Detecting Local Dependence: A Threshold-Autoregressive Item Response Theory (TAR-IRT) Approach for Polytomous Items

2020 ◽  
Vol 33 (4) ◽  
pp. 280-292
Author(s):  
Xiaodan Tang ◽  
George Karabatsos ◽  
Haiqin Chen
Keyword(s):  
Item Response Theory ◽  
Item Response ◽  
Local Dependence ◽  
Response Theory ◽  
Polytomous Items ◽  
Threshold Autoregressive

Item Response Theory for Scores on Tests Including Polytomous Items with Ordered Responses

1995 ◽  
Vol 19 (1) ◽  
pp. 39-49 ◽  
Author(s):  
David Thissen ◽  
Mary Pommerich ◽  
Kathleen Billeaud ◽  
Valerie S. L. Williams
Keyword(s):  
Item Response Theory ◽  
Item Response ◽  
Response Theory ◽  
Polytomous Items

scholarly journals An Extension of Testlet-Based Equating to the Polytomous Testlet Response Theory Model

2022 ◽  
Vol 12 ◽  
Author(s):  
Feifei Huang ◽  
Zhe Li ◽  
Ying Liu ◽  
Jingan Su ◽  
Li Yin ◽  
...  
Keyword(s):  
Item Response Theory ◽  
Sample Size ◽  
Item Response ◽  
Theory Model ◽  
Response Theory ◽  
Polytomous Items ◽  
Testlet Response Theory ◽  
Accurate Performance ◽  
The Impact ◽  
Item Response Theory Models

Educational assessments tests are often constructed using testlets because of the flexibility to test various aspects of the cognitive activities and broad content sampling. However, the violation of the local item independence assumption is inevitable when tests are built using testlet items. In this study, simulations are conducted to evaluate the performance of item response theory models and testlet response theory models for both the dichotomous and polytomous items in the context of equating tests composed of testlets. We also examine the impact of testlet effect, length of testlet items, and sample size on estimating item and person parameters. The results show that more accurate performance of testlet response theory models over item response theory models was consistently observed across the studies, which supports the benefits of using the testlet response theory models in equating for tests composed of testlets. Further, results of the study indicate that when sample size is large, item response theory models performed similarly to testlet response theory models across all studies.

Evaluation of the psychometric properties of the burn specific health scale-brief: A National Institute on Disability, Independent Living, and Rehabilitation Research Burn Model System Study

2021 ◽  
Author(s):  
Dagmar Amtmann ◽  
Alyssa Bamer ◽  
Kara McMullen ◽  
Colleen M Ryan ◽  
Jeffrey C Schneider ◽  
...  
Keyword(s):  
Item Response Theory ◽  
Psychometric Properties ◽  
Item Response ◽  
Burn Injury ◽  
Local Dependence ◽  
Response Theory ◽  
Response Options ◽  
Ceiling Effects ◽  
Item Response Theory Models ◽  
Specific Health

Abstract Objective The Burn Specific Health Scale-Brief (BSHS-B) is a commonly used burn specific health outcome measure that includes 40 items across nine subscales. The objective of this study was to use both classical and modern psychometric methods to evaluate psychometric properties of the BSHS-B. Methods Data were collected post burn injury by a multisite federally funded project tracking long term outcomes. We examined dimensionality, local dependence, item fit, and functioning of response categories, homogeneity, and floor and ceiling effects. Items were fit to Item Response Theory models for evaluation. Results A total of 653 adults with burn injury completed the BSHS-B. Factor analyses supported unidimensionality for all subscales, but not for a total score based on all 40 items. All nine of the subscales had significant ceiling effects. Six item pairs displayed local dependence suggesting redundance and 11 items did not fit the Item Response Theory models. At least 15 items have too many response options. Conclusions Results identified numerous psychometric issues with the BSHS-B. A single summary score should never be used for any purpose. Psychometric properties of the scale need to be improved by removing redundant items, reducing response categories and modifying or deleting problematic items. Additional conceptual work is needed to, at a minimum, revise the work subscale and optimally to revisit and clearly define the constructs measured by all the subscales. Additional items are needed to address ceiling effects.

scholarly journals Is the Polythetic Approach Efficient in Identifying Potentially Addicted to Work Individuals? Comparison of the Polythetic Approach With the Item Response Theory Framework

2019 ◽  
Author(s):  
Piotr Bereznowski ◽  
Roman Konarski
Keyword(s):  
Item Response Theory ◽  
Item Response ◽  
Latent Trait ◽  
Substantial Effect ◽  
Prevalence Rates ◽  
Response Theory ◽  
Polytomous Items ◽  
Work Addiction ◽  
Trait Level ◽  
Theory Framework

This study included investigation of efficiency of the threshold used to classify symptoms as present, investigation of efficiency of the cut-off point used to identify potentially addicted to work individuals, investigation of magnitude of the problem of class overlap, and investigation of effects of dichotomization of polytomous items on the estimates of the latent trait level. The sample comprised 16,426 working Norwegians (M age = 37.31; SD = 11.36) who filled out the Bergen Work Addiction Scale (BWAS). The results showed that the difficulty/third threshold parameters corresponding to the threshold used to classify symptoms as present were lower than 1.5 for the items corresponding to tolerance and conflict and higher than or equal to 1.5 for the items corresponding to salience, mood modification, relapse, withdrawal, and problems. The cut-off point used to identify individuals as potentially addicted to work identified 411 individuals (31.9% of all individuals classified by the polythetic approach as potentially addicted to work) whose estimates of the latent trait level were lower than 1.5 as potentially addicted to work. The problem of class overlap (being classified by the polythetic approach into different class despite almost the same level of the latent trait) affected 4,686 individuals (28.5% of the whole sample). The dichotomization of polytomous items had a substantial effect on the estimates of the latent trait level. The findings show that the polythetic approach is not efficient in identifying potentially addicted to work individuals and that the prevalence rates of work addiction based on the polythetic approach are not trustworthy.

scholarly journals A Posterior Predictive Model Checking Method Assuming Posterior Normality for Item Response Theory

2018 ◽  
Vol 43 (2) ◽  
pp. 125-142 ◽  
Author(s):  
Megan Kuhfeld
Keyword(s):  
Item Response Theory ◽  
Model Checking ◽  
Predictive Model ◽  
Item Response ◽  
Local Dependence ◽  
Response Theory ◽  
Full Information Maximum Likelihood ◽  
Posterior Predictive Model Checking ◽  
Irt Models ◽  
Straightforward Method

This study investigated the violation of local independence assumptions within unidimensional item response theory (IRT) models. Bayesian posterior predictive model checking (PPMC) methods are increasingly being used to investigate multidimensionality in IRT models. The current work proposes a PPMC method for evaluating local dependence in IRT models that are estimated using full-information maximum likelihood. The proposed approach, which was termed as “PPMC assuming posterior normality” (PPMC-N), provides a straightforward method to account for parameter uncertainty in model fit assessment. A simulation study demonstrated the comparability of the PPMC-N and the Bayesian PPMC approach in the detection of local dependence in dichotomous IRT models.

Local Dependence Indexes for Item Pairs Using Item Response Theory

1997 ◽  
Vol 22 (3) ◽  
pp. 265-289 ◽  
Author(s):  
Wen-Hung Chen ◽  
David Thissen
Keyword(s):  
Item Response Theory ◽  
Item Response ◽  
Special Interest ◽  
Simulated Data ◽  
Local Dependence ◽  
Null Condition ◽  
Local Independence ◽  
Response Theory ◽  
Null Case ◽  
New Statistics

Four statistics are proposed for the detection of local dependence (LD) among items analyzed using item response theory. Among them, the X2 and G2 LD indexes are of special interest. Simulated data are used to study the distribution and sensitivity of these statistics under the null condition, as well as under conditions in which LD is introduced. The results show that under the null condition of local independence, both the X2 and G2 LD indexes have distributions very similar to the X2 distribution with 1 degree of freedom. Under the locally dependent conditions, both indexes appear to be sensitive in detecting LD or multidimensionality among items. When compared to Q3, another statistic often used to detect LD, these new statistics are somewhat less powerful for underlying LD, equally powerful for surface LD, and better behaved in the null case.

Sign in / Sign up

Export Citation Format

Share Document