ITEM ANALYSIS FOR THE MODIFIED VERSION OF ADOLESCENT PARENTING ATTITUDE FOUR FACTOR QUESTIONNAIRE USING RASCH MEASUREMENT MODEL

This study aims to conduct a validity and reliability test on the modified version of adolescent parenting attitude four factor questionnaire (APA-FFQ) with rasch measurement model. The adapted instrument consisted of 40 items based on 4 constructs namely authoritarian, authoritative, permissive and uninvolved parenting style. Some modifications have been carried out to improve the item clarity and to capture the type of maternal and paternal parenting style. Based on the sample size of 70 adolescents from one of the private higher education institution in Malaysia, the analysis revealed that all items from the modified version of APA-FFQ fits the model as the value of infor and outfit mean square (MNSQ) fell within the acceptable range of 0.50 to 1.50 with positive Point Measure Correlation (PTMEA) value. The dimensionality analysis also revealed that all items involved were measured what it supposed to measure and possessed a strong unidimensionality. Furthermore, the separation and reliability analysis showed that all items and respondents are stable and consistent when tested with different items in measuring the same construct. Therefore, the instrument can be adapted in the Malaysian educational context.

Analyzing the Validity of the Adult-Adolescent Parenting Inventory for Low-Income Populations

Objectives: The purpose of this study was to examine the construct and predictive validity of the Adult-Adolescent Parenting Inventory (AAPI-2). Methods: The validity of the AAPI-2 was evaluated using multiple statistical methods, including exploratory factor analysis, confirmatory factor analysis, and latent class analysis. These analyses were conducted using data collected from a culturally diverse sample of 2,160 low-income parents. Results: Although the AAPI-2 yielded high reliability coefficients, analyses of the instrument’s validity diverged significantly from the results reported by the instrument’s developers. Specifically, the instruments’ reported five-factor structure was not supported in this study. Moreover, parents’ AAPI-2 scores were not associated with child abuse as originally hypothesized. However, when the AAPI-2 was analyzed as a categorical latent variable, the results were useful in identifying parents who were unlikely to abuse or neglect their children. Conclusion: Further replication and extension research on the AAPI-2 with other low-income populations is warranted.