China
Africa
Explore chapters and articles related to this topic
Trial Designs for Rare Diseases and Small Samples in Oncology
Published in Susan Halabi, Stefan Michiels, Textbook of Clinical Trials in Oncology, 2019
Robert A. Beckman, Cong Chen, Martin Posch, Sarah Zohar
The above design concept can also be varied to use a smaller amount of data from the definitive clinical endpoint to govern pruning at the interim analysis. In this case, typically the type I error threshold must be set higher at interim due to the smaller amount of data accumulated. The bar for passing pruning and the fraction of available definitive endpoint information available at interim are important design parameters in this instance.
Incorporating patient preferences and burden-of-disease in evaluating ALS drug candidate AMX0035: a Bayesian decision analysis perspective
Published in Amyotrophic Lateral Sclerosis and Frontotemporal Degeneration, 2023
Qingyang Xu, Joonhyuk Cho, Zied Ben Chaouch, Andrew W. Lo
The question raised and answered by BDA is ‘Are patient preferences consistent with using a fixed 2.5% significance level threshold for type I error rate?’. For fatal diseases with no existing treatments, patients may be willing to accept a much higher false positive rate, especially if it yields a lower false negative rate or type II error, as is often the case. For example, suppose the conventional 2.5% type I error is associated with a type II error of 25%. A glioblastoma patient who has exhausted the standard of care may accept a type I error of 20% if it is associated with a type II error of 10%. Since such patients have no other recourse, the relative importance of false positives and negatives should reflect their circumstances. On the other hand, diabetes patients may require a much lower type I error threshold of 1.3% (10) as there already are treatments to enhance their quality of life.
Regression models using the LINEX loss to predict lower bounds for the number of points for approximating planar contour shapes
Published in Journal of Applied Statistics, 2022
J. M. Thilini Jayasinghe, Leif Ellingson, Chalani Prematilake
For our specific application, there also remains a considerable amount of work that remains to be done. First, both here and in Prematilake and Ellingson [16], we fixed the error threshold at a set amount, but Prematilake [15] shows that, as expected, the values of the parameters change with different error thresholds. An ideal model would allow for us to incorporate the error threshold directly in the model, but this is considerably more complicated since, even under OLS, residuals will be correlated in the classical regression framework. Developing a model that can incorporate the error threshold into the model directly as a predictor would help make these models more generalizable. Furthermore, in shape analysis, it is not sufficient to simply approximate the shape of a single contour, but rather requires us to approximate all shapes within a sample using the same number of landmarks to ensure that all observations lie in the same mathematical space.
Construct and discriminative validity and reliability of the Selective Control of the Upper Extremity Scale (SCUES) in children with unilateral cerebral palsy
Published in Physiotherapy Theory and Practice, 2022
Ayse Yildiz, Ramazan Yildiz, Halil Ibrahim Celik, Omer Faruk Manzak, Bulent Elbasan
To assess the intrarater reliability, a single rater scored all the videos within a timeframe of 5 weeks. Interrater reliability of the SCUES was evaluated based on the repeated observations by two raters. Relatively high intra- and interrater reliability for the SCUES was found in this study. Our current results are similar to those previously reported (Wagner, Davids, and Hardin, 2016). These results indicate that the scale can be used as a clinically reliable tool. In addition, the SRD values determining the magnitude of change that would exceed the measurement error threshold were calculated to be useful in clinical practice. To our knowledge, this study is the first to report SRD values of the SCUES. The SRD values indicated that a change of equal to or greater than 2.11 points for the intrarater analysis and 1.16 points for interrater analysis would be required to be 95% certain that the change is not due to the measurement error. To evaluate the acceptability and sensitivity of the SRD values, it is more accurate to use SRD% values. Although there are no universally accepted limits for SRD%, Huang et al. (2011) suggested that SRD% score less than 30 is considered acceptable. Considering the SRD% values of the SCUES total score (25.7% for inrarater reliability and 15.1% for interrater reliability), the SRD values are acceptable and sensitive for detecting changes beyond the error threshold. Therefore, clinicians and researchers should consider the SRD values when interpreting changed values of the SCUES total score between different raters and between assessment sessions.