statements are self-descriptive on a Likert scale (i.e., a rating response format). The current research demonstrates that when NPI items have a binary or a rating response format, the scale has a bifactor structure (i.e., the items load on a general factor and on 6 specific group factors). Indexes of factor strength suggest that the data are unidimensional enough for the NPI's general factor to be considered a measure of a narcissism latent trait. However, the rating item general factor assessed more narcissism components than the binary item one. The positive correlations of the NPI's general factor, assessed when items have a rating response format, were moderate with self-esteem, strong with a measure of narcissistic grandiosity, and weak with 2 measures of narcissistic vulnerability. Together, the results suggest that using a rating format for items enhances the information provided by the NPI.

Equivalence of Narcissistic Personality Inventory constructs and correlates across scoring approaches and response formats

“…It is possible that the psychometric properties of the NPI would be clarified if the 40 couplets were rated as individual items. In fact, multiple studies have applied the NPI in a single-stimulus format (Bogart, Benotsch, & Pavlovic, 2004;Boldero, Bell, & Davies, 2015;R. P. Brown & Zeigler-Hill, 2004;Egan & Lewis, 2011;Gerbasi & Prentice, 2013;Jordan, Spencer, Zanna, Hoshino-Browne, & Correll, 2003;Lee, Gregg, & Park, 2013;Morf & Rhodewalt, 1993), although these investigations did not check whether equivalent constructs were measured across formats.…”

“…Small to moderate correlations between socioeconomic status and NPI scores were also found in our study for the total score and the leadership and vanity facets (e.g., latent r = .22 for total NPI) in the unidimensional forced-choice format. For data based on the multidimensional forced-choice format and the true/false and rating scale format, socioeconomic status was positively related Future research could also investigate the incremental validity of one facet over the others or investigate in how far the specific facets predict criteria over and above a shared narcissism dimension in the context of a bifactor model (see for example Boldero et al, 2015).…”

French Adaptation of the Narcissistic Personality Inventory in a Belgian French-Speaking Sample

“…According to Barelds and Dijkstra (2010), the correlation between the dichotomous forced-choice format and a 5-point Likert version of the scale (using the dichotomous statements as anchor points) is excellent ( r = 0.97; p < 0.01). In Boldero et al (2015) the use of a 6-point rating scale showed a similar correlation ( r = 0.96; p < 0.01).…”

“…Kubarych et al (2004) proposed a 2-factor or a 3-factor model with (1) Power and (2) Exhibitionism as the two factors of the first one, and (1) Power, (2) Exhibitionism, and (3) Being a Special Person as the three factors of the second one. Inconsistent results in factor structure are generally considered to be associated with methodological differences between studies (see in Boldero et al, 2015). However, even the most recent studies that have taken the current psychometric recommendations into account (performing tetrachoric correlation matrix because of the dichotomous format, using the scree plot and interpreting the items' meanings to obtain a factor solution, …), failed to replicate the 7-factor structure (Corry et al, 2008; Ackerman et al, 2011).…”

“…They observed a Leadership/Authority factor similar to Corry et al's (2008) but suggested to split the Exhibitionism/Entitlement dimension into two parts: Grandiose Exhibitionism and Entitlement/Expoitativeness. However, Boldero et al (2015) point toward the fact that, despite psychometrical precautions, some methodological differences remain between Corry et al's (2008) and Ackerman et al's (2011) studies regarding the criteria for the EFA (type of rotation, choice of estimator and utilization of the internal consistency indices). Moreover, Boldero et al (2015) emphasize the superiority of the parallel analysis (Horn, 1965) over the traditional criteria (scree plot, eigenvalues) in determining the number of factors to retain, and support the choice of an oblique rotation in this context (because of probable correlated items).…”