A Rasch Analysis Validation of the Maslach Burnout Inventory-Student Survey with Preclinical Medical Students

Construct: Burnout is a psychological construct characterized by emotional exhaustion that arises from an excess of physical, emotional, and social demands over an extended period. Symptoms of burnout include withdrawal or disengagement from work. Burnout has become an important public health concern due to its association with severe negative consequences across numerous professions. Background: The most widely used instrument for measuring burnout is the Maslach Burnout Inventory (MBI). An adaptation of the MBI, the MBI-Student Survey (MBI-SS), was developed for college students. The MBI-SS consists of 15 items covering 3 domains of burnout: exhaustion, cynicism (CY), and professional efficacy (PE). Although studies have confirmed the validity of the MBI-SS for college student populations, studies of its use with medical students are limited. The purpose of this study was to employ the Rasch model to examine the psychometric properties of the MBI-SS when used with a population of preclinical medical students. Approach: Data were collected from 787 medical students who answered the MBI-SS at the conclusion of their 1st year. A maximum likelihood exploratory factor analysis for ordinal data confirmed the hypothesized three factor structure of the MBI-SS. Subsequently, a Rasch analysis was employed to further evaluate the measurement properties of MBI-SS. We used the Rasch Rating Scale model to investigate the extent to which the three MBI subscales conformed to proper measurement characteristics, including comprehensive coverage of person ability and item difficulty along the latent continuum. Results: Most of the 15 items on the MBI-SS effectively fit the Rasch Rating Scale Model, with minimal measurement error. Respondents effectively used the full range of the rating scale for all 15 items. Two subscales (PE and CY) contained items that were difficult for respondents to endorse, resulting in significant gaps along the measurement continuum. The CY subscale exhibited a slight floor effect. The 3 subscales showed good person reliability, good real-item reliability, and good person separation. Conclusions: The Rasch analysis confirmed that the MBI-SS works well for measuring burnout among preclinical medical students. However, the Rasch analysis was able to identify that additional items are needed to improve the performance of MBI-SS. New items would be targeted at reducing the floor effect for the CY subscale and filling the other gaps in measurement along the latent continuum for the PE and CY subscales.