Item Response Theory and Differential Item Functioning Analyses With the Suicidal Behaviors Questionnaire–Revised in US and Chinese Samples

Background: Despite the widespread use of the Suicidal Behaviors Questionnaire–Revised (SBQ-R) and advances in item response theory (IRT) modeling, item-level analysis with the SBQ-R has been minimal. Aims: This study extended IRT modeling strategies to examine the response parameters and potential differential item functioning (DIF) of the individual SBQ-R items in samples of US ( N = 320) and Chinese ( N = 298) undergraduate students. Method: Responses to the items were calibrated using the unidimensional graded response IRT model. Goodness-of-fit, item parameters, and DIF were evaluated. Results: The unidimensional graded response IRT model provided a good fit to the sample data. Results showed that the SBQ-R items had various item discrimination parameters and item severity parameters. Also, each SBQ-R item functioned similarly between the US and Chinese respondents. In particular, Item 1 (history of attempts) demonstrated high discrimination and severity of suicide-related thoughts and behaviors (STBs). Limitations: The use of cross-sectional data from convenience samples of undergraduate students could be considered a major limitation. Conclusion: The findings from the IRT analysis provided empirical support that each SBQ-R item taps into STBs and that scores for Item 1 can be used for screening purposes.

A New Multiprocess IRT Model With Ideal Points for Likert-Type Items

For surveys of complex issues that entail multiple steps, multiple reference points, and nongradient attributes (e.g., social inequality), this study proposes a new multiprocess model that integrates ideal-point and dominance approaches into a treelike structure (IDtree). In the IDtree, an ideal-point approach describes an individual’s attitude and then a dominance approach describes their tendency for using extreme response categories. Evaluation of IDtree performance via two empirical data sets showed that the IDtree fit these data better than other models. Furthermore, simulation studies showed a satisfactory parameter recovery of the IDtree. Thus, the IDtree model sheds light on the response processes of a multistage structure.

manuscript

Forced choice (FC) is one of the most used forms measurement for non-cognitive assessments, which can effectively resist faking and some other response biases compared to the Likert-types scales, and has been a popular topic in the field of industrial organizational psychology in recent years. Inspired by Lee et al., (2019) study, the present study proposed a 2PL-RANK model as a variant of the GGUM-RANK for fitting dominance RANK items. To improve the efficiency of parameter estimation, the authors apply the stEM algorithm to the 2PL-RANK model, which greatly improves the efficiency of parameter estimation in joint estimation. What’s more, we derived information functions for this model based on the logic of Joo et al., (2018). Then, simulation studies were conducted to examined the recovery of model's parameters with RANK triplet responses, which manipulated four factors, with sample size, the number of dimensions, the number of blocks measured in each dimension, and the correlation between dimensions. Results show that the 2PL-RANK model performed well in estimating item and trait parameters. Finally, the utility of 2PL-RANK and Thurstonian IRT model (TIRT) in a 24-dimensional FC personality test was compared. An empirical study was then conducted based on a 24-dimensional FC personality test to illustrate the practical use of the model.

Validation of the EQ-5D in Taiwan using item response theory

Background Our study aims to provide validity evidence for the EuroQol five dimensions questionnaire (EQ-5D) in the National Health Interview Survey of Taiwan in the 2013 wave and further interpret the EQ-5D scores for patients with chronic diseases. Another goal of the study was to use item response theory (IRT) to identify items that are informative for assessing quality of life using EQ-5D. Methods There were 17,260 participants, aged 12-64, who completed the interviews in our study. Psychometric methods, including factor analysis and the IRT model known as the Graded Response Model (GRM), were used to assess the unidimensionality of EQ-5D and its item properties. Correlation analysis was used to assess whether EQ-5D scores are associated with scores from the 36-Item Short Form Survey (SF-36). Results The EQ-5D scores have moderate internal consistency (Cronbach’s alpha: 0.60) and a scree plot suggests that the EQ-5D measure is unidimensional. The item information function analysis from the IRT model demonstrates that the first 3 items, “mobility,” “self-care,” and “usual activities” are the most informative items for patients who have chronic diseases and health-related quality of life below the 10th percentile. The EQ-5D scores have a moderate correlation (r: 0.61) with SF-36 scores. Conclusions The EQ-5D scale shows promise for use in the general population. The IRT model informs our interpretation of the EQ-5D scores. Given the time constraints in clinical settings, we suggest using the first three items in EQ-5D to measure the health-related quality of life for patients with chronic diseases.

Finding DORI: Using Item Response Theory to Measure Difficulty of Registration in the U.S. and Its Impact on Voters

How do states differ in how difficult they make voter registration, and what effect does this have on voters? We propose and validate a new Difficulty of Registration Index (DORI) calculated via an item response theory (IRT) model of five key dimensions of registration (automaticity, portability, deadline, mode, and preregistration) for each state from 2004 to 2020. Since 2004, most states eased registration processes, with Democratic statehouses in racially diverse and young states leading the way. Using CCES data, we find that DORI is associated with increased probability that voters experience problems registering and failing to turnout (in both self-reported and validated turnout data). These effects are pronounced for young voters. This study holds lessons for how restrictive registration procedures can change the shape of the electorate and make it harder to achieve political equality.

Questions to the Article: Exploring the Shift in International Trends in Mobile Health Research From 2000 to 2020 (Preprint)

UNSTRUCTURED The article published on September 9, 2021, is well-written and of interest, but remains two questions that are required for clarifications, such as the ways (1) to construct the growth curve and (2) to determine the flashpoint(or, say, inflection point, IP) on the growth curve shown in Figure 3. The authors addressed that the year 2015 was a flashpoint on the curve(ie. y = 37e0.3062x, with R2=0.9935) and determined the flash point by the naked eye. Although numerous bibliometric analyses applied the cumulative publications to release information about the growth curve and the IP using a particular formula, none of such research proposed an appropriate way to determine the IP. Accordingly, we are motivated to propose an item response theory (IRT) model(IRT) to determine the IP on a given ogive curve and found that the IP is in 2017 instead of 2015 with R2=0.9797 rather than 0.9935 in the questionable article. Similarly, the real model coefficient and R2 are 0.2942 and 0.9954, respectively, if the growth curve is modeled by the formula(= 37ebx ) in Microsoft Excel using the Solver add-in tool demonstrated in this article. The ITR model used to determine the IP location on cumulative time-series data is recommended to future relevant studies, not merely limited to the bibliometric analysis.

Assessing Dimensionality of the Ideal Point Item Response Theory Model Using Posterior Predictive Model Checking

Although the use of ideal point item response theory (IRT) models for organizational research has increased over the last decade, the assessment of construct dimensionality of ideal point scales has been overlooked in previous research. In this study, we developed and evaluated dimensionality assessment methods for an ideal point IRT model under the Bayesian framework. We applied the posterior predictive model checking (PPMC) approach to the most widely used ideal point IRT model, the generalized graded unfolding model (GGUM). We conducted a Monte Carlo simulation to compare the performance of item pair discrepancy statistics and to evaluate the Type I error and power rates of the methods. The simulation results indicated that the Bayesian dimensionality detection method controlled Type I errors reasonably well across the conditions. In addition, the proposed method showed better performance than existing methods, yielding acceptable power when 20% of the items were generated from the secondary dimension. Organizational implications and limitations of the study are further discussed.

A Lognormal Ipsative Model for Multidimensional Compositional Items

Compositional items – a form of forced-choice items – require respondents to allocate a fixed total number of points to a set of statements. To describe the responses to these items, the Thurstonian item response theory (IRT) model was developed. Despite its prominence, the model requires that items composed of parts of statements result in a factor loading matrix with full rank. Without this requirement, the model cannot be identified, and the latent trait estimates would be seriously biased. Besides, the estimation of the Thurstonian IRT model often results in convergence problems. To address these issues, this study developed a new version of the Thurstonian IRT model for analyzing compositional items – the lognormal ipsative model (LIM) – that would be sufficient for tests using items with all statements positively phrased and with equal factor loadings. We developed an online value test following Schwartz’s values theory using compositional items and collected response data from a sample size of N = 512 participants with ages from 13 to 51 years. The results showed that our LIM had an acceptable fit to the data, and that the reliabilities exceeded 0.85. A simulation study resulted in good parameter recovery, high convergence rate, and the sufficient precision of estimation in the various conditions of covariance matrices between traits, test lengths and sample sizes. Overall, our results indicate that the proposed model can overcome the problems of the Thurstonian IRT model when all statements are positively phrased and factor loadings are similar.