Detecting Differential Item Functioning Using Logistic Regression Procedures

Swaminathan, Hariharan; Rogers, H. Jane

doi:10.1111/j.1745-3984.1990.tb00754.x

Cited by 851 publications

(865 citation statements)

References 10 publications

Supporting

Mentioning

831

Contrasting

Unclassified

Order By: Relevance

“…After considering some well-regarded methods, we chose to test for DIF using the method that Gelin and Zumbo used because of its wide acceptance and its suitability for performing the large number of DIF analyses we needed to perform in an efficient manner (Gelin and Zumbo, 2003). The Gelin and Zumbo method is similar to the logistic regression approach that Swaminathan and Rogers introduced, but it uses ordinal rather than binary logistic regression to accommodate items with more than two response levels (Swaminathan and Rogers, 1990). We corrected for multiple comparisons using a Benjamini-Hochberg correction (Benjamini and Hochberg, 1995).…”

Section: Chapter Three Analytic Methods and Results: Validation Of Imentioning

confidence: 99%

Patient-Reported Outcome–Based Performance Measures for Older Adults with Multiple Chronic Conditions

Edelen¹,

Rose²,

Bayliss³

et al. 2017

View full text Add to dashboard Cite

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited. Permission is given to duplicate this document for personal use only, as long as it is unaltered and complete. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial use. For information on reprint and linking permissions, please visit www.rand.org/pubs/permissions.The RAND Corporation is a research organization that develops solutions to public policy challenges to help make communities throughout the world safer and more secure, healthier and more prosperous. RAND is nonprofit, nonpartisan, and committed to the public interest.RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.Support RAND Make a tax-deductible charitable contribution at www.rand.org/giving/contribute www.rand.org For more information on this publication, visit www.rand.org/t/RR2176This study was conducted in response to contract HHSN271201500064C NIH NIA (AG).Published by the RAND Corporation, Santa Monica, Calif. © Copyright 2017 RAND CorporationR® is a registered trademark.iii Preface Ensuring patients' survival and curing disease are no longer the sole goals of patient care; functional status and well-being must also be optimized. Standardized assessments through patient-reported outcome (PRO) performance measures (PMs) allow evaluators to see how well these aspects of care are being delivered and compare the performance of health care systems and different provider groups.To meaningfully assess health-related quality of life, PMs must align with patients' goals. Most PMs in current use assess technical quality of care, the benefit of which can take years to realize. These sorts of measures might not be particularly salient to older adults (especially age 80 and older) with multiple chronic conditions (MCC) because their expectations for long-term survival are limited. The desire of such patients to maximize quality of life for the remainder of their life spans is obviously undiminished. However, no PMs have been formally developed or validated for use in this population. Therefore, policymakers and researchers who focus on quality of health care are especially interested in developing PRObased PMs to measure the care delivered to older adults with MCC.This project aimed to address this gap in validated PRO-based PMs through the completion of two aims. The first aim was to determine whether the Patient-Reported Outcomes Measurement Information System 29-item (PROMIS-29) profile instrument is valid for use in this population. The second aim was to study how well PMs based on PROs, specifically the Veterans RAND 36 Item Health Survey (VR-36) and the PROMIS-29, measure functional status and well-being in the same population. This report summarizes our analyses and provides recommendations for future efforts to develo...

show abstract

Section: Chapter Three Analytic Methods and Results: Validation Of Imentioning

confidence: 99%

Patient-Reported Outcome–Based Performance Measures for Older Adults with Multiple Chronic Conditions

Edelen¹,

Rose²,

Bayliss³

et al. 2017

View full text Add to dashboard Cite

show abstract

“…LR is also a common method for detecting DIF (11,32), and a main advantage of this approach is the ability to simultaneously test for both uniform and nonuniform DIF (33). A hierarchical 3-step sequential binary LR modeling process was applied (34):…”

Section: Methods 2: Logistic Regression (Lr)mentioning

confidence: 99%

“…As an initial screen, we examined the discrepancy in the Ϫ2 log likelihood between models 1 and 3 using a chisquare distribution with 2 df (11). If the model fit is better (significant chi-square) in model 3, then some diseaserelated DIF is suggested for the item.…”

Section: Methods 2: Logistic Regression (Lr)mentioning

confidence: 99%

“…Moreover, this would also suggest the need to identify unique score cut points for each form of arthritis. Examples of popular DIF detection methods include the Mantel-Haenszel procedure (10), logistic regression (11) and, more recently, approaches based on item response theory (IRT) measurement frameworks. To date, most attention has been given to investigations of DIF associated with age (12,13), sex (12,14,15), language/translations (16 -18), or culture (12,19,20), but few studies have examined disease-related DIF (21).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Disease‐related differential item functioning in the work instability scale for rheumatoid arthritis: Converging results from three methods

Tang

2011

Arthritis Care & Research

View full text Add to dashboard Cite

Objective. The 23-item Work Instability Scale for Rheumatoid Arthritis (RA-WIS) is a promising measure to assess risk for future work disability. Validated in both rheumatoid arthritis (RA) and osteoarthritis (OA), it has high potential for cross-disease applications. Our objective was to examine disease-related differential item functioning (DIF) in the RA-WIS. Methods. Workers with RA (n ‫؍‬ 120) or OA (n ‫؍‬ 130) were recruited from 3 sites and completed a questionnaire consisting of demographic and health-and work-related variables, including the RA-WIS (range 0 -23, where 23 ‫؍‬ highest work instability). Multiple DIF detection methods were applied for comparability: 1) Mantel-Haenszel and Breslow-Day procedures, 2) hierarchical 3-step sequential logistic regression procedure, and 3) a 1-parameter item response theory approach (Rasch analysis). Both tests of significance (chi-square and F tests) and effect size statistics (⌬ MH , ⌬R 2 ) were assessed to confirm items demonstrating uniform or nonuniform DIF. A 2-step purification procedure was applied to establish a DIF-free conditioning variable (total RA-WIS score) for DIF analyses. The resultant impact of disease-related DIF at the scale level was also evaluated. Results. All 3 DIF detection methods converged to reveal 3 RA-WIS items as having significant disease-related uniform DIF. Two items ("difficulty opening doors" and "pressure on hand") were more likely affirmed in RA, while 1 item ("very stiff") was more likely affirmed in OA. Overall, only a marginal impact at the scale level was found due to a small proportion of scale items exhibiting DIF and the bidirectional nature of DIF effects. Conclusion. RA-WIS scores can be directly compared between RA and OA without significant concerns for DIF-related measurement bias.

show abstract

“…Currently, some of the most commonly used or studied older DIF procedures include the standardization (STAND) 1 procedure (Dorans & Kulick, 1986), SIBTEST (Shealy & Stout, 1993), the Mantel-Haenszel (MH) procedure (Holland & Thayer, 1988), and logistic regression (Swaminathan & Rogers, 1990). Because of their popularity, these are the only old methods that will be compared to the new ones described in this paper.…”

Section: Older Methodsmentioning

confidence: 99%

A Review of Recent Developments in Differential Item Functioning

Mapuranga

Dorans

Middleton

2008

ETS Research Report Series

View full text Add to dashboard Cite

In many practical settings, essentially the same differential item functioning (DIF) procedures have been in use since the late 1980s. Since then, examinee populations have become more heterogeneous, and tests have included more polytomously scored items. This paper summarizes and classifies new DIF methods and procedures that have appeared since the early 1990s and assesses their appropriateness for practical use. Widely used DIF methods are evaluated alongside these new methods for completeness, clarity, and comparability.

show abstract

Detecting Differential Item Functioning Using Logistic Regression Procedures

Cited by 851 publications

References 10 publications

Patient-Reported Outcome–Based Performance Measures for Older Adults with Multiple Chronic Conditions

Patient-Reported Outcome–Based Performance Measures for Older Adults with Multiple Chronic Conditions

Disease‐related differential item functioning in the work instability scale for rheumatoid arthritis: Converging results from three methods

A Review of Recent Developments in Differential Item Functioning

Contact Info

Product

Resources

About

Detecting Differential Item Functioning Using Logistic Regression Procedures

Cited by 851 publications

References 10 publications

Patient-Reported Outcome&ndash;Based Performance Measures for Older Adults with Multiple Chronic Conditions

Patient-Reported Outcome&ndash;Based Performance Measures for Older Adults with Multiple Chronic Conditions

Disease‐related differential item functioning in the work instability scale for rheumatoid arthritis: Converging results from three methods

A Review of Recent Developments in Differential Item Functioning

Contact Info

Product

Resources

About

Patient-Reported Outcome–Based Performance Measures for Older Adults with Multiple Chronic Conditions

Patient-Reported Outcome–Based Performance Measures for Older Adults with Multiple Chronic Conditions