A note on familywise error rate for a primary and secondary endpoint

Hung et al. (2007) considered the problem of controlling the type I error rate for a primary and secondary endpoint in a clinical trial using a gatekeeping approach in which the secondary endpoint is tested only if the primary endpoint crosses its monitoring boundary. They considered a two-look trial and showed by simulation that the naive method of testing the secondary endpoint at full level α at the time the primary endpoint reaches statistical significance does not control the familywise error rate at level α. Tamhane et al. (2010) derived analytic expressions for familywise error rate and power and confirmed the inflated error rate of the naive approach. Nonetheless, many people mistakenly believe that the closure principle can be used to prove that the naive procedure controls the familywise error rate. The purpose of this note is to explain in greater detail why there is a problem with the naive approach and show that the degree of alpha inflation can be as high as that of unadjusted monitoring of a single endpoint.     

Cost analysis in choosing group size when group testing for Potato virus Y in the presence of classification errors

In many areas of the world, Potato virus Y (PVY) is one of the most economically important disease problems in seed potatoes. In Taiwan, generation 2 (G2) class certified seed potatoes are required by law to be free of detectable levels of PVY. To meet this standard, it is necessary to perform accurate tests at a reasonable cost. We used a two‐stage testing design involving group testing which was performed in Taiwan's Seed Improvement and Propagation Station to identify plants infected with PVY. At the first stage of this two‐stage testing design, plants are tested in groups. The second stage involves no retesting for negative test groups and exhaustive testing of all constituent individual samples from positive test groups. In order to minimise costs while meeting government standards, it is imperative to estimate optimal group size. However, because of limited test accuracy, classification errors for diagnostic tests are inevitable; to get a more accurate estimate, it is necessary to adjust for these errors. Therefore, this paper describes an analysis of diagnostic test data in which specimens are grouped for batched testing to offset costs. The optimal batch size is determined by various cost parameters as well as test sensitivity, specificity and disease prevalence. Here, the Bayesian method is employed to deal with uncertainty in these parameters. Moreover, we developed a computer program to determine optimal group size for PVY tests such that the expected cost is minimised even when using imperfect diagnostic tests of pooled samples. Results from this research show that, compared with error free testing, when the presence of diagnostic testing errors is taken into account, the optimal group size becomes smaller. Higher diagnostic testing costs, lower costs of false negatives or smaller prevalence can all lead to a larger optimal group size. Regarding the effects of sensitivity and specificity, optimal group size increases as sensitivity increases; however, specificity has little effect on determining optimal group size. From our simulated study, it is apparent that the Bayesian method can truly update the prior information to more closely approximate the intrinsic characteristics of the parameters of interest. We believe that the results of this study will be useful in the implementation of seed potato certification programmes, particularly those which require zero tolerance for quarantine diseases in certified tubers.     

Mid‐P confidence intervals for group testing based on the total number of positive groups

In the estimation of proportions by group testing, unequal sized groups results in an ambiguous ordering of the sample space, which complicates the construction of exact confidence intervals. The total number of positive groups is shown to be a suitable statistic for ordering outcomes, provided its ties are broken by the MLE. We propose an interval estimation method based on this quantity, with a mid‐P correction. Coverage is evaluated using group testing problems in plant disease assessment and virus transmission by insect vectors. The proposed method provides good coverage in a range of situations, and compares favorably with existing exact methods.     

Approval policies for modifications to machine learning‐based software as a medical device: A study of bio‐creep

Successful deployment of machine learning algorithms in healthcare requires careful assessments of their performance and safety. To date, the FDA approves locked algorithms prior to marketing and requires future updates to undergo separate premarket reviews. However, this negates a key feature of machine learning—the ability to learn from a growing dataset and improve over time. This paper frames the design of an approval policy, which we refer to as an automatic algorithmic change protocol (aACP), as an online hypothesis testing problem. As this process has obvious analogy with noninferiority testing of new drugs, we investigate how repeated testing and adoption of modifications might lead to gradual deterioration in prediction accuracy, also known as “biocreep” in the drug development literature. We consider simple policies that one might consider but do not necessarily offer any error‐rate guarantees, as well as policies that do provide error‐rate control. For the latter, we define two online error‐rates appropriate for this context: bad approval count (BAC) and bad approval and benchmark ratios (BABR). We control these rates in the simple setting of a constant population and data source using policies aACP‐BAC and aACP‐BABR, which combine alpha‐investing, group‐sequential, and gate‐keeping methods. In simulation studies, bio‐creep regularly occurred when using policies with no error‐rate guarantees, whereas aACP‐BAC and aACP‐BABR controlled the rate of bio‐creep without substantially impacting our ability to approve beneficial modifications.