On the Large-Sample Distribution of the Mantel-Haenszel Odds-Ratio Estimator

Biometrics ◽  
1983 ◽  
Vol 39 (2) ◽  
pp. 523 ◽  
Author(s):  
O. Guilbaud ◽  
Walter Hauck
Keyword(s):  
Odds Ratio ◽  
Ratio Estimator ◽  
Sample Distribution ◽  
Large Sample

Inference for Support Vector Regression under ℓ1 Regularization

2021 ◽  
Vol 111 ◽  
pp. 611-615
Author(s):  
Yuehao Bai ◽  
Hung Ho ◽  
Guillaume A. Pouliot ◽  
Joshua Shea
Keyword(s):  
Support Vector Regression ◽  
Tuning Parameter ◽  
Support Vector ◽  
L1 Norm ◽  
Test Statistic ◽  
Sample Distribution ◽  
Large Sample ◽  
Variance Estimate ◽  
Error Bars ◽  
ℓ1 Regularization

We provide large-sample distribution theory for support vector regression (SVR) with l1-norm along with error bars for the SVR regression coefficients. Although a classical Wald confidence interval obtains from our theory, its implementation inherently depends on the choice of a tuning parameter that scales the variance estimate and thus the width of the error bars. We address this shortcoming by further proposing an alternative large-sample inference method based on the inversion of a novel test statistic that displays competitive power properties and does not depend on the choice of a tuning parameter.

Variation in COVID-19 Mortality Across 117 US Hospitals in High- and Low-Burden Settings

2021 ◽  
Author(s):  
Brian L Block ◽  
Thomas M Martin ◽  
W John Boscardin ◽  
Kenneth E Covinsky ◽  
Michele Mourad ◽  
...  
Keyword(s):  
Odds Ratio ◽  
Adjusted Odds Ratio ◽  
Hospital Death ◽  
Hospital Level ◽  
Large Variability ◽  
Large Sample ◽  
Number Of Patients ◽  
Study Population

Some hospitals have faced a surge of patients with COVID-19, while others have not. We assessed whether COVID-19 burden (number of patients with COVID-19 admitted during April 2020 divided by hospital certified bed count) was associated with mortality in a large sample of US hospitals. Our study population included 14,226 patients with COVID-19 (median age 66 years, 45.2% women) at 117 hospitals, of whom 20.9% had died at 5 weeks of follow-up. At the hospital level, the observed mortality ranged from 0% to 44.4%. After adjustment for age, sex, and comorbidities, the adjusted odds ratio for in-hospital death in the highest quintile of burden was 1.46 (95% CI, 1.07-2.00) compared to all other quintiles. Still, there was large variability in outcomes, even among hospitals with a similar level of COVID-19 burden and after adjusting for age, sex, and comorbidities.

Social Support and Success at Stopping Smoking

2007 ◽  
Vol 2 (2) ◽  
pp. 47-53 ◽  
Author(s):  
Sylvia May ◽  
Robert West ◽  
Peter Hajek ◽  
Andy McEwen ◽  
Hayden McRobbie
Keyword(s):  
Social Support ◽  
Treatment Program ◽  
Odds Ratio ◽  
Short Term ◽  
Large Sample ◽  
End Of Treatment ◽  
The Social ◽  
The Relationship

AbstractThis article characterises the social support received by a large sample of smokers attempting to stop and the relationship between this and the outcome of their attempt. A survey was conducted of 928 smokers attending a group-based program. Smoking among colleagues and a perception of having someone to turn to predicted outcome at the end of treatment, 4 weeks from the quit date (Odds ratio [OR] = 0.81, p = .008 and OR = 1.31, p = .003 respectively) Among those who abstained for the first week, smoking among colleagues and the frequency with which they had been offered cigarettes predicted outcome at the end of treatment (OR = 0.81, p = .04 and OR = 0.73, p = .01 respectively). There were no significant social support correlates of cessation for 26 weeks. Social support has a role to play in the short-term, but in the context of a group-based treatment program appears not to be related to long-term success.

Sign in / Sign up

Export Citation Format

Share Document