Construct validity and internal consistency of the Home and Family Work Roles Questionnaires: a cross-sectional study with exploratory factor analysis

Abstract

Introduction Exploratory Factor Analysis (EFA) measures the underlying relationships between questionnaire items and the factors (“constructs”) measured by a questionnaire. The Home and Family Work Roles Questionnaire has not been assessed using EFA; therefore, our objective was to identify the factors measured by this questionnaire. Methods We recruited 314 persons to complete the questionnaire and to answer several demographic questions. We determined if the data was factorable by performing Bartlett’s test of sphericity and the Kaiser–Meyer–Olkin measure of sampling adequacy. We used the Factor package in Jamovi statistical software to perform EFA. We employed an Oblimin rotation and a Principal Axis extraction method. We also calculated the internal consistency of the questionnaire as a whole as well as each individual question. Results Our sample consisted of 265 (85%) women, 45 (14%) men, and 3 (1%) non-binary or other genders. The mean age of our participants was 34.65 (SD = 11.57, range = 18–65) years. EFA suggested a three-factor model. Questions 11, 13, 14, 15, and 16 measured one factor (we interpreted this as “Caregiving Roles”), questions 1, 3, 4, 8, 9, 10, 18, and 19 measured a different factor (“Traditionally Feminine Roles”), and questions 2, 5, 6, and 12 measured the “Traditionally Masculine Roles”. The questionnaire and each individual question demonstrated excellent internal consistency (Cronbach's α > 0.90). Conclusion The Home and Family Work Roles Questionnaire may measure three distinct factors, which we have named Caregiving, Traditionally Feminine, and Traditionally Masculine Roles. This aligns with the theory used in developing the questionnaire. Separation of the Home and Family Work Roles Questionnaire into three sub-scales with distinct scores is recommended to measure each of the recommended constructs.

Coopetition, exploration and exploitation capabilities, and growth performance in digital healthcare ventures

“…The EFA extracted five factors with eigenvalues exceeding 1.0, explaining 68.029% of the variance in the data: coopetition (18.425%), exploration capability (16.802%), exploitation capability (11.470%), growth performance (11.181%), and environmental uncertainty (10.151%). The Kaiser-Mayer-Olkin (KMO) test yielded a value of 0.885, above the threshold of 0.8, and Bartlett’s test of sphericity achieved a chi-square of 3011.506 with 171 degrees of freedom, p < 0.01, indicating suitability for factor analysis ( 94 ). Table 1 presents a prerequisite analysis for descriptive statistics and confirmatory factor analysis.…”

Threat or prospect? Exploring the impact of digital entrepreneurs’ artificial intelligence perception and intention to adopt blockchain technology on the achievement of SDGs

“…Additionally, a measurement model's discriminant validity requires a threshold of 0.9 according to the HTMT criteria [ 62 ]; Table 5 illustrates that each construct successfully meets this criterion with nonbolded value. To further validate discriminant validity, item cross-loading is employed, revealing also in Table 5 with bolded value that all items are strongly loaded within their respective constructs but weakly loaded on other constructs [ 63 , 64 ].…”

Development and psychometric testing of a questionnaire for the Korea Youth risk behavior survey to assess physical activity behaviors

“…First, exploratory factor analysis was not conducted because a single item was developed per theme. This analysis would have allowed researchers to assess the internal consistency among the components within a factor [ 43 ]. Second, because it is a self-report questionnaire, it is prone to reporting errors and social desirability bias [ 44 ].…”