Coefficient α as a Measure of Test Score Reliability: Review of 3 Popular Misconceptions

Morera, Osvaldo F.; Stokes, Sonya M.

doi:10.2105/ajph.2015.302993

Cited by 82 publications

(64 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Chronbach’s alpha (internal consistency) was measured to evaluate the reliability of each factor. Chronbach’s alpha ≥.5 was considered acceptable, in line with previous studies [43, 44]. The correlations between the IPQ-A subscales were evaluated by calculating the Pearson’s correlation coefficient.…”

Section: Methodsmentioning

confidence: 64%

Good Psychometric Properties of the Addiction Version of the Revised Illness Perception Questionnaire for Health Care Professionals

et al. 2016

View full text Add to dashboard Cite

BackgroundAddiction, or substance dependence, is nowadays considered a chronic relapsing condition. However, perceptions of addiction vary widely, also among healthcare professionals. Perceptions of addiction are thought to contribute to attitude and stigma towards patients with addiction. However, studies into perceptions of addiction among healthcare professionals are limited and instruments for reliable assessment of their perceptions are lacking. The Illness Perception Questionnaire (IPQ) is widely used to evaluate perceptions of illness. The aim of this study was to evaluate the psychometric properties of the IPQ: factor structure, internal consistency, and discriminant validity, when applied to evaluate healthcare professionals’ perceptions of addiction.MethodsParticipants were 1072 healthcare professionals in training and master students from the Netherlands and Indonesia, recruited from various addiction-training programs. The revised version of the IPQ was adapted to measure perceptions of addiction (IPQ-A). Maximum likelihood method was used to explore the best-fit IPQ factor structure. Internal consistency was evaluated for the final factors. The final factor structure was used to assess discriminant validity of the IPQ, by comparing illness perceptions of addiction between 1) medical students from the Netherlands and Indonesia, 2) medical students psychology students and educational science students from the Netherlands, and 3) participants with different training levels: medical students versus medical doctors.ResultsFactor analysis revealed an eight-factor structure for the perception subscale (demoralization, timeline chronic, consequences, personal control, treatment control, illness coherence, timeline cyclical emotional representations) and a four-factor structure for the attribution subscale (psychological attributions, risk factors, smoking/alcohol, overwork). Internal reliability was acceptable to good. The IPQ-A was able to detect differences in perceptions between healthcare professionals from different cultural and educational background and level of training.ConclusionsThe IPQ-A is a valid and reliable instrument to assess healthcare professionals’ perceptions of addiction.

show abstract

Section: Methodsmentioning

confidence: 64%

Good Psychometric Properties of the Addiction Version of the Revised Illness Perception Questionnaire for Health Care Professionals

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Reliability was studied using internal consistency, assuming all items were similar and measured a single construct. Internal consistency was supported if Cronbach's alpha exceeded 0.70 …”

Section: Methodsmentioning

confidence: 99%

Validity and reliability of the Health Assessment Questionnaire among patients with spondyloarthritis in Singapore

et al. 2016

View full text Add to dashboard Cite

show abstract

“…A reliable instrument is one where the observed values are true with acceptable errors of measurement . The overall consistency of ASAS HI was measured using internal consistency and it is supported if Cronbach's alpha is greater than or equal to 0.70 . Test‐retest reliability assesses repeatability of the values and was measured with intraclass correlation coefficient (ICC) (2‐way mixed effects model) with a 95% confidence interval .…”

Section: Methodsmentioning

confidence: 99%

Validity and reliability of the Assessment of Spondyloarthritis International Society Health Index in English‐speaking patients with axial spondyloarthritis in Singapore

Kwan

Fong

et al. 2019

Int J of Rheum Dis

View full text Add to dashboard Cite

Objectives To assess the validity and reliability of the Assessment of Spondyloarthritis International Society Health Index (ASAS HI) among patients with axial spondyloarthritis (axSpA) in Singapore. Methods We collected data from English‐speaking patients with axSpA seen at a dedicated axSpA clinic in a Singapore tertiary referral hospital from 2017 to 2018. Face validity of the English version of ASAS HI was assessed through cognitive debriefing interviews (CDIs). Structural validity was assessed with confirmatory factor analysis. Convergent construct validity was assessed with 12 a priori hypotheses about the magnitude and direction of correlations between the ASAS HI summary score and other patient‐reported outcome measures. Internal consistency was assessed using Cronbach's alpha. Test‐retest reliability was assessed by intraclass correlation coefficient (ICC). Measurement error was assessed by analyzing smallest detectable change (SDC). Results Ten patients (age range 22‐46 years, 50% male) participated in CDIs and face validity was supported. Among 108 patients (median age: 37 [21‐77], 80.6% males), unidimensionality was confirmed (comparative fit index = 0.960, Tucker‐Lewis Index = 0.952, root mean square error of approximation = 0.038, standardized root mean residuals = 0.068, model Chi‐square test P = 0.1251) in the 17‐item ASAS HI. The ASAS HI showed good internal consistency of 0.83 and excellent test‐retest reliability (ICC = 0.95; 95% CI 0.91‐0.98) when baseline was compared with week 2. SDC was 1.02. Convergent validity was supported as hypotheses were confirmed in 100% of the results. Conclusions This study supports the ASAS HI as a valid and reliable measure of health status for use in patients with axSpA in Singapore.

show abstract

Coefficient α as a Measure of Test Score Reliability: Review of 3 Popular Misconceptions

Cited by 82 publications

References 18 publications

Good Psychometric Properties of the Addiction Version of the Revised Illness Perception Questionnaire for Health Care Professionals

Good Psychometric Properties of the Addiction Version of the Revised Illness Perception Questionnaire for Health Care Professionals

Validity and reliability of the Health Assessment Questionnaire among patients with spondyloarthritis in Singapore

Validity and reliability of the Assessment of Spondyloarthritis International Society Health Index in English‐speaking patients with axial spondyloarthritis in Singapore

Contact Info

Product

Resources

About