Estimating reliability coefficients with heterogeneous item weightings using Stata: A factor based approach

General

Martijn Boermans (Lid Lectoraat) ; Mark Kattenberg

Hogeschool Utrecht

学科分类：社会科学、人文和艺术（综合）

荷兰|英语

来源: HBO Kennisbank

【 摘 要 】

We show how to estimate a Cronbach's alpha reliability coefficientin Stata after running a principal component or factor analysis. Alpha evaluatesto what extent items measure the same underlying content when the items arecombined into a scale or used for latent variable. Stata allows for testing thereliability coefficient (alpha) of a scale only when all items receive homogenousweights. We present a user-written program that computes reliability coefficientswhen implementation of principal component or factor analysis shows heterogeneousitem loadings. We use data on management practices from Bloom and VanReenen (2010) to explain how to implement and interpret the adjusted internalconsistency measure using afa.