Identifying Critical Factors That Predict Quality Management Program Success: Data Mining Analysis of Baldrige Award Data

Abstract

This study identifies the critical factors that predict quality management program success using the Malcolm Baldrige National Quality Award (MBNQA) Criteria for Performance Excellence framework as a measurement proxy. Success is measured based on MBNQA applicant scores that qualify for award recipient consideration. Use of the MBNQA system as a proxy for success is supported by prior research. This study performs longitudinal and cross-sectional data mining analyses using ANOVA, multiple regression analysis, discriminant analysis, and decision tree analysis to compare 1,098 independent review process cases and 486 consensus review process cases drawn from the MBNQA item-level applicant scoring data from 1991 to 2006. The data are drawn from the MBNQA item-level blinded applicant scoring data released in 2011 by the National Institute of Standards and Technology (NIST). The analyses use an MBNQA “award” threshold score of 608 points that is stable for the 1991 through 2006 reporting period. This score is the approximate lowest winning score of the 66 award recipients for the reporting period, and is a function of the component scores that are being modeled. This study contributes to the quality management literature by empirically identifying the factors that matter the most when predicting quality management program success as measured by qualifying for an MBNQA award. The author found that MBNQA Category 4 (Measurement, Analysis, and Knowledge Management) and Category 1 (Leadership) MBNQA criteria (factors) are the only contributing factors—none of the other MBNQA factors matter. This finding suggests that quality management practitioners should consider focusing on leadership development and informatics-related interventions as a strategy for improving organizational performance and achieving MBNQA award status as measured by MBNQA criteria and financial outcomes.