A note on exact confidence interval for causal effects on a binary outcome in randomized trials

2016 ◽  
Vol 35 (10) ◽  
pp. 1739-1741 ◽  
Author(s):  
Yasutaka Chiba
Keyword(s):  
Confidence Interval ◽  
Randomized Trials ◽  
Causal Effects ◽  
Binary Outcome ◽  
Exact Confidence Interval

scholarly journals Bayesian Inference of Causal Effects for an Ordinal Outcome in Randomized Trials

2018 ◽  
Vol 6 (2) ◽  
Author(s):  
Yasutaka Chiba
Keyword(s):  
Randomized Trials ◽  
Randomized Clinical Trials ◽  
Likelihood Function ◽  
Causal Effect ◽  
Causal Effects ◽  
Potential Outcomes ◽  
Response Type ◽  
Binary Outcome ◽  
Modeling Assumption ◽  
Ordinal Outcome

AbstractIn randomized trials in which two treatment arms are compared with a binary outcome, the causal effect can be identified by assuming that the two treatment arms are exchangeable. In trials with an ordinal outcome, which is categorized as more than two, the causal effect can be identified by assuming that the potential outcomes are independent and that the two treatment arms are exchangeable. In this article, we propose a Bayesian approach to causal inference that does not rely on these two assumptions. To achieve this purpose, we use a randomization-based approach and response type. Then, the likelihood function is derived by physical randomization in which subjects who belong to a response type are randomly assigned to the treatment or control, with no modeling assumption on the outcome. Our approach can derive not only the posterior distribution of the causal effect but also that of the number of subjects in each response type. The proposed approach is illustrated with two examples from randomized clinical trials.

Phase II study of vinorelbine in patients with pretreated advanced ovarian cancer: activity in platinum-resistant disease.

1996 ◽  
Vol 14 (9) ◽  
pp. 2546-2551 ◽  
Author(s):  
E Bajetta ◽  
A Di Leo ◽  
L Biganzoli ◽  
L Mariani ◽  
F Cappuzzo ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Confidence Interval ◽  
Cancer Patients ◽  
Response Rate ◽  
Advanced Ovarian Cancer ◽  
Dose Intensity ◽  
Ca 125 ◽  
Resistant Disease ◽  
Platinum Resistant ◽  
Exact Confidence Interval

PURPOSE The aim of the study was to evaluate the activity of vinorelbine (VNLB) in a population of advanced ovarian cancer patients, with particular attention to defining its role in platinum-resistant disease. PATIENTS AND METHODS Thirty-three patients were recruited and treated with VNLB 25 mg/m2 intravenously (IV) weekly. the median age was 53 years, performance status 0 to 2, and number of previous chemotherapy regimens two (range, one to five). Twenty-four patients were platinum-resistant; the remaining nine either were platinum-sensitive (four cases) or had undetermined sensitivity (five cases). RESULTS The mean delivered dose-intensity of VNLB was 67% of the planned level, because 60% of the cycles were delayed due to neutropenia or anemia. Four partial responses (PRs) and one complete response (CR) were observed, for an overall response rate of 15% (95% exact confidence interval, 5.1% to 31.9%). All the responses occurred in the subgroup of 24 platinum-resistant cases, in whom the response rate was 21% (95% exact confidence interval, 7.1% to 42.1%). Seven patients became stabilized on VNLB, and 27% of the cases showed a reduction in serum cancer antigen 125 (CA 125) levels. G3/G4 side effects consisted of neutropenia, anemia, and worsening of preexisting peripheral neuropathy. No treatment-related deaths occurred. CONCLUSION VNLB led to a 21% response rate in the population of heavily pretreated and platinum-resistant ovarian cancer patients. Further studies of VNLB alone or in combination with taxanes are warranted in patients with less pretreatment.

scholarly journals Technical Considerations in the Use of the E-Value

2019 ◽  
Vol 7 (2) ◽  
Author(s):  
Tyler J. VanderWeele ◽  
Peng Ding ◽  
Maya Mathur
Keyword(s):  
Confidence Interval ◽  
Risk Ratio ◽  
Design Sensitivity ◽  
Causal Effects ◽  
Ratio Scale ◽  
Unmeasured Confounder ◽  
Strength Of Association ◽  
Technical Considerations

AbstractThe E-value is defined as the minimum strength of association on the risk ratio scale that an unmeasured confounder would have to have with both the exposure and the outcome, conditional on the measured covariates, to explain away the observed exposure-outcome association. We have elsewhere proposed that the reporting of E-values for estimates and for the limit of the confidence interval closest to the null become routine whenever causal effects are of interest. A number of questions have arisen about the use of E-value including questions concerning the interpretation of the relevant confounding association parameters, the nature of the transformation from the risk ratio scale to the E-value scale, inference for and using E-values, and the relation to Rosenbaum’s notion of design sensitivity. Here we bring these various questions together and provide responses that we hope will assist in the interpretation of E-values and will further encourage their use.

Lee Silverman Voice Treatment (LSVT)-BIG to improve motor function in people with Parkinson’s disease: a systematic review and meta-analysis

2017 ◽  
Vol 32 (5) ◽  
pp. 607-618 ◽  
Author(s):  
Michelle N McDonnell ◽  
Briony Rischbieth ◽  
Tenille T Schammer ◽  
Chantel Seaforth ◽  
Alex J Shaw ◽  
...  
Keyword(s):  
Systematic Review ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Confidence Interval ◽  
Motor Function ◽  
Randomized Trials ◽  
Meta Analysis ◽  
Mean Difference ◽  
Lee Silverman Voice Treatment ◽  
Voice Treatment

Objective: The technique called Lee Silverman Voice Treatment (LSVT)-LOUD has previously been used to improve voice quality in people with Parkinson’s disease. The objective of this study was to assess the effectiveness of an alternate intervention, LSVT-BIG (signifying big movements), to improve functional mobility. Design: Systematic review with meta-analysis of randomized trials. Data sources: Medline, Embase, CINAHL, AgeLine, Scopus and Cochrane Library were searched from inception to September 2017 using multiple search terms related to Parkinson’s disease and LSVT-BIG. Review method: Two researchers searched the literature for studies of the LSVT-BIG intervention of 16 sessions, delivered by a certified instructor over four weeks, to any other intervention. Outcomes related to functional ability were included. Study quality was appraised using the Cochrane Risk of Bias tool. Results: Four studies were included, reporting on three randomized trials of 84 participants with mild Parkinson’s disease. Compared to physiotherapy exercises, or a shorter training protocol, there was a significant improvement in motor function assessed with the Unified Parkinson’s Disease Rating Scale part III (mean difference = −3.20, 95% confidence interval = −5.18 to −1.23) and a trend towards faster Timed Up and Go performance (mean difference = −0.47, 95% confidence interval = −0.99 to 0.06) and 10-metre walk test (mean difference = −0.53, 95% confidence interval = −1.07 to 0.01). Conclusion: Compared to shorter format LSVT-BIG or general exercise, LSVT-BIG was more effective at improving motor function. This provides preliminary, moderate quality evidence that amplitude-oriented training is effective in reducing motor impairments for people with mild Parkinson’s disease.

Sample Size Requirements for Testing and Estimating Coefficient Alpha

2002 ◽  
Vol 27 (4) ◽  
pp. 335-340 ◽  
Author(s):  
Douglas G. Bonett
Keyword(s):  
Confidence Interval ◽  
Sample Size ◽  
Closed Form ◽  
Coefficient Alpha ◽  
Exact Test ◽  
Exact Confidence Interval

An approximate test and confidence interval for coefficient alpha are derived. The approximate test and confidence interval are then used to derive closed-form sample size formulas. The sample size formulas can be used to determine the sample size needed to test coefficient alpha with desired power or to estimate coefficient alpha with desired precision. The sample size formulas closely approximate the sample size requirements for an exact confidence interval or an exact test.

Sign in / Sign up

Export Citation Format

Share Document