Verifying management innovation practices constructs validity using Rasch measurement model: An investigation in Northern Malaysia manufacturing companies

Abstract

The study on management innovation (MI) practices by manufacturing firm towards sustainable performance has received significant attention over the past decades. Generally, firms have implemented many practices and enjoyed their capabilities of innovative practices of their future investments towards sustaining strong firm performance. Hence, most of MI practices have been implemented beyond expectation for manufacturing firms and it is totally contradicted with local firms’ expectation for those practices. The aim of this study is to verify the construct for a new integrated of MI practices items which consisted of 110 items. A pilot study was conducted using Rasch Measurement Model in which WINSTEPS software was used to analyse the responses from 30 manufacturing firms. This use of model is to measure the construct validity, unidimensionality analysis, and reliability of the questionnaire. The respondents of this study consisted of top echelon of the manufacturing firms. The summary statistic from the pilot study indicated that item reliability and item separation was 0.63 and 1.29 respectively, while for person reliability and person separation was 0.95 and 4.51 respectively. However, the result for model unidimensionality show that there is a need to improve the unidimensionality of the instruments. Therefore, the possibility of multicollinearity problem need to re-examined and MI practices need to be reviewed and call for further improvement. The final result 88 items are suitable to use for measurement of the real study in future work.