scholarly journals Selective inference in complex research

2009 ◽  
Vol 367 (1906) ◽  
pp. 4255-4271 ◽  
Author(s):  
Yoav Benjamini ◽  
Ruth Heller ◽  
Daniel Yekutieli
Keyword(s):  
Type 2 Diabetes ◽  
False Discovery Rate ◽  
Confidence Intervals ◽  
False Discovery ◽  
False Discovery Rate Approach ◽  
Selective Inference

We explain the problem of selective inference in complex research using a recently published study: a replicability study of the associations in order to reveal and establish risk loci for type 2 diabetes. The false discovery rate approach to such problems will be reviewed, and we further address two problems: (i) setting confidence intervals on the size of the risk at the selected locations and (ii) selecting the replicable results.

scholarly journals Simulation of trajectories in the illness-death model for chronic diseases: discrete event simulation, Doob-Gillespie algorithm and coverage of Wald confidence intervals

2020 ◽  
Author(s):  
Ralph Brinks ◽  
Annika Hoyer
Keyword(s):  
Type 2 Diabetes ◽  
Chronic Diseases ◽  
Confidence Intervals ◽  
Discrete Event Simulation ◽  
Discrete Event ◽  
Gillespie Algorithm ◽  
Event Simulation ◽  
Bias Variance

AbstractWe compare two approaches for simulating events in the illness-death model in a test example about type 2 diabetes in Germany. The first approach is a discrete event simulation, where relevant events, i.e., onset of disease and death, are simulated for each subject individually. The second approach is the Doob-Gillespie algorithm, which simulates the number of people in each state of the illness-death model at each point in time. The algorithms are compared in terms of bias, variance and speed. Based on the results of the comparison in the test example, we assess coverage of the corresponding Wald confidence intervals.

scholarly journals Bootstrap Confidence Intervals for Costs-of-Illness of Type 2 Diabetes Mellitus in Germany

2002 ◽  
Vol 5 (5) ◽  
pp. 398-404 ◽  
Author(s):  
Stefan Wagenpfeil ◽  
Albrecht Neiss ◽  
Anita Goertz ◽  
Ursula Reitberger ◽  
Holger Stammer ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Type 2 Diabetes ◽  
Type 2 Diabetes Mellitus ◽  
Confidence Intervals ◽  
Bootstrap Confidence Intervals ◽  
Costs Of Illness

Abstract 009: Plain Water and Total Beverage Intakes and Risk of Type 2 Diabetes in Young and Middle-aged Women

Circulation ◽  
2012 ◽  
Vol 125 (suppl_10) ◽  
Author(s):  
An Pan ◽  
Vasanti Malik ◽  
Walter C Willett ◽  
Frank B Hu
Keyword(s):  
Type 2 Diabetes ◽  
Confidence Intervals ◽  
Lower Risk ◽  
Fruit Juice ◽  
Reference Group ◽  
Plain Water ◽  
Sugar Sweetened Beverage ◽  
Sweetened Beverage ◽  
Relative Risks

Introduction: Some caloric beverages (e.g., sugar-sweetened beverage and fruit juice) have been associated with an elevated risk of type 2 diabetes; therefore, substitution of these caloric beverages with non-caloric beverages such as plain water may be important for diabetes prevention. Few previous studies have examined the association between plain water or total beverage intake and risk of type 2 diabetes. Methods: We followed 82,900 women, aged 27-45 years and free of diabetes, cardiovascular disease and cancer at baseline, from 1991 to 2007. Diet, including various beverages, was assessed by food frequency questionnaires and updated every four years. Incident type 2 diabetes cases were confirmed by supplementary questionnaires. Cox proportional hazard models were used to calculate relative risks (RRs) and corresponding 95% confidence intervals (CIs), and we estimated the effect of “substituting” a serving of one beverage for another by including both as continuous variables in the same multivariable model. The difference in their beta coefficients and their variances and covariance were used to estimate the RR and 95% CI for the substitution effect. Results: During 1,294,196 person-years of follow-up, we documented 2,980 incident T2DM cases. After adjustment for age and body mass index, compared with the reference group (<1 glass/d), the relative risks (RRs) and 95% confidence intervals (CIs) of type 2 diabetes according to categories of plain water consumption were 0.91 (0.81-1.02) for 1 glass/d, 0.91 (0.82-1.01) for 2-3 glasses/d, 0.98 (0.87-1.11) for 4-5 glasses/d, and 1.02 (0.89-1.18) for 6 or more glasses/d (P-for-trend=0.51). Further adjustment for other diabetes risk factors did not substantially alter the RRs. We estimated that substituting one serving/d of plain water for one serving/d of sugar-sweetened beverage or fruit juice was associated with a 10% (95% CI, 6%-13%) and 13% (95% CI, 7%-18%) lower risk of type 2 diabetes, respectively. In this cohort, no association was found for total beverage intake and risk of type 2 diabetes: compared with women who drank less than 6 servings/d of total beverage, the RRs (95% CIs) were 0.97 (0.87-1.09), 0.98 (0.88-1.10), 1.01 (0.89-11.5), and 0.99 (0.86-1.14) for women drank 6-8, 8-10, 10-12, and ≥12 servings/d of total beverages (P-for-trend=0.83). Conclusions: Increasing consumption of water per se was not associated with risk of type 2 diabetes, but substituting plain water for sugar-sweetened beverage or fruit juice was associated with a significantly lower risk of type 2 diabetes.

scholarly journals False Discovery Rate Approach to Unsupervised Image Change Detection

2016 ◽  
Vol 25 (10) ◽  
pp. 4704-4718 ◽  
Author(s):  
Vladimir A. Krylov ◽  
Gabriele Moser ◽  
Sebastiano B. Serpico ◽  
Josiane Zerubia
Keyword(s):  
Change Detection ◽  
False Discovery Rate ◽  
False Discovery ◽  
Image Change Detection ◽  
False Discovery Rate Approach

scholarly journals Rural prevalence of type 2 diabetes mellitus: A cross sectional study

2014 ◽  
Vol 02 (02) ◽  
pp. 082-086 ◽  
Author(s):  
Hetal Rathod ◽  
Sanjay Darade ◽  
Uday Chitnis ◽  
Jitendra Bhawalkar ◽  
Sudhir Jadhav ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Risk Factors ◽  
Type 2 Diabetes ◽  
Family History ◽  
Confidence Intervals ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Cross Sectional ◽  
Waist Hip Ratio

Abstract Background: Recent studies in India indicate rising trends of diabetes even in rural areas. Continuous monitoring of the diabetes situation is required by repeated cross sectional studies in different parts of the country both urban rural to plan control measures. Aim: To estimate the prevalence of Type 2 diabetes in a sample of rural population and explore associations between diabetes and known risk factors. Materials and Methods: A cross sectional study was carried out in 3 villages in the rural field practice area of a medical college in Pune, India. All eligible adults of both genders were included and screened for diabetes by house to house survey. A total of 1000 subjects were examined. Physical examination included measuring height, weight, and waist hip ratio. Blood glucose was estimated using glucometer. Family history of diabetes was also elicited. Data was analysed by descriptive statistics using proportions with 95% confidence intervals. Various associations were explored using using Odds Ratio with 95% confidence intervals as applicable. Results: The prevalence of diabetes mellitus was 9.1% (91/1000; 95% CI 7.4, 11). Most cases of newly detected diabetics were in the age group 36 - 40 years. There was no association between gender and diabetes (OR = 1.38, 95% CI 0.88, 2.17). Overweight status was associated with diabetes: 38.5% (35/91) of diabetics were overweight compared to 18.6% (169/909) of non-diabetics (OR = 2.74, 95% CI 1.69, 4.41). Similarly abnormal waist hip ratio was associated with diabetes: 47.25% (43/91) of diabetics had high waist hip ratio compared with 29.59% (269/909) of non-diabetics (OR = 2.13, 95% CI 1.35, 3.37). Also family history was strongly associated with diabetes: 27.5% (25/91) of diabetics gave positive family history compared with 9.4% (85/909) of non-diabetics (OR = 3.67, 95% CI = 2.13, 6.30). Conclusion: The burden of diabetes was present in the rural population studied. The associated known risk factors were also prevalent and showed strong relationship with diabetes. Diabetes mellitus erstwhile thought to be a disease of urban life appears to be equally prevalent in the rural setting.

Sign in / Sign up

Export Citation Format

Share Document