A Machine-learning Approach to Predicting Perceived Organizational Performance in the Federal Public Health Workforce

• In Event: OTP- Organizational Performance and the Digital Divide (v)

Short Description

This study aims to identify subgroups at high risks for low-level perceived organizational performance, and suggest tailored interventions on at-risk subgroups in federal public health agencies, using a nationally representative sample of the federal public health employees (weighted N=75,706) from 2018 Federal Employee Viewpoint Survey. Classification tree modeling was used to identify predictors of perceived organizational performance and stratify subgroups of the federal public health employees based on perceived organizational performance after accounting for sampling weights.

Authors

• Presenter: In Gu Kang, Boise State University

• Presenter: Barbara A. Bichelmeyer, University of Kansas

• Contributor: Nayoung Kim, University of Wisconsin-Madison