A small sample simulation study of methods for log odds ratio regression analysis

Objectives We aimed to evaluate peripheral varicose vein symptoms including ecchymosis and coldness by using the Venous Insufficiency Epidemiological and Economic Study-Quality of Life/Symptoms (VEINES-QoL/Sym) questionnaire. Methods A total of 1120 patients were enrolled to the analysis after the exclusion of 199 patients who did not match the inclusion criteria. Patients were asked to answer the VEINES-Sym questionnaire and questions about ecchymosis and coldness. Scores of ecchymosis and coldness were calculated similar to VEINES-Sym questionnaire. Classifications of peripheral varicose vein were made according to the clinical part of clinical, etiological, anatomical, and pathophysiological classification system and patients with grade 2 or higher were considered as positive for peripheral varicose vein. Results Frequency of symptoms present in the VEINES-Sym instrument, ecchymosis and coldness were significantly higher in patients with peripheral varicose vein. Mean score of each symptom was significantly lower in peripheral varicose vein patients including scores of ecchymosis and coldness. Logistic regression analysis revealed that presence of hemorrhoids and all symptoms in VEINES-Sym questionnaire except restless leg were significantly and independently associated with peripheral varicose vein. Besides, ecchymosis (odds ratio: 2.04, 95% confidence interval: 1.34–3.08, p = 0.008) but not coldness was significantly and independently associated with peripheral varicose vein. There was also significant correlation of VEINES-Sym score with ecchymosis ( r = 0.43, p < 0.001) and coldness ( r = 0.47, p < 0.001). Conclusions Venous leg symptoms present in VEINES-Sym questionnaire except restless legs, presence of hemorrhoids and ecchymosis are significantly and independently associated with peripheral varicose vein. Not only ecchymosis but also coldness has shown an independent association with total VEINES-Sym score.

Download Full-text

Sensitivity and specificity of normality tests and consequences on reference interval accuracy at small sample size: a computer-simulation study

Veterinary Clinical Pathology ◽

10.1111/vcp.12390 ◽

2016 ◽

Vol 45 (4) ◽

pp. 648-656 ◽

Cited By ~ 24

Author(s):

Kevin Le Boedec

Keyword(s):

Computer Simulation ◽

Sample Size ◽

Sensitivity And Specificity ◽

Simulation Study ◽

Small Sample Size ◽

Reference Interval ◽

Small Sample ◽

Computer Simulation Study

Download Full-text

Small Sample Confidence Intervals for the Odds Ratio

Communications in Statistics - Simulation and Computation ◽

10.1081/sac-200040691 ◽

2004 ◽

Vol 33 (4) ◽

pp. 1095-1113 ◽

Cited By ~ 27

Author(s):

Raef Lawson

Keyword(s):

Confidence Intervals ◽

Odds Ratio ◽

Small Sample

Download Full-text

Small-Sample Bias of Point Estimators of the Odds Ratio from Matched Sets

Biometrics ◽

10.2307/2531395 ◽

1984 ◽

Vol 40 (2) ◽

pp. 421 ◽

Cited By ~ 43

Author(s):

Nicholas P. Jewell

Keyword(s):

Odds Ratio ◽

Small Sample ◽

Sample Bias ◽

Point Estimators

Download Full-text

Using an Interaction Parameter in Model-Based Phase I Trials for Combination Treatments? A Simulation Study

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18010345 ◽

2021 ◽

Vol 18 (1) ◽

pp. 345

Author(s):

Pavel Mozgunov ◽

Rochelle Knight ◽

Helen Barnett ◽

Thomas Jaki

Keyword(s):

Phase I ◽

Interaction Parameter ◽

Simulation Study ◽

Small Sample Size ◽

Small Sample ◽

Dose Finding ◽

Phase I Trials ◽

Model Based ◽

Combination Toxicity ◽

Toxicity Relationship

There is growing interest in Phase I dose-finding studies studying several doses of more than one agent simultaneously. A number of combination dose-finding designs were recently proposed to guide escalation/de-escalation decisions during the trials. The majority of these proposals are model-based: a parametric combination-toxicity relationship is fitted as data accumulates. Various parameter shapes were considered but the unifying theme for many of these is that typically between 4 and 6 parameters are to be estimated. While more parameters allow for more flexible modelling of the combination-toxicity relationship, this is a challenging estimation problem given the typically small sample size in Phase I trials of between 20 and 60 patients. These concerns gave raise to an ongoing debate whether including more parameters into combination-toxicity model leads to more accurate combination selection. In this work, we extensively study two variants of a 4-parameter logistic model with reduced number of parameters to investigate the effect of modelling assumptions. A framework to calibrate the prior distributions for a given parametric model is proposed to allow for fair comparisons. Via a comprehensive simulation study, we have found that the inclusion of the interaction parameter between two compounds does not provide any benefit in terms of the accuracy of selection, on average, but is found to result in fewer patients allocated to the target combination during the trial.

Download Full-text

Abstract TP74: Early Administration of Tissue-plasminogen Activator Improves the Long-term Clinical Outcome at 5 Years After Onset

Stroke ◽

10.1161/str.47.suppl_1.tp74 ◽

2016 ◽

Vol 47 (suppl_1) ◽

Author(s):

Junya Aoki ◽

Kazumi Kimura ◽

Yuki Sakamoto

Keyword(s):

Regression Analysis ◽

Confidence Interval ◽

Plasminogen Activator ◽

Clinical Outcomes ◽

Tissue Plasminogen Activator ◽

Odds Ratio ◽

Univariate Analysis ◽

Favorable Outcome ◽

Tissue Plasminogen

Introduction & Hypothesis: Data on long-term outcomes after tissue-plasminogen activator (tPA) therapy are limited. We evaluated the rate of favorable outcomes and mortality at 5 years after tPA therapy and investigated factors related to long-term clinical outcomes. Methods: Telephone interviews were used to assess the to the the modified Rankin Scale (mRS) scores at 3 months, 6 months, 1 year, 2 years, 3 years, 4 years, and 5 years after tPA therapy after written informed consent was obtained. When a telephone interview was not successfully accomplished, an interview letter was sent as an alternative method. Favorable outcome was defined as mRS 0-2, and unfavorable outcome was as mRS 3-6. Multivariate logistic regression analysis was conducted to investigate factors associated with favorable outcomes and mortality at 5 years after tPA therapy. Results: From 2005 to 2013, 256 (median age, 77 [interquartile range, 68-84] years; 157 [61%] males) patients were enrolled. The onset-to-treatment time (OTT) was 153 (120-176) minutes. At 3 months after tPA therapy, the median mRS score was assessed as 3 (1-5). Kaplan-Meier curve showed that favorable outcomes after 5 years after tPA therapy occurred in 45% patients and that the mortality rate was 40%. Univariate analysis showed that OTT was 123 (107-172) minutes in patients with favorable outcomes and 155 (124-172) minutes in patients with non-favorable outcomes (p=0.046). In addition, OTT was 157 (133-172) minutes in the death group and 123 (106-169) minutes in the survival group (p=0.001). Multivariate regression analysis indicated that OTT was an independent factor related to favorable outcomes (odds ratio 0.97, 95% confidence interval 0.95-0.99, p=0.008) and mortality (odds ratio 1.04, 95% confidence interval 1.02-1.06, p=0.001). Receiver operating characteristic curve analysis showed that OTT ≥ 136 minutes was the optimal cut-off value to predict favorable outcome at 5 years after tPA therapy, with a sensitivity of 0.67, a specificity of 0.70, and an area under curve (AUC) of 0.662 (p=0.016), and that to predict death within 5 years after tPA therapy, with a sensitivity of 0.70, a specificity of 0.66, and an AUC of 0.679 (p=0.001). Conclusion: Early tPA administration can improves long-term clinical outcomes.

Download Full-text

Retrospective Analysis of Risk Factors for Postoperative Perineal Hernia After Endoscopic Abdominoperineal Excision for Rectal Cancer

10.21203/rs.3.rs-962418/v1 ◽

2021 ◽

Author(s):

Tatsuya Manabe ◽

Yusuke Mizuuchi ◽

Yasuhiro Tsuru ◽

Hiroshi Kitagawa ◽

Takaaki Fujimoto ◽

...

Keyword(s):

Risk Factors ◽

Rectal Cancer ◽

Regression Analysis ◽

Odds Ratio ◽

Open Surgery ◽

Abdominoperineal Excision ◽

Perineal Hernia ◽

Lower Rectal Cancer ◽

Peritoneal Closure ◽

Initial Surgery

Abstract Background: In contrast to open-surgery abdominoperineal excision (APE) for rectal cancer, postoperative perineal hernia (PPH) is reported to increase after extralevator APE and endoscopic surgery. In this study, therefore, we aimed to determine the risk factors for PPH after endoscopic APE.Methods: A total 73 patients who underwent endoscopic APE for lower rectal cancer were collected from January 2009 to March 2020, and the risk factors for PPH were analyzed retrospectively.Results: Nineteen patients (26%) developed PPH after endoscopic APE, and the diagnosis of PPH was made at 9–393 days (median: 183 days) after initial surgery. Logistic regression analysis showed that absence of pelvic peritoneal closure alone increased the incidence of PPH significantly (odds ratio; 13.76, 95% confidence interval; 1.48–1884.84, p = 0.004).Conclusions: Pelvic peritoneal closure should be performed when possible after endoscopic APE to prevent PPH.

Download Full-text