Preprints are early versions of research articles that have not been peer reviewed. They should not be regarded as conclusive and should not be reported in news media as established information.
Development and Validation of the Multidimensional Scale of Turnover Reasons
preprintposted on 28.11.2018, 17:16 by Igor MenezesIgor Menezes, Ana Cristina Menezes, Jersica Assis, Elton Moraes, Damar Sandbrand, Patryk Muszynski, Tamás Várkonyi, Kai Ruggeri
The purpose of this study is to make available to researchers and practitioners a new instrument to measure turnover reasons based on a compensatory Multidimensional Item Response Theory (MIRT) model. Since extrinsic and intrinsic aspects are measured, item parameters and individual scores are provided for each dimension. An alternative procedure for standardization (WS scores) was introduced for the calculation of respondents’ scores. The Multidimensional Turnover Reasons Scale (MTRS) was administered to 615 workers. Multidimensional Graded Response Model was chosen for item calibration and EAP estimation technique was deployed for producing the individual’s factor scores. The two-dimensional structure was confirmed, with 28 out of 30 items properly measuring turnover reasons. Items more likely to predict turnover reasons and an interpretation about individual scoring under a MIRT approach are presented. Finally, when compared to estimated factor scores, WS scoring technique shows very attractive psychometric properties, which suggests it could be used in place of factor scores for the standardization of multidimensional models, under the scenario in consideration. The MTRS can help companies to work beyond their turnover rates, mainly on the analyses of their talented employees with stronger reasons to leave the organization, and then create new strategies aimed at worker retention.
Declaration of conflicts of interestNo conflicts of interest
Corresponding author firstname.lastname@example.org
Lead author countryUnited Kingdom
Lead author job roleHigher Education Lecturer
Lead author institutionUniversity of Lincoln
Log in to write your comment here...