VALIDITY OF APPROXIMATION TECHNIQUES FOR DETECTING ITEM BIAS

The purpose of this research was to recommend an item bias procedure when the number of minority examinees is too small to use preferred three-parameter IRT methods. The chi-square, Angoff delta-plot, andpseudo-IRT indices were compared with both real and simulated data. For the real test data a criterion of known bias had been established by cross-validated IRT-3 results. The findings from the Math Test and the simulated test were consistent. The pseudo-IRT approach was best (measured by both correlations and percent agreement) in delecting criterion bias. The chi-square was close in accuracy to the pseudo-IRT index. The Angoff delta-plot method was found to be inadequate on both heuristic and empirical grounds. In extreme cases it even identified items as biased against whites that were simulated to be biased against blacks. However, a modified Angoff index, where p-value differences were regressed on item point biserials (and the residualized values used as the index), was nearly as good as the chi-square in identifying known bias. A final caution was offered regarding the use of item bias techniques. The statistical flags should never be used mechanically to discard items; rather they should be used to inspect items for possible differences in meaning.     

Comparisons among Designs for Equating Mixed-Format Tests in Large-Scale Assessments

In this study we examined variations of the nonequivalent groups equating design for tests containing both multiple-choice (MC) and constructed-response (CR) items to determine which design was most effective in producing equivalent scores across the two tests to be equated. Using data from a large-scale exam, this study investigated the use of anchor CR item rescoring (known as trend scoring) in the context of classical equating methods. Four linking designs were examined: an anchor with only MC items, a mixed-format anchor test containing both MC and CR items; a mixed-format anchor test incorporating common CR item rescoring; and an equivalent groups (EG) design with CR item rescoring, thereby avoiding the need for an anchor test. Designs using either MC items alone or a mixed anchor without CR item rescoring resulted in much larger bias than the other two designs. The EG design with trend scoring resulted in the smallest bias, leading to the smallest root mean squared error value.     

A Synthesis of the Peer‐Reviewed Differential Bundle Functioning Research

The purpose of this article was to present a synthesis of the peer‐reviewed differential bundle functioning (DBF) research that has been conducted to date. A total of 16 studies were synthesized according to the following characteristics: tests used and learner groups, organizing principles used for developing bundles, DBF detection methods used, and types of bundles that indicated statistically significant DBF in the hypothesized direction on multiple occasions. The article concludes with a list of suggestions to individuals who conduct DBF research. For example, effect size guidelines should be established for interpreting the amount of DBF in bundles of items assessed with simultaneous item bias test (SIBTEST), given that it is the most commonly used DBF procedure. This would reduce our reliance on statistical significance testing. General effect size guidelines are needed as well as guidelines for special circumstances like small sample cases. Other useful suggestions are offered as well.     

Item Function Characteristics and Dimensionality for Alternative Response Formats in Mathematics

The purpose of this study was to investigate the technical properties of stem-equivalent mathematics items differing only with respect to response format. Using socio- economic factors to define the strata, a proportional stratified random sample of 1,366 Connecticut sixth-grade students were administered one of three forms. Classical item analysis, dimensionality assessment, item response theory goodness-of-fit, and an item bias analysis were conducted. Analysis of variance and confirmatory factor analysis were used to examine the functioning of the items presented in the three different formats. It was found that, after equating forms, the constructed-response formats were somewhat more difficult than the multiple-choice format. However, there was no significant difference across formats with respect to item discrimination. A differential item functioning (DIF) analysis was conducted using both the Mantel-Haenszel procedure and the comparison of the item characteristic curves. The DIF analysis indicated that the presence of bias was not greatly affected by item format; that is, items biased in one format tended to be biased in a similar manner when presented in a different format, and unbiased items tended to remain so regardless of format.     

EMPIRICAL COMPARISON OF SELECTED ITEM BIAS DETECTION PROCEDURES WITH BIAS MANIPULATION

Biased test items were intentionally imbedded within a set of test items, and the resulting instrument was administered to large samples of blacks and whites. Three popular item bias detection procedures were then applied to the data: (1) the three-parameter item characteristic curve procedure, (2) the chi-square method, and (3) the transformed item difficulty approach. The three-parameter item characteristic curve procedure proved most effective at detecting the intentionally biased test items; and the chi-square method was viewed as the best alternative. The transformed item difficulty approach has certain limitations yet represents a practical alternative if sample size, lack of computer facilities, or the like preclude the use of the other two procedures.     

Detecting Calculator Effects on Item Performance

Calculator effects were examined using methods taken from research on differential item functioning. Use of a calculator was controlled on two experimental forms of a test assembled from operational items used on a standardized university mathematics placement test. Results indicated that calculator effects were not present based on analysis of test scores and in only two of the three subscores composed from homogeneous item types. Analyses of item-level functioning indicated, however, that a number of items, including several not included in the two significant subscore combinations, also contained calculator effects. For those items identified, use of the calculator appeared to have changed the actual objective being tested. The findings were generally consistent with previous research: Items that were easier when a calculator was used required either simple computations or use of a function key on the calculator; items that were more difficult required knowledge of a procedure either with or without additional computation. Analysis at the item level facilitated clearer understanding of the impact of calculator use on measurement of the underlying objective.     

A Stepwise Test Characteristic Curve Method to Detect Item Parameter Drift

An important assumption of item response theory is item parameter invariance. Sometimes, however, item parameters are not invariant across different test administrations due to factors other than sampling error; this phenomenon is termed item parameter drift. Several methods have been developed to detect drifted items. However, most of the existing methods were designed to detect drifts in individual items, which may not be adequate for test characteristic curve–based linking or equating. One example is the item response theory–based true score equating, whose goal is to generate a conversion table to relate number‐correct scores on two forms based on their test characteristic curves. This article introduces a stepwise test characteristic curve method to detect item parameter drift iteratively based on test characteristic curves without needing to set any predetermined critical values. Comparisons are made between the proposed method and two existing methods under the three‐parameter logistic item response model through simulation and real data analysis. Results show that the proposed method produces a small difference in test characteristic curves between administrations, an accurate conversion table, and a good classification of drifted and nondrifted items and at the same time keeps a large amount of linking items.     

AN ITERATIVE ITEM BIAS DETECTION METHOD

Two strategies for assessing item bias are discussed: methods that compare (transformed) item difficulties unconditional on ability level and methods that compare the probabilities of correct response conditional on ability level. In the present study, the logit model was used to compare the probabilities of correct response to an item by members of two groups, these probabilities being conditional on the observed score. Here the observed score serves as an indicator of ability level. The logit model was iteratively applied: In the Tth iteration, the T items with the highest value of the bias statistic are excluded from the test, and the observed score indicator of ability for the (T + 1)th iteration is computed from the remaining items. This method was applied to simulated data. The results suggest that the iterative logit method is a substantial improvement on the noniterative one, and that the iterative method is very efficient in detecting biased and unbiased items.     

Multilevel Modeling of Item Position Effects

In many testing programs it is assumed that the context or position in which an item is administered does not have a differential effect on examinee responses to the item. Violations of this assumption may bias item response theory estimates of item and person parameters. This study examines the potentially biasing effects of item position. A hierarchical generalized linear model is formulated for estimating item‐position effects. The model is demonstrated using data from a pilot administration of the GRE wherein the same items appeared in different positions across the test form. Methods for detecting and assessing position effects are discussed, as are applications of the model in the contexts of test development and item analysis.     

Item Discrimination: When More Is Worse

High item discrimination can be a symptom o f a special kind of measurement disturbance introduced by an item that gives persons o f high ability a special advantage over and above their higher abilities. This type o f disturbance, which can be interpreted as a form o f item "bias," can be encouraged by methods that routinely interpret highly discriminating items as the "best" items on a test and may be compounded by procedures that weight items by their discrimination. The type of measurement disturbance described and illustrated in this paper occurs when an item is sensitive to individual differences on a second, undesired dimension that is positively correlated with the variable intended to be measured. Possible secondary influences o f this type include opportunity to learn, opportunity to answer, and test wiseness     

A Comparison of Limited-Information and Full-Information Methods in Mplus for Estimating Item Response Theory Parameters for Nonnormal Populations

In structural equation modeling software, either limited-information (bivariate proportions) or full-information item parameter estimation routines could be used for the 2-parameter item response theory (IRT) model. Limited-information methods assume the continuous variable underlying an item response is normally distributed. For skewed and platykurtic latent variable distributions, 3 methods were compared in Mplus: limited information, full information integrating over a normal distribution, and full information integrating over the known underlying distribution. Interfactor correlation estimates were similar for all 3 estimation methods. For the platykurtic distribution, estimation method made little difference for the item parameter estimates. When the latent variable was negatively skewed, for the most discriminating easy or difficult items, limited-information estimates of both parameters were considerably biased. Full-information estimates obtained by marginalizing over a normal distribution were somewhat biased. Full-information estimates obtained by integrating over the true latent distribution were essentially unbiased. For the a parameters, standard errors were larger for the limited-information estimates when the bias was positive but smaller when the bias was negative. For the d parameters, standard errors were larger for the limited-information estimates of the easiest, most discriminating items. Otherwise, they were generally similar for the limited- and full-information estimates. Sample size did not substantially impact the differences between the estimation methods; limited information did not gain an advantage for smaller samples.     

Routing Strategies and Optimizing Design for Multistage Testing in International Large‐Scale Assessments

This study investigates the effect of several design and administration choices on item exposure and person/item parameter recovery under a multistage test (MST) design. In a simulation study, we examine whether number‐correct (NC) or item response theory (IRT) methods are differentially effective at routing students to the correct next stage(s) and whether routing choices (optimal versus suboptimal routing) have an impact on achievement precision. Additionally, we examine the impact of testlet length on both person and item recovery. Overall, our results suggest that no single approach works best across the studied conditions. With respect to the mean person parameter recovery, IRT scoring (via either Fisher information or preliminary EAP estimates) outperformed classical NC methods, although differences in bias and root mean squared error were generally small. Item exposure rates were found to be more evenly distributed when suboptimal routing methods were used, and item recovery (both difficulty and discrimination) was most precisely observed for items with moderate difficulties. Based on the results of the simulation study, we draw conclusions and discuss implications for practice in the context of international large‐scale assessments that recently introduced adaptive assessment in the form of MST. Future research directions are also discussed.     

Formulation of the DETECT Population Parameter and Evaluation of DETECT Estimator Bias

The development of the DETECT procedure marked an important advancement in nonparametric dimensionality analysis. DETECT is the first nonparametric technique to estimate the number of dimensions in a data set, estimate an effect size for multidimensionality, and identify which dimension is predominantly measured by each item. The efficacy of DETECT critically depends on accurate, minimally biased estimation of the expected conditional covariances of all the item pairs. However, the amount of bias in the DETECT estimator has been studied only in a few simulated unidimensional data sets. This is because the value of the DETECT population parameter is known to be zero for this case and has been unknown for cases when multidimensionality is present. In this article, integral formulas for the DETECT population parameter are derived for the most commonly used parametric multidimensional item response theory model, the Reckase and McKinley model. These formulas are then used to evaluate the bias in DETECT by positing a multidimensional model, simulating data from the model using a very large sample size (to eliminate random error), calculating the large-sample DETECT statistic, and finally calculating the DETECT population parameter to compare with the large-sample statistic. A wide variety of two- and three-dimensional models, including both simple structure and approximate simple structure, were investigated. The results indicated that DETECT does exhibit statistical bias in the large-sample estimation of the item-pair conditional covariances; but, for the simulated tests that had 20 or more items, the bias was small enough to result in the large-sample DETECT almost always correctly partitioning the items and the DETECT effect size estimator exhibiting negligible bias.     

The PISA Tasks: Unveiling Prospective Elementary Mathematics Teachers’ Difficulties with Contextual,Conceptual, and Procedural Knowledge

The aim of this mixed methods study was to investigate the difficulties prospective elementary mathematics teachers have in solving the Programme for International Student Assessment (PISA) 2012 released items. A mathematics test consisting of 26 PISA items was administered, followed by interviews. Multiple data were utilized to provide rich insights into the types of mathematical knowledge that a particular item requires and prospective teachers’ difficulties in using these knowledge types. A sample of 52 prospective teachers worked the mathematics test, and 12 of them were interviewed afterwards. The data-sets were complementary: the quantitative data showed that PISA items could be categorized under contextual, conceptual, and procedural knowledge and indicated the most frequent difficulties in the combined contextual, conceptual, and procedural knowledge items. The qualitative data revealed that few prospective teachers could give mathematical explanations for conceptual knowledge items, and that their contextual knowledge was fragmented. Educational implications were discussed.     

Estimating Average Domain Scores

A simulation study was performed to determine whether a group's average percent correct in a content domain could be accurately estimated for groups taking a single test form and not the entire domain of items. Six Item Response Theory based domain score estimation methods were evaluated, under conditions of few items per content area perform taken, small domains, and small group sizes. The methods used item responses to a single form taken to estimate examinee or group ability; domain scores were then computed using the ability estimates and domain item characteristics. The IRT-based domain score estimates typically showed greater accuracy and greater consistency across forms taken than observed performance on the form taken. For the smallest group size and least number of items taken, the accuracy of most IRT-based estimates was questionable; however, a procedure that operates on an estimated distribution of group ability showed promise under most conditions.     

A Method for Maintaining Scale Stability in the Presence of Test Speededness

Administering tests under time constraints may result in poorly estimated item parameters, particularly for items at the end of the test (Douglas, Kim, Habing, & Gao, 1998; Oshima, 1994). Bolt, Cohen, and Wollack (2002) developed an item response theory mixture model to identify a latent group of examinees for whom a test is overly speeded, and found that item parameter estimates for end-of-test items in the nonspeeded group were similar to estimates for those same items when administered earlier in the test. In this study, we used the Bolt et al. (2002) method to study the effect of removing speeded examinees on the stability of a score scale over an II-year period. Results indicated that using only the nonspeeded examinees for equating and estimating item parameters provided a more unidimensional scale, smaller effects of item parameter drift (including fewer drifting items), and less scale drift (i.e., bias) and variability (i.e., root mean squared errors) when compared to the total group of examinees.     

Are Inferential Reading Items More Susceptible to Cultural Bias Than Literal Reading Items?

The purpose of this article is to illustrate a seven-step process for determining whether inferential reading items were more susceptible to cultural bias than literal reading items. The seven-step process was demonstrated using multiple-choice data from the reading portion of a reading/language arts test for fifth and seventh grade Hispanic, Black, and White examinees. The process began at the broadest level of analyzing bundles of items for differential bundle functioning and finished at the narrowest level of analyzing individual items for differential distractor functioning. Some evidence was found to indicate that inferential items are more susceptible to cultural bias than literal items. Implications of the results are discussed, and suggestions for item writers and test developers are given.     

A Didactic Explanation of Item Bias, Item Impact, and Item Validity From a Multidimensional Perspective

Many researchers have suggested that the main cause of item bias is the misspecification of the latent ability space, where items that measure multiple abilities are scored as though they are measuring a single ability. If two different groups of examinees have different underlying multidimensional ability distributions and the test items are capable of discriminating among levels of abilities on these multiple dimensions, then any unidimensional scoring scheme has the potential to produce item bias. It is the purpose of this article to provide the testing practitioner with insight about the difference between item bias and item impact and how they relate to item validity. These concepts will be explained from a multidimensional item response theory (MIRT) perspective. Two detection procedures, the Mantel-Haenszel (as modified by Holland and Thayer, 1988) and Shealy and Stout's Simultaneous Item Bias (SIB; 1991) strategies, will be used to illustrate how practitioners can detect item bias.     

The Effects of Dimensionality on Equating the Law School Admission Test

Using factor analysis, we conducted an assessment of multidimensionality for 6 forms of the Law School Admission Test (LSAT) and found 2 subgroups of items or factors for each of the 6 forms. The main conclusion of the factor analysis component of this study was that the LSAT appears to measure 2 different reasoning abilities: inductive and deductive. The technique of N. J. Dorans & N. M. Kingston (1985) was used to examine the effect of dimensionality on equating. We began by calibrating (with item response theory [IRT] methods) all items on a form to obtain Set I of estimated IRT item parameters. Next, the test was divided into 2 homogeneous subgroups of items, each having been determined to represent a different ability (i.e., inductive or deductive reasoning). The items within these subgroups were then recalibrated separately to obtain item parameter estimates, and then combined into Set II. The estimated item parameters and true-score equating tables for Sets I and II corresponded closely.     

Effects of Linking Methods on Detection of DIF

Studies of differential item functioning under item response theory require that item parameter estimates be placed on the same metric before comparisons can be made. The present study compared the effects of three methods for linking metrics: a weighted mean and sigma method (WMS); the test characteristic curve method (TCC); and the minimum chi-square method (MCS), on detection of differential item functioning. Both iterative and noniterative linking procedures were compared for each method. Results indicated that detection of differentially functioning items following linking via the test characteristic curve method gave the most accurate results when the sample size was small. When the sample size was large, results for the three linking methods were essentially the same. Iterative linking provided an improvement in detection of differentially functioning items over noniterative linking particularly with the .05 alpha level. The weighted mean and sigma method showed greater improvement with iterative linking than either the test characteristic curve or minimum chi-square method.