Likelihood Ratio Tests for Model Selection and Non-Nested Hypotheses

Vuong, Quang

doi:10.2307/1912557

Cited by 4,932 publications

(3,826 citation statements)

References 23 publications

Supporting

Mentioning

3,637

Contrasting

Unclassified

Order By: Relevance

“…28 Although we are unable to draw conclusions about the underlying latent traits that result in a score of ≤ 27, whether it is a cognitive impairment or limited health literacy; we argue that we are in fact capturing an individual-level deficit in self-care proficiencies that would be missed with the original MMSE thresholds. 24 Patients falling within this range therefore might be presumed to have inadequate ability to understand and impart medical instructions. This could warrant more in-depth assessment as to what remediation is necessary.…”

Section: Discussionmentioning

confidence: 99%

The Mini Mental Status Exam as a Surrogate Measure of Health Literacy

Dahlke¹,

Curtis

Federman

et al. 2013

J GEN INTERN MED

View full text Add to dashboard Cite

BACKGROUND: Studies have documented strong associations between cognitive function, health literacy skills, and health outcomes, such that outcome performance may be partially explained by cognitive ability. Common cognitive assessments such as the Mini Mental Status Exam (MMSE) therefore may be measuring the same latent construct as existing health literacy tools. OBJECTIVES: We evaluated the potential of the MMSE as a surrogate measure of health literacy by comparing its convergent and predictive validity to the three most commonly used health literacy assessments and education. SUBJECTS: 827 older adults recruited from an academic general internal medicine ambulatory care clinic or one of five federally qualified health centers in Chicago, IL. Non-English speakers and those with severe cognitive impairment were excluded. MEASURES: Pearson correlations were completed to test the convergent validity of the MMSE with assessments of health literacy and education. Receiver Operating Characteristic (ROC) curves and the d statistic were calculated to determine the optimal cut point on the MMSE for classifying participants with limited health literacy. Multivariate logistic regression models were completed to measure the predictive validity of the new MMSE cut point. KEY RESULTS: The MMSE was found to have moderate to high convergent validity with the existing health literacy measures. The ROC and d statistic analyses suggested an optimal cut point of ≤ 27 on the MMSE. The new threshold score was found to predict health outcomes at least as well as, or better than, existing health literacy measures or education alone. CONCLUSIONS: The MMSE has considerable face validity as a health literacy measure that could be easily administered in the healthcare setting. Further research should aim to validate this cut point and examine the constructs being measured by the MMSE and other literacy assessments.

show abstract

Section: Discussionmentioning

confidence: 99%

The Mini Mental Status Exam as a Surrogate Measure of Health Literacy

Dahlke¹,

Curtis

Federman

et al. 2013

J GEN INTERN MED

View full text Add to dashboard Cite

show abstract

“…First, we were predicting count data, and the simplest of count regression models (Poisson) would underestimate the variance in our sample. The negative binomial model does not restrict the variance to be equal to the mean (17) and therefore fit our data better than a Poisson regression. In addition, zeroes occur more frequently in the data than predicted by a Poisson model (that is, most people were not in the hospital or emergency room for most observation months).…”

Section: Methodsmentioning

confidence: 95%

“…The zero-inflated negative binomial model has been useful in predicting low base-rate phenomena in other studies (20,21). A Vuong test (17) indicated that the zero-inflated negative binomial model fit better than the negative binomial model.…”

Section: Methodsmentioning

confidence: 99%

Impact of Illness Management and Recovery Programs on Hospital and Emergency Room Use by Medicaid Enrollees

Salyers

Rollins²,

Clendenning³

et al. 2011

Psychiatric Services

View full text Add to dashboard Cite

Objective Illness management and recovery is a structured program that helps consumers with severe mental illness learn effective ways to manage illness and pursue recovery goals. This study examined the impact of the program on health service utilization. Methods This was a retrospective cohort study of five assertive community treatment (ACT) teams in Indiana that implemented illness management and recovery. With Medicaid claims data from July 1, 2003, to June 30, 2008, panel data were created with person-months as the level of analysis, resulting in 14,261 observations, for a total of 498 unique individuals. Zero-inflated negative binomial regression models were used to predict hospitalization days and emergency room visits, including covariates of demographic characteristics, employment status, psychiatric diagnosis, and concurrent substance use disorder. The main predictor variables of interest were receipt of illness management and recovery services, dropout from the program, and program graduation status. Results Consumers who received some illness management and recovery services had fewer hospitalization days than those receiving only ACT. Graduates had fewer emergency room visits than did ACT-only consumers. Conclusions This is the first study to examine the impact of illness management and recovery on service utilization. Controlling for a number of background variables, the study showed that illness management and recovery programs were associated with reduced inpatient hospitalization and emergency room use over and above ACT.

show abstract

“…The Vuong test, a likelihood-ratio based approach for nonnested models, was used to determine whether the variance explained by models (R 2 ) significantly changed when health literacy, fluid or crystallized abilities were included or omitted. 50 Analyses were performed using STATA 11.2 (College Station, TX).…”

Section: Analysis Planmentioning

confidence: 99%

Literacy, Cognitive Function, and Health: Results of the LitCog Study

et al. 2012

View full text Add to dashboard Cite

BACKGROUND: Emerging evidence suggests the relationship between health literacy and health outcomes could be explained by cognitive abilities. OBJECTIVE:To investigate to what degree cognitive skills explain associations between health literacy, performance on common health tasks, and functional health status. DESIGN: Two face-to-face, structured interviews spaced a week apart with three health literacy assessments and a comprehensive cognitive battery measuring 'fluid' abilities necessary to learn and apply new information, and 'crystallized' abilities such as background knowledge. SETTING: An academic general internal medicine practice and three federally qualified health centers in Chicago, Illinois. PATIENTS: Eight hundred and eighty-two Englishspeaking adults ages 55 to 74. MEASUREMENTS: Health literacy was measured using the Rapid Estimate of Adult Literacy in Medicine (REALM), Test of Functional Health Literacy in Adults (TOFHLA), and Newest Vital Sign (NVS). Performance on common health tasks were globally assessed and categorized as 1) comprehending print information, 2) recalling spoken information, 3) recalling multimedia information, 4) dosing and organizing medication, and 5) healthcare problem-solving. RESULTS: Health literacy measures were strongly correlated with fluid and crystallized cognitive abilities (range: r=0.57 to 0.77, all p<0.001). Lower health literacy and weaker fluid and crystallized abilities were associated with poorer performance on healthcare tasks. In multivariable analyses, the association between health literacy and task performance was substantially reduced once fluid and crystallized cognitive abilities were entered into models (without cognitive abilities: β=−28.9, 95 % Confidence Interval (CI) -31.4

show abstract

Likelihood Ratio Tests for Model Selection and Non-Nested Hypotheses

Cited by 4,932 publications

References 23 publications

The Mini Mental Status Exam as a Surrogate Measure of Health Literacy

The Mini Mental Status Exam as a Surrogate Measure of Health Literacy

Impact of Illness Management and Recovery Programs on Hospital and Emergency Room Use by Medicaid Enrollees

Literacy, Cognitive Function, and Health: Results of the LitCog Study

Contact Info

Product

Resources

About