Advantages of the Closed Testing Method in Multiple Comparisons Procedures

Improving walking speed reduces hospitalization costs in outpatients with cardiovascular disease. An analysis based on a multistrata non-parametric test

BACKGROUND

To assess the association between walking speed (WS) and its improvement on hospitalization rates and costs in outpatients with cardiovascular disease.

METHODS

Six hundred forty-nine patients participating in an exercise-based secondary prevention program were studied. Patients were divided at baseline into two groups characterized by low and high WS based on the average WS maintained during a moderate 1-km treadmill-walking test. WS and other covariates were grouped into three domains (demographic factors, medical history and risk factors), and used to estimate a propensity score, in order to create homogeneous groups of patients. All-cause hospitalization was assessed 3 years after baseline as a function of WS. Hospitalization and related costs were also assessed during the fourth-to-sixth years after enrollment. To test whether the hospitalization costs were related to changes in WS after 36 months, a multistrata permutation test was performed by combining within strata partial tests.

RESULTS

The results support the hypothesis that hospitalization costs are significantly reduced in accordance with an improvement in WS. This effect is most evident among older patients, overweight or obese, smokers, and those without a history of coronary artery bypass surgery.

CONCLUSIONS

The present study supports growing evidence of an inverse association between WS, risk of hospitalization and consequent health-care costs. The joint use of propensity score and multistrata permutation approaches represent a flexible and robust testing method which avoids the possible effects of several confounding factors typical of these studies.

An Assay System to Evaluate Riboflavin/UV-A Corneal Phototherapy Efficacy in a Porcine Corneal Organ Culture Model

Simple summary

The scope of this study is to quantitatively evaluate, with an automated digital image analysis method, the efficacy of riboflavin/UV-A corneal phototherapy on the cornea in a porcine corneal organ culture model of ulcerative melting keratitis. Riboflavin/UV-A corneal phototherapy provided a favorable outcome in the corneal wound healing process after chemical injury: the treatment restores the damaged corneas to the texture of healthy corneas. This automated image analysis method may be compared to clinical diagnostic methods, such as optical coherence tomography (OCT) imaging, for in vivo damaged ocular structural investigations. Positive results from this research could provide an opportunity for studying the effects of this method in other economically and emotionally valued species, such as dogs, cats, and horses. The relatively overall low treatment cost and the ease of performing the procedure make riboflavin/UV-A corneal phototherapy accessible to the veterinary market.

Abstract

The purpose of this study was to investigate the response of porcine corneal organ cultures to riboflavin/UV-A phototherapy in the injury healing of induced lesions. A porcine corneal organ culture model was established. Corneal alterations in the stroma were evaluated using an assay system, based on an automated image analysis method able to (i) localize the holes and gaps within the stroma and (ii) measure the brightness values in these patches. The analysis has been performed by dividing the corneal section in 24 regions of interest (ROIs) and integrating the data analysis with a “multi-aspect approach.” Three group of corneas were analyzed: healthy, injured, and injured-and-treated. Our study revealed a significant effect of the riboflavin/UV-A phototherapy in the injury healing of porcine corneas after induced lesions. The injured corneas had significant differences of brightness values in comparison to treated (p < 0.00) and healthy (p < 0.001) corneas, whereas the treated and healthy corneas showed no significant difference (p = 0.995). Riboflavin/UV-A phototherapy shows a significant effect in restoring the brightness values of damaged corneas to the values of healthy corneas, suggesting treatment restores the injury healing of corneas after lesions. Our assay system may be compared to clinical diagnostic methods, such as optical coherence tomography (OCT) imaging, for in vivo damaged ocular structure investigations.

Testing and ranking on round-robin design for data sport analytics with application to basketball

By modelling results of sport matches as a set of paired fixed effect linear models, the goal of the present article is showing that traditional scoring outputs can be used to do inference on parameters related to the net relative strength or weakness of teams within a league. As hypothesis testing method, we propose either a normal-based and a non-parametric permutation-based approach. As an extension to round-robin of the ranking methodology recently proposed by Arboretti Giancristofaro et al. (2014) and Corain et al. (2016) , results of pairwise testing are then exploited to provide a ranking of teams within a league. Through an extensive Monte Carlo simulation study, we investigated the properties of the proposed testing and ranking methodology where we proved its validity under different random distributions. In its simplest univariate version, the proposed methodology allows us to infer on the teams average net scoring within a league, while in its more intriguing multivariate layout it is suitable for looking for any team-related global dominance using a wide set of performance indicators. Finally, by using traditional basketball box scores, we present an application to the Italian Basket League.

Iterated combination-based paired permutation tests to determine shape effects of chemotherapy in patients with esophageal cancer

The nonparametric combination of dependent permutation tests method is a useful general tool when a testing problem can be broken down into a set of different k > 1 partial tests. These partial tests, after adjustment of p-values to control for multiplicity, can be marginally analyzed, but jointly considered they can provide information on an overall hypothesis, which might represent the true goal of the testing problem. On the one hand, independence among the partial tests is usually an unrealistic assumption; on the other, even when the underlying dependence relations are known quite often they are difficult to cope with properly. Therefore this combination must be achieved nonparametrically, by implicitly taking into account the dependence structure of tests without explicitly describing it. An important property of the tests based on nonparametric combination methodology, when the number of response variables is high compared to the sample sizes, consists in the finite sample consistency. A practical problem involves choosing the most suitable combining function for each specific testing problem given that the final result can be affected by this crucial choice. The purpose of this article is to present an nonparametric combination solution based on the iterated combination of partial tests, evaluate its power behavior using a Monte Carlo simulation study and apply it to a real medical problem, namely the evaluation of the effects of chemotherapy on the shape of esophageal tumors. R code has been implemented to carry out the analyses.