Dataset Information

Robustness of statistical methods when measure is affected by ceiling and/or floor effect.

ABSTRACT:

Goals and methods

A simulation study investigated how ceiling and floor effect (CFE) affect the performance of Welch's t-test, F-test, Mann-Whitney test, Kruskal-Wallis test, Scheirer-Ray-Hare-test, trimmed t-test, Bayesian t-test, and the "two one-sided tests" equivalence testing procedure. The effect of CFE on the estimate of group difference and on its confidence interval, and on Cohen's d and on its confidence interval was also evaluated. In addition, the parametric methods were applied to data transformed with log or logit function and the performance was evaluated. The notion of essential maximum from abstract measurement theory is used to formally define CFE and the principle of maximum entropy was used to derive probability distributions with essential maximum/minimum. These distributions allow the manipulation of the magnitude of CFE through a parameter. Beta, Gamma, Beta prime and Beta-binomial distributions were obtained in this way with the CFE parameter corresponding to the logarithm of the geometric mean. Wald distribution and ordered logistic regression were also included in the study due to their measure-theoretic connection to CFE, even though these models lack essential minimum/maximum. Performance in two-group, three-group and 2 × 2 factor design scenarios was investigated by fixing the group differences in terms of CFE parameter and by adjusting the base level of CFE.

Results and conclusions

In general, bias and uncertainty increased with CFE. Most problematic were occasional instances of biased inference which became more certain and more biased as the magnitude of CFE increased. The bias affected the estimate of group difference, the estimate of Cohen's d and the decisions of the equivalence testing methods. Statistical methods worked best with transformed data, albeit this depended on the match between the choice of transformation and the type of CFE. Log transform worked well with Gamma and Beta prime distribution while logit transform worked well with Beta distribution. Rank-based tests showed best performance with discrete data, but it was demonstrated that even there a model derived with measurement-theoretic principles may show superior performance. Trimmed t-test showed poor performance. In the factor design, CFE prevented the detection of main effects as well as the detection of interaction. Irrespective of CFE, F-test misidentified main effects and interactions on multiple occasions. Five different constellations of main effect and interactions were investigated for each probability distribution, and weaknesses of each statistical method were identified and reported. As part of the discussion, the use of generalized linear models based on abstract measurement theory is recommended to counter CFE. Furthermore, the necessity of measure validation/calibration studies to obtain the necessary knowledge of CFE to design and select an appropriate statistical tool, is stressed.

SUBMITTER: Simkovic M

PROVIDER: S-EPMC6699673 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Chemically active particles achieve motility without external forces and torques ("self-propulsion") due to catalytic chemical reactions at their surfaces, which change the chemical composition of the surrounding solution (called "chemical field") and induce hydrodynamic flow of the solution. By coupling the distortions of these fields back to its motion, a chemically active particle experiences an effective interaction with confining surfaces. This coupling can lead to a rich behavior, such as the occurrence of wall-bound steady states of "sliding". Most active particles are density mismatched with the solution and, thus, tend to sediment. Moreover, the often employed Janus spheres, which consist of an inert core material decorated with a cap-like, thin layer of a catalyst, are gyrotactic (i.e., "bottom-heavy"). Whether or not they may exhibit sliding states at horizontal walls depends on the interplay between the active motion and the gravity-driven sedimentation and alignment, such as the gyrotactic tendency to align the axis along the gravity direction being overcome by a competing, activity-driven alignment with a different orientation. It is therefore important to understand and quantify the influence of these gravity-induced effects on the behavior of model chemically active particles moving in the vicinity of walls. For model gyrotactic, self-phoretic Janus particles, here we study theoretically the occurrence of sliding states at horizontal planar walls that are either below ("floor") or above ("ceiling") the particle. We construct "state diagrams" characterizing the occurrence of such states as a function of the sedimentation velocity and of the gyrotactic response of the particle, as well as of the phoretic mobility of the particle. We show that in certain cases sliding states may emerge simultaneously at both the ceiling and the floor, while the larger part of the experimentally relevant parameter space corresponds to particles that would exhibit sliding states only either at the floor or at the ceiling-or there are no sliding states at all. These predictions are critically compared with the results of previous experimental studies, as well as with our dedicated experiments carried out with Pt-coated, polystyrene-core, or silica-core Janus spheres immersed in aqueous hydrogen peroxide solutions.

Project description:Beta-lactam antibiotics exhibit high interindividual variability in drug concentrations in patients with critical illness which led to an interest in the use of therapeutic drug monitoring to improve effectiveness and safety. To implement therapeutic drug monitoring, it is necessary to define the beta-lactam therapeutic range-in essence, what drug concentration would prompt a clinician to make dose adjustments up or down. This objective of this narrative review was to summarize evidence for the "floor" (for effectiveness) and "ceiling" (for toxicity) for the beta-lactam therapeutic range to be used with individualized therapeutic drug monitoring.Data sourcesResearch articles were sourced from PubMed using search term combinations of "pharmacokinetics," "pharmacodynamics," "toxicity," "neurotoxicity," "therapeutic drug monitoring," "beta-lactam," "cefepime," "meropenem," "piperacillin/tazobactam," "ICU," and "critical illness."Study selectionArticles were selected if they included preclinical, translational, or clinical data on pharmacokinetic and pharmacodynamic thresholds for effectiveness and safety for beta-lactams in critical illness.Data synthesisExperimental data indicate a beta-lactam concentration above the minimum inhibitory concentration of the organism for greater than or equal to 40-60% of the dosing interval is needed, but clinical data indicate that higher concentrations may be preferrable. In the first 48 hours of critical illness, a free beta-lactam concentration at or above the susceptibility breakpoint of the most likely pathogen for 100% of the dosing interval would be reasonable (typically based on Pseudomonas aeruginosa). After 48 hours, the lowest acceptable concentration could be tailored to 1-2× the observed minimum inhibitory concentration of the organism for 100% of the dosing interval (often a more susceptible organism). Neurotoxicity is the primary dose-dependent adverse effect of beta-lactams, but the evidence remains insufficient to link a specific drug concentration to greater risk.ConclusionsAs studies advance the understanding of beta-lactam exposure and response in critically ill patients, it is essential to clearly define the acceptable therapeutic range to guide regimen selection and adjustment.

Project description:BackgroundThe European Organization for Research and Treatment of Cancer (EORTC) Quality of Life Questionnaire Core 30 Physical Functioning subscale is a widely used patient-reported outcome measure that quantifies cancer patients' physical functioning. Strong floor/ceiling effects can affect a scale's sensitivity to change. The aim of this study was to characterize floor/ceiling effects of the physical functioning domain in patients with advanced/metastatic breast cancer enrolled in commercial clinical trials and a community-based trial.MethodsThe clinical trial cohort comprised patients from 5 registrational trials submitted to the Food and Drug Administration for review (2010-2017). The community cohort comprised a subgroup of patients from the Alliance Patient Reported Outcomes to Enhance Cancer Treatment (PRO-TECT) trial. The distribution of patient responses to Physical Functioning items and the summed score were assessed at the baseline and 3-month follow-up for both cohorts. Descriptive statistics were used to determine floor/ceiling effects at the item and scale levels.ResultsThe clinical trial cohort and the community cohort consisted of 2407 and 178 patients, respectively. Twenty-four percent or more of the respondents reported "not at all" for having trouble/needing help with each Physical Functioning item across both cohorts and measurement time points. Fourteen to twenty percent of the patients scored perfectly (100 of 100) on the Physical Functioning subscale summary measure (where higher scores indicated better physical functioning) across both cohorts and time points.ConclusionsMinor floor effects and notable ceiling effects were found at the item and scale levels of the Physical Functioning subscale, regardless of cohort, and this creates some uncertainty about its ability to detect changes in physical functioning among high-functioning patients. Investigators may consider adding additional high-functioning items from the EORTC's item library to more accurately describe the impact of anticancer treatment on patients' physical functioning.

Dataset Information

Robustness of statistical methods when measure is affected by ceiling and/or floor effect.

Goals and methods

Results and conclusions

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets