Interim analyses for monitoring clinical trials that do not materially affect the type I error rate

1992 ◽  
Vol 11 (1) ◽  
pp. 55-66 ◽  
Author(s):  
A. Lawrence Gould
Keyword(s):  
Clinical Trials ◽  
Error Rate ◽  
Type I Error ◽  
Type I ◽  
Interim Analyses ◽  
Type I Error Rate

Adaptive designs in multi-reader multi-case clinical trials of imaging devices

2019 ◽  
Vol 29 (6) ◽  
pp. 1592-1611
Author(s):  
Zhipeng Huang ◽  
Frank Samuelson ◽  
Lucas Tcheuko ◽  
Weijie Chen
Keyword(s):  
Clinical Trials ◽  
Error Rate ◽  
Interim Analysis ◽  
Type I Error ◽  
Adaptive Methods ◽  
Type I ◽  
Type I Error Rate ◽  
Power And Control ◽  
Target Power ◽  
And Control

Evaluation of medical imaging devices often involves clinical studies where multiple readers (MR) read images of multiple cases (MC) for a clinical task, which are often called MRMC studies. In addition to sizing patient cases as is required in most clinical trials, MRMC studies also require sizing readers, since both readers and cases contribute to the uncertainty of the estimated diagnostic performance, which is often measured by the area under the ROC curve (AUC). Due to limited prior information, sizing of such a study is often unreliable. It is desired to adaptively resize the study toward a target power after an interim analysis. Although adaptive methods are available in clinical trials where only the patient sample is sized, such methodologies have not been established for MRMC studies. The challenge lies in the fact that there is a correlation structure in MRMC data and the sizing involves both readers and cases. We develop adaptive MRMC design methodologies to enable study resizing. In particular, we resize the study and adjust the critical value for hypothesis testing simultaneously after an interim analysis to achieve a target power and control the type I error rate in comparing AUCs of two modalities. Analytical results have been derived. Simulations show that the type I error rate is controlled close to the nominal level and the power is adjusted toward the target value under a variety of simulation conditions. We demonstrate the use of our methods in a real-world application comparing two imaging modalities for breast cancer detection.

Influence of Selection Bias on the Test Decision

2012 ◽  
Vol 51 (02) ◽  
pp. 138-143 ◽  
Author(s):  
E. Cramer ◽  
L. N. Kennes ◽  
N. Heussen ◽  
M. Tamm
Keyword(s):  
Clinical Trials ◽  
Selection Bias ◽  
Error Rate ◽  
Randomized Clinical Trials ◽  
Type I Error ◽  
Patient Characteristics ◽  
Allocation Concealment ◽  
Type I ◽  
Type I Error Rate ◽  
Block Randomization

SummaryBackground: Selection bias arises in clinical trials by reason of selective assignment of patients to treatment groups. Even in randomized clinical trials with allocation concealment this phenomenon can occur if future assignments can be predicted due to knowledge of former allocations.Objectives: Considering unmasked randomized clinical trials with allocation concealment the impact of selection bias on type I error rate under permuted block randomization is investigated. We aimed to extend the existing research into this topic by including practical assumptions concerning misclassification of patient characteristics to get an estimate of type I error close to clinical routine. To establish an upper bound for the type I error rate different biasing strategies of the investigator are compared first. In addition, the aspect of patient availability is considered.Methods: To evaluate the influence of selection bias on type I error rate under several practical situations, different block sizes, selection effects, biasing strategies and success rates of patient classification were simulated using SAS.Results: Type I error rate exceeds 5 percent significance level; it reaches values up to 21 percent. More cautious biasing strategies and misclassification of patient characteristics may diminish but cannot eliminate selection bias. The number of screened patients is about three times larger than the needed number for the trial.Conclusions: Even in unmasked randomized clinical trials using permuted block randomization with allocation concealment the influence of selection bias must not be disregarded evaluating the test decision. It should be incorporated when designing and reporting a clinical trial.

Correction: “Influence of Selection Bias on the Test Decision – A Simulation Study”

2014 ◽  
Vol 53 (05) ◽  
pp. 343-343
Keyword(s):  
Selection Bias ◽  
Simulation Study ◽  
Error Rate ◽  
Type I Error ◽  
Block Size ◽  
Error Rates ◽  
Type I ◽  
Type I Error Rate ◽  
Representation Error ◽  
Numeric Representation

We have to report marginal changes in the empirical type I error rates for the cut-offs 2/3 and 4/7 of Table 4, Table 5 and Table 6 of the paper “Influence of Selection Bias on the Test Decision – A Simulation Study” by M. Tamm, E. Cramer, L. N. Kennes, N. Heussen (Methods Inf Med 2012; 51: 138 –143). In a small number of cases the kind of representation of numeric values in SAS has resulted in wrong categorization due to a numeric representation error of differences. We corrected the simulation by using the round function of SAS in the calculation process with the same seeds as before. For Table 4 the value for the cut-off 2/3 changes from 0.180323 to 0.153494. For Table 5 the value for the cut-off 4/7 changes from 0.144729 to 0.139626 and the value for the cut-off 2/3 changes from 0.114885 to 0.101773. For Table 6 the value for the cut-off 4/7 changes from 0.125528 to 0.122144 and the value for the cut-off 2/3 changes from 0.099488 to 0.090828. The sentence on p. 141 “E.g. for block size 4 and q = 2/3 the type I error rate is 18% (Table 4).” has to be replaced by “E.g. for block size 4 and q = 2/3 the type I error rate is 15.3% (Table 4).”. There were only minor changes smaller than 0.03. These changes do not affect the interpretation of the results or our recommendations.

Controlling type I error rate for fast track drug development programmes

2003 ◽  
Vol 22 (5) ◽  
pp. 665-675 ◽  
Author(s):  
Weichung J. Shih ◽  
Peter Ouyang ◽  
Hui Quan ◽  
Yong Lin ◽  
Bart Michiels ◽  
...  
Keyword(s):  
Drug Development ◽  
Error Rate ◽  
Fast Track ◽  
Type I Error ◽  
Type I ◽  
Type I Error Rate

Alternative models and randomization techniques for Bayesian response-adaptive randomization with binary outcomes

2021 ◽  
pp. 174077452110101
Author(s):  
Jennifer Proper ◽  
John Connett ◽  
Thomas Murray
Keyword(s):  
Logistic Regression ◽  
Sample Size ◽  
Error Rate ◽  
Adaptive Design ◽  
Type I Error ◽  
Probability Model ◽  
Binary Outcomes ◽  
Type I ◽  
Operating Characteristics ◽  
Type I Error Rate

Background: Bayesian response-adaptive designs, which data adaptively alter the allocation ratio in favor of the better performing treatment, are often criticized for engendering a non-trivial probability of a subject imbalance in favor of the inferior treatment, inflating type I error rate, and increasing sample size requirements. The implementation of these designs using the Thompson sampling methods has generally assumed a simple beta-binomial probability model in the literature; however, the effect of these choices on the resulting design operating characteristics relative to other reasonable alternatives has not been fully examined. Motivated by the Advanced R2 Eperfusion STrategies for Refractory Cardiac Arrest trial, we posit that a logistic probability model coupled with an urn or permuted block randomization method will alleviate some of the practical limitations engendered by the conventional implementation of a two-arm Bayesian response-adaptive design with binary outcomes. In this article, we discuss up to what extent this solution works and when it does not. Methods: A computer simulation study was performed to evaluate the relative merits of a Bayesian response-adaptive design for the Advanced R2 Eperfusion STrategies for Refractory Cardiac Arrest trial using the Thompson sampling methods based on a logistic regression probability model coupled with either an urn or permuted block randomization method that limits deviations from the evolving target allocation ratio. The different implementations of the response-adaptive design were evaluated for type I error rate control across various null response rates and power, among other performance metrics. Results: The logistic regression probability model engenders smaller average sample sizes with similar power, better control over type I error rate, and more favorable treatment arm sample size distributions than the conventional beta-binomial probability model, and designs using the alternative randomization methods have a negligible chance of a sample size imbalance in the wrong direction. Conclusion: Pairing the logistic regression probability model with either of the alternative randomization methods results in a much improved response-adaptive design in regard to important operating characteristics, including type I error rate control and the risk of a sample size imbalance in favor of the inferior treatment.

Anova Tests for Homogeneity of Variance: Nonnormality and Unequal Samples

1977 ◽  
Vol 2 (3) ◽  
pp. 187-206 ◽  
Author(s):  
Charles G. Martin ◽  
Paul A. Games
Keyword(s):  
Error Rate ◽  
Type I Error ◽  
Type I ◽  
Empirical Comparison ◽  
Jackknife Test ◽  
Type I Error Rate ◽  
Power And Control ◽  
Homogeneity Of Variance ◽  
Test Use ◽  
And Control

This paper presents an exposition and an empirical comparison of two potentially useful tests for homogeneity of variance. Control of Type I error rate, P(EI), and power are investigated for three forms of the Box test and for two forms of the jackknife test with equal and unequal n's under conditions of normality and nonnormality. The Box test is shown to be robust to violations of the assumption of normality. The jackknife test is shown not to be robust. When n's are unequal, the problem of heterogeneous within-cell variances of the transformed values and unequal n's affects the jackknife and Box tests. Previously reported suggestions for selecting subsample sizes for the Box test are shown to be inappropriate, producing an inflated P(EI). Two procedures which alleviate this problem are presented for the Box test. Use of the jack-knife test with a reduced alpha is shown to provide power and control of P(EI) at approximately the same level as the Box test. Recommendations for the use of these techniques and computational examples of each are provided.

Sign in / Sign up

Export Citation Format

Share Document