Transformational and Transactional Leadership in the Polish Organizational Context: Validation of the Full and Short Forms of the Multifactor Leadership Questionnaire

Artificial Neural Networks for Short-Form Development of Psychometric Tests: A Study on Synthetic Populations Using Autoencoders

Short-form development is an important topic in psychometric research, which requires researchers to face methodological choices at different steps. The statistical techniques traditionally used for shortening tests, which belong to the so-called exploratory model, make assumptions not always verified in psychological data. This article proposes a machine learning-based autonomous procedure for short-form development that combines explanatory and predictive techniques in an integrative approach. The study investigates the item-selection performance of two autoencoders: a particular type of artificial neural network that is comparable to principal component analysis. The procedure is tested on artificial data simulated from a factor-based population and is compared with existent computational approaches to develop short forms. Autoencoders require mild assumptions on data characteristics and provide a method to predict long-form items' responses from the short form. Indeed, results show that they can help the researcher to develop a short form by automatically selecting a subset of items that better reconstruct the original item's responses and that preserve the internal structure of the long-form.

Measuring educational leadership in Singapore: re-examining the psychometric properties of the Multifactor Leadership Questionnaire

Introduction

The Multifactor Leadership Questionnaire (MLQ-5X) has been used frequently to assess leadership in different settings. Despite its popularity, there are many critiques of the MLQ-5X such as its questionable multidimensional structure, lack of connection to the theory and the different factor structures of the measurement tool. The purpose of this study was to re-examine the psychometric properties of the MLQ-5X in the Singapore educational context using two datasets.

Methods

A total of 872 teachers (40.1% male and 59.9% female) from 20 secondary schools in Singapore completed two sets of MLQ-5X, one set for their immediate reporting officer and one set for their school leaders.

Results

Congeneric Confirmatory Factor Analysis, Rho's coefficients, and AVE were used to analyze MLQ-5X's convergent validity and internal consistency. After five items were deleted, the MLQ-5X showed acceptable internal consistency and convergent validity. Eight measurement models were tested with the original 36 items and the reduced items MLQ-5X. Latent factor correlation matrix with confidence intervals was used to assess the discriminant validity of the MLQ-5X. The results provided support for a nine first-order factors and three second-order factors model (transformation [IIA, IIB, IM, IS, IC, CR], transactional (MBEA), and non-leadership (MBEP and LF).

Discussion

The discriminant validity of the hierarchical measurement model of MLQ-5X is supported using dataset 2.