A Beta Item Response Model for Continuous Bounded Responses

Noël, Yvonnick; Dauvier, Bruno

doi:10.1177/0146621605287691

Cited by 49 publications

(76 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Now is the time to develop an online survey app that uses smartphones to collect patient feedback. The reason is attributable not only to studies [36][37][38] which report that Internet-based online ratings correlate well with the national traditional national surveys and have similar response rates but also to hospitals' need for patient feedback. The results should prove useful when patients choose healthcare providers and when clinicians want to improve the quality of their services.…”

Section: Discussionmentioning

confidence: 99%

Inpatient Perception on Hospitalization Experience across US 50 States: Analysis of the Historical Series from 2007 To 2014

Chen¹,

Chien²,

Tang³

2020

SARJAMS

View full text Add to dashboard Cite

Background: There are many ways to gather and assess patient expectations, experience, and satisfaction, but few use visual representations to report their results on the Google maps and help patients select the best hospitals for consultation. Objectives: To analyze 10-dimensional scores of states in the USA about inpatients' perceptions of their hospitalization experience to develop a method for analyzing data on the Google maps and getting feedback on the smartphones. Methods: We downloaded HCAHPS (Hospital Consumer Assessment of Healthcare Providers and Services) data from the 2007 to 2014 summary of survey results to study (1) whether the 10 dimensional scores can be combined to determine its unidimensionality using Rasch continuous item responses, (2) what type of trends about inpatient perception on hospitalization experience that can be reported with an individual and an overall base, (3) what an online dashboard that can be designed using the Google maps for comparing results of each US state, and (4) how to demonstrate an online assessment that uses smartphones for gathering perceptions of their hospitalization experience in the future. Results: The ten core dimensional scores of each US state about inpatient hospitalization experience reported by the HCAHPS can be unidimensional. The improvement was evident of inpatient perception on hospitalization experience in the historical series. Online visual representation of the Google maps can be easy to build and allows for real-time identification in comparison with the performance of each state. A smartphone app was designed to get feedback directly from patients. Conclusions: We verified that the 10-dimensional scores reporting patient satisfaction in US states could be a unidimensional scale and use Rasch continuous item responses to show results on the Google maps.Keywords: Smart phone, unidimensionality, HCAHPS, hospitalized experience perception, the Google maps SUDPAR.Psychometrically, we are interested in identifying aberrant survey respondents and selecting the best and worst respondents [12]. A method for distinguishing the best and worst clusters is required using the multiple variables of the assessed dimensional scores for an investigation.

show abstract

Section: Discussionmentioning

confidence: 99%

Inpatient Perception on Hospitalization Experience across US 50 States: Analysis of the Historical Series from 2007 To 2014

Chen¹,

Chien²,

Tang³

2020

SARJAMS

View full text Add to dashboard Cite

show abstract

“…In addition, a great deal of work has been devoted to the probabilistic modelling of Likert‐type responses in the past 50 years (Noel & Dauvier, ). However, there are so many patient's clinical data that are not limited to the categorically ordered data.…”

Section: Discussionmentioning

confidence: 99%

Using graphical representations to enhance the quality-of-care for colorectal cancer patients

et al. 2016

View full text Add to dashboard Cite

The study was to enhance adherence to quality-of-care guidelines for colorectal cancer (CRC) patients through plotting graphical representations. Rasch analysis was performed to examine the unidimensional measurement of the 13 core indicators. An author-made Excel module was applied to plot the so-called Wright map and KIDMAP in education field to report physicians' adherence to the quality-of-life guidelines. We found that the scale of the quality-of-care guidelines for patients with colon cancer is unidimensional. A total of 15 (3.8%) and 14 (3.5%) persons' response patterns (i.e., Outfit MNSQs >2.0 and 4.0, respectively) are aberrantly dispersed from the majority of sample according to their estimated parameters of persons and indicators. It can be used for investigating the root cause of the 1ow measures and/or the most unexpected aberrant pattern of responses using Rasch analysis once any one indicator of unexpectedly aberrant treatment (p < .05) presents. The Rasch model can deal with these binary and/or missing data frequently seen in clinical settings. We confirm this computer module can contribute to ensuring that hospitals adhere to the treatment guidelines for patients with colon cancer.

show abstract

“…For instance, Zou, Carlsson and Quinn () apply beta regression to Likert scale data, and Moberg, Alderling and Meding () apply beta regression to a quality of life index. Likewise, Noël and Dauvier () provide item‐response models for doubly bounded continuous scale items using the beta distribution. Verkuilen and Smithson () extended beta regression to mixed (multi‐level) models for dealing with dependencies in the data.…”

Section: Introductionmentioning

confidence: 99%

CDF‐quantile distributions for modelling random variables on the unit interval

Smithson

Shou

2017

Brit J Math & Statis

View full text Add to dashboard Cite

This paper introduces a two-parameter family of distributions for modelling random variables on the (0,1) interval by applying the cumulative distribution function of one 'parent' distribution to the quantile function of another. Family members have explicit probability density functions, cumulative distribution functions and quantiles in a location parameter and a dispersion parameter. They capture a wide variety of shapes that the beta and Kumaraswamy distributions cannot. They are amenable to likelihood inference, and enable a wide variety of quantile regression models, with predictors for both the location and dispersion parameters. We demonstrate their applicability to psychological research problems and their utility in modelling real data.

show abstract

A Beta Item Response Model for Continuous Bounded Responses

Cited by 49 publications

References 33 publications

Inpatient Perception on Hospitalization Experience across US 50 States: Analysis of the Historical Series from 2007 To 2014

Inpatient Perception on Hospitalization Experience across US 50 States: Analysis of the Historical Series from 2007 To 2014

Using graphical representations to enhance the quality-of-care for colorectal cancer patients

CDF‐quantile distributions for modelling random variables on the unit interval

Contact Info

Product

Resources

About