Use of Restricted Item Response Theory Models for Examining the Stability of Item Parameter Estimates Over Time

Item parameter instability can threaten the validity of inferences about changes in student achievement when using Item Response Theory- (IRT) based test scores obtained on different occasions. This article illustrates a model-testing approach for evaluating the stability of IRT item parameter estimates in a pretest-posttest design. Stability of item parameter estimates was assessed for a random sample of pretest and posttest responses to a 19-item math test. Using MULTILOG (Thissen, 1986), IRT models were estimated in which item parameter estimates were constrained to be equal across samples (reflecting stability) and item parameter estimates were free to vary across samples (reflecting instability). These competing models were then compared statistically in order to test the invariance assumption. The results indicated a moderately high degree of stability in the item parameter estimates for a group of children assessed on two different occasions.     

Comparing the Difficulty of Examination Subjects with Item Response Theory

Methods are presented for comparing grades obtained in a situation where students can choose between different subjects. It must be expected that the comparison between the grades is complicated by the interaction between the students' pattern and level of proficiency on one hand, and the choice of the subjects on the other hand. Three methods based on item response theory (IRT) for the estimation of proficiency measures that are comparable over students and subjects are discussed: a method based on a model with a unidimensional representation of proficiency, a method based on a model with a multidimensional representation of proficiency, and a method based on a multidimensional representation of proficiency where the stochastic nature of the choice of examination subjects is explicitly modeled. The methods are compared using the data from the Central Examinations in Secondary Education in the Netherlands. The results show that the unidimensional IRT model produces unrealistic results, which do not appear when using the two multidimensional IRT models. Further, it is shown that both the multidimensional models produce acceptable model fit. However, the model that explicitly takes the choice process into account produces the best model fit.     

Item Response Models for Examinee‐Selected Items

In some tests, examinees are required to choose a fixed number of items from a set of given items to answer. This practice creates a challenge to standard item response models, because more capable examinees may have an advantage by making wiser choices. In this study, we developed a new class of item response models to account for the choice effect of examinee‐selected items. The results of a series of simulation studies showed: (1) that the parameters of the new models were recovered well, (2) the parameter estimates were almost unbiased when the new models were fit to data that were simulated from standard item response models, (3) failing to consider the choice effect yielded shrunken parameter estimates for examinee‐selected items, and (4) even when the missingness mechanism in examinee‐selected items did not follow the item response functions specified in the new models, the new models still yielded a better fit than did standard item response models. An empirical example of a college entrance examination supported the use of the new models: in general, the higher the examinee's ability, the better his or her choice of items.     

Item Response Theory Models for Performance Decline During Testing

Sometimes, test‐takers may not be able to attempt all items to the best of their ability (with full effort) due to personal factors (e.g., low motivation) or testing conditions (e.g., time limit), resulting in poor performances on certain items, especially those located toward the end of a test. Standard item response theory (IRT) models fail to consider such testing behaviors. In this study, a new class of mixture IRT models was developed to account for such testing behavior in dichotomous and polytomous items, by assuming test‐takers were composed of multiple latent classes and by adding a decrement parameter to each latent class to describe performance decline. Parameter recovery, effect of model misspecification, and robustness of the linearity assumption in performance decline were evaluated using simulations. It was found that the parameters in the new models were recovered fairly well by using the freeware WinBUGS; the failure to account for such behavior by fitting standard IRT models resulted in overestimation of difficulty parameters on items located toward the end of the test and overestimation of test reliability; and the linearity assumption in performance decline was rather robust. An empirical example is provided to illustrate the applications and the implications of the new class of models.     

Item Response Models for Multiple Attempts With Incomplete Data

Allowance for multiple chances to answer constructed response questions is a prevalent feature in computer‐based homework and exams. We consider the use of item response theory in the estimation of item characteristics and student ability when multiple attempts are allowed but no explicit penalty is deducted for extra tries. This is common practice in online formative assessments, where the number of attempts is often unlimited. In these environments, some students may not always answer‐until‐correct, but may rather terminate a response process after one or more incorrect tries. We contrast the cases of graded and sequential item response models, both unidimensional models which do not explicitly account for factors other than ability. These approaches differ not only in terms of log‐odds assumptions but, importantly, in terms of handling incomplete data. We explore the consequences of model misspecification through a simulation study and with four online homework data sets. Our results suggest that model selection is insensitive for complete data, but quite sensitive to whether missing responses are regarded as informative (of inability) or not (e.g., missing at random). Under realistic conditions, a sequential model with similar parametric degrees of freedom to a graded model can account for more response patterns and outperforms the latter in terms of model fit.     

Item Response Models for Local Dependence Among Multiple Ratings

Ratings given to the same item response may have a stronger correlation than those given to different item responses, especially when raters interact with one another before giving ratings. The rater bundle model was developed to account for such local dependence by forming multiple ratings given to an item response as a bundle and assigning fixed‐effect parameters to describe response patterns in the bundle. Unfortunately, this model becomes difficult to manage when a polytomous item is graded by more than two raters. In this study, by adding random‐effect parameters to the facets model, we propose a class of generalized rater models to account for the local dependence among multiple ratings and intrarater variation in severity. A series of simulations was conducted with the freeware WinBUGS to evaluate parameter recovery of the new models and consequences of ignoring the local dependence or intrarater variation in severity. The results revealed a good parameter recovery when the data‐generating models were fit, and a poor estimation of parameters and test reliability when the local dependence or intrarater variation in severity was ignored. An empirical example is provided.     

The Consequences of Ignoring Item Parameter Drift in Longitudinal Item Response Models

Utilizing a longitudinal item response model, this study investigated the effect of item parameter drift (IPD) on item parameters and person scores via a Monte Carlo study. Item parameter recovery was investigated for various IPD patterns in terms of bias and root mean-square error (RMSE), and percentage of time the 95% confidence interval covered the true parameter. The simulation results suggest that item parameters were not recovered well when IPD was ignored, especially if there was a larger number of IPD conditions. In addition, coverage was not accurate in all IPD conditions when IPD is ignored. Also, the results suggest that the accuracy of person scores (measured by bias) is potentially problematic when the larger number of IPD items is ignored. However, the overall accuracy (measured by RMSE) and coverage were unexpectedly acceptable in the presence of IPD as defined in this study.     

项目反应理论复杂模型发展与参数估计

项目反应数据的建模过程属于项目反应理论范畴,被称为现代测量理论。随着社会测量要求的广度和复杂度的增加,以及测量功能的不断扩展的要求,需要越来越复杂的项目反应模型来完成心理学、教育学、社会学等领域的测量任务。本文就当前较普遍以及发展迅速的项目反应复杂模型,如高阶、多维、多层模型进行论述,并且描述了复杂模型的参数评估技术,结合复杂模型的应用情况,期望本土的测量技术向客观化、尖端化发展。     

Subjective Priors for Item Response Models: Application of Elicitation by Design

Bayesian methods incorporate model parameter information prior to data collection. Eliciting information from content experts is an option, but has seen little implementation in Bayesian item response theory (IRT) modeling. This study aims to use ethical reasoning content experts to elicit prior information and incorporate this information into Markov Chain Monte Carlo (MCMC) estimation. A six‐step elicitation approach is followed, with relevant details at each stage for two IRT items parameters: difficulty and guessing. Results indicate that using content experts is the preferred approach, rather than noninformative priors, for both parameter types. The use of a noninformative prior for small samples provided dramatically different results when compared to results from content expert–elicited priors. The WAMBS (When to worry and how to Avoid the Misuse of Bayesian Statistics) checklist is used to aid in comparisons.     

Item Position and Item Difficulty Change in an IRT-Based Common Item Equating Design

In operational testing programs using item response theory (IRT), item parameter invariance is threatened when an item appears in a different location on the live test than it did when it was field tested. This study utilizes data from a large state's assessments to model change in Rasch item difficulty (RID) as a function of item position change, test level, test content, and item format. As a follow-up to the real data analysis, a simulation study was performed to assess the effect of item position change on equating. Results from this study indicate that item position change significantly affects change in RID. In addition, although the test construction procedures used in the investigated state seem to somewhat mitigate the impact of item position change, equating results might be impacted in testing programs where other test construction practices or equating methods are utilized.     

Comparing the Fit of Item Response Theory and Factor Analysis Models

Linear factor analysis (FA) models can be reliably tested using test statistics based on residual covariances. We show that the same statistics can be used to reliably test the fit of item response theory (IRT) models for ordinal data (under some conditions). Hence, the fit of an FA model and of an IRT model to the same data set can now be compared. When applied to a binary data set, our experience suggests that IRT and FA models yield similar fits. However, when the data are polytomous ordinal, IRT models yield a better fit because they involve a higher number of parameters. But when fit is assessed using the root mean square error of approximation (RMSEA), similar fits are obtained again. We explain why. These test statistics have little power to distinguish between FA and IRT models; they are unable to detect that linear FA is misspecified when applied to ordinal data generated under an IRT model.     

Item Difficulty of Four Verbal Item Types and an Index of Differential Item Functioning for Black and White Examinees

In this study, the authors explored the importance of item difficulty (equated delta) as a predictor of differential item functioning (DIF) of Black versus matched White examinees for four verbal item types (analogies, antonyms, sentence completions, reading comprehension) using 13 GRE-disclosed forms (988 verbal items) and 11 SAT-disclosed forms (935 verbal items). The average correlation across test forms for each item type (and often the correlation for each individual test form as well) revealed a significant relationship between item difficulty and DIF value for both GRE and SAT. The most important finding indicates that for hard items, Black examinees perform differentially better than matched ability White examinees for each of the four item types and for both the GRE and SAT tests! The results further suggest that the amount of verbal context is an important determinant of the magnitude of the relationship between item difficulty and differential performance of Black versus matched White examinees. Several hypotheses accounting for this result were explored.     

An NCME Instructional Module on Polytomous Item Response Theory Models

A polytomous item is one for which the responses are scored according to three or more categories. Given the increasing use of polytomous items in assessment practices, item response theory (IRT) models specialized for polytomous items are becoming increasingly common. The purpose of this ITEMS module is to provide an accessible overview of polytomous IRT models. The module presents commonly encountered polytomous IRT models, describes their properties, and contrasts their defining principles and assumptions. After completing this module, the reader should have a sound understating of what a polytomous IRT model is, the manner in which the equations of the models are generated from the model's underlying step functions, how widely used polytomous IRT models differ with respect to their definitional properties, and how to interpret the parameters of polytomous IRT models.     

An Assessment of the Nonparametric Approach for Evaluating the Fit of Item Response Models

As item response theory has been more widely applied, investigating the fit of a parametric model becomes an important part of the measurement process. There is a lack of promising solutions to the detection of model misfit in IRT. Douglas and Cohen introduced a general nonparametric approach, RISE (Root Integrated Squared Error), for detecting model misfit. The purposes of this study were to extend the use of RISE to more general and comprehensive applications by manipulating a variety of factors (e.g., test length, sample size, IRT models, ability distribution). The results from the simulation study demonstrated that RISE outperformed G² and S‐X² in that it controlled Type I error rates and provided adequate power under the studied conditions. In the empirical study, RISE detected reasonable numbers of misfitting items compared to G² and S‐X², and RISE gave a much clearer picture of the location and magnitude of misfit for each misfitting item. In addition, there was no practical consequence to classification before and after replacement of misfitting items detected by three fit statistics.     

Assessing the Utility of Item Response Models: Computerized Adaptive Testing

How has Item Response Theory helped solve problems in the development and use of computer-adaptive tests? Do we need to balance item content with computer-adaptive tests? Could we use IRT to evaluate unusual responses to computer-delivered tests?     

Assessing Fit of Item Response Models Using the Information Matrix Test

The information matrix can equivalently be determined via the expectation of the Hessian matrix or the expectation of the outer product of the score vector. The identity of these two matrices, however, is only valid in case of a correctly specified model. Therefore, differences between the two versions of the observed information matrix indicate model misfit. The equality of both matrices can be tested with the so‐called information matrix test as a general test of misspecification. This test can be adapted to item response models in order to evaluate the fit of single items and the fit of the whole scale. The performance of different versions of the test is compared in a simulation study with existing tests of model fit, among them the test of Orlando and Thissen, the score test of local independence due to Glas and Suarez‐Falcon, and the limited information approach of Maydeu‐Olivares and Joe. In general, the different versions of the information matrix test adhere to the nominal Type I error rate and have high power for detecting misspecified item characteristic curves. Additionally, some versions of the test can be used in order to detect violations of the local independence assumption.     

Detecting Differential Item Discrimination (DID) and the Consequences of Ignoring DID in Multilevel Item Response Models

Cross‐level invariance in a multilevel item response model can be investigated by testing whether the within‐level item discriminations are equal to the between‐level item discriminations. Testing the cross‐level invariance assumption is important to understand constructs in multilevel data. However, in most multilevel item response model applications, the cross‐level invariance is assumed without testing of the cross‐level invariance assumption. In this study, the detection methods of differential item discrimination (DID) over levels and the consequences of ignoring DID are illustrated and discussed with the use of multilevel item response models. Simulation results showed that the likelihood ratio test (LRT) performed well in detecting global DID at the test level when some portion of the items exhibited DID. At the item level, the Akaike information criterion (AIC), the sample‐size adjusted Bayesian information criterion (saBIC), LRT, and Wald test showed a satisfactory rejection rate (>.8) when some portion of the items exhibited DID and the items had lower intraclass correlations (or higher DID magnitudes). When DID was ignored, the accuracy of the item discrimination estimates and standard errors was mainly problematic. Implications of the findings and limitations are discussed.     

试题难度的主观预估方法

试题难度一般通过实际测试考生而获得,但这种预试方法的实施具有一定局限性。难度的主观预估方法无需依赖考生,主要由学科专家根据经验对试题难度进行预测,因此在中、高考等考试实践中受到广泛应用。在研究和实践中,研究者们不断完善主观预估法,并提出不同的估计方法。本文对传统的主观评判法与配对比较的难度估计法进行介绍,以期更系统地认识难度的主观预估方法,促进主观预估法在考试实践中的应用。