Search

Social desirability bias (SDB) is a common threat to the validity of conclusions from responses to a scale or survey. There is a wide range of person-fit statistics in the literature that can be employed to detect SDB. In addition, machine learning classifiers, such as logistic regression and random forest, have the potential to distinguish between biased and unbiased responses. This study proposes a new application of these classifiers to detect SDB by considering several person-fit indices as features or predictors in the machine learning methods. The results of a Monte Carlo simulation study showed that for a single feature, applying person-fit indices directly and logistic regression led to similar classification results. However, the random forest classifier improved the classification of biased and unbiased responses substantially. Classification was improved in both logistic regression and random forest by considering multiple features simultaneously. Moreover, cross-validation indicated stable area under the curves (AUCs) across machine learning classifiers. A didactical illustration of applying random forest to detect SDB is presented. [ABSTRACT FROM AUTHOR]

Introduction: This study investigates the confounding effects of reverse-coded items on the measurement of confidence in mathematics using data from the 2019 Trends in International Mathematics and Science Study (TIMSS). Methods: The sample came from the Saudi Arabian cohort of 8th graders in 2019 involving 4,515 students. Through mixture modeling, two subgroups responding in similar ways to reverse-coded items were identified representing approximately 9% of the sample. Results: Their response to positively valenced and negatively valenced items showed inconsistency and the observed unexpected response patterns were further verified using Lz*, U3, and the number of Guttman errors person fit indicators. Psychometric analyses on the full sample and the truncated sample after deleting the aberrant responders indicated significant improvements in both internal consistency reliability and factorial validity. Discussion: It was concluded that reverse-coded items contribute to systematic measurement error that is associated with distorted item level parameters that compromised the scale's reliability and validity. The study underscores the need for reconsideration of reverse-coded items in survey design, particularly in contexts involving younger populations and low-achieving students. [ABSTRACT FROM AUTHOR]

IntroductionThis study investigates the confounding effects of reverse-coded items on the measurement of confidence in mathematics using data from the 2019 Trends in International Mathematics and Science Study (TIMSS).MethodsThe sample came from the Saudi Arabian cohort of 8th graders in 2019 involving 4,515 students. Through mixture modeling, two subgroups responding in similar ways to reverse-coded items were identified representing approximately 9% of the sample.ResultsTheir response to positively valenced and negatively valenced items showed inconsistency and the observed unexpected response patterns were further verified using Lz*, U3, and the number of Guttman errors person fit indicators. Psychometric analyses on the full sample and the truncated sample after deleting the aberrant responders indicated significant improvements in both internal consistency reliability and factorial validity.DiscussionIt was concluded that reverse-coded items contribute to systematic measurement error that is associated with distorted item level parameters that compromised the scale’s reliability and validity. The study underscores the need for reconsideration of reverse-coded items in survey design, particularly in contexts involving younger populations and low-achieving students.