Search results for "hypothesis"
showing 10 items of 426 documents
Testing for local structure in spatiotemporal point pattern data
2017
The detection of clustering structure in a point pattern is one of the main focuses of attention in spatiotemporal data mining. Indeed, statistical tools for clustering detection and identification of individual events belonging to clusters are welcome in epidemiology and seismology. Local second-order characteristics provide information on how an event relates to nearby events. In this work, we extend local indicators of spatial association (known as LISA functions) to the spatiotemporal context (which will be then called LISTA functions). These functions are then used to build local tests of clustering to analyse differences in local spatiotemporal structures. We present a simulation stud…
Bayesian Design of “Successful” Replications
2002
Replication of experiments is commonin applied research. However, systematic studies of the goals and motivations of a “replication” are rare. As a consequence, there does not seem to be a precise notion of what a “success” when replicating means. This article discusses some of the possible goals for replication; this leads to different (but precise) notions of “success” when replicating. Bayesian hierarchical models allow for a flexible and explicit incorporation of the assumed relationship among the experiments. Bayesian predictive distributions are a natural tool to compute the probability of the replication being successful, and hence to design the replication so that the probability of…
Segmented relationships to model erosion of regression effect in Cox regression
2010
In this article we propose a parsimonious parameterisation to model the so-called erosion of the covariate effect in the Cox model, namely a covariate effect approaching to zero as the follow-up time increases. The proposed parameterisation is based on the segmented relationship where proper constraints are set to accomodate for the erosion. Relevant hypothesis testing is discussed. The approach is illustrated on two historical datasets in the survival analysis literature, and some simulation studies are presented to show how the proposed framework leads to a test for a global effect with good power as compared with alternative procedures. Finally, possible generalisations are also present…
Bayesian measures of surprise for outlier detection
2003
From a Bayesian point of view, testing whether an observation is an outlier is usually reduced to a testing problem concerning a parameter of a contaminating distribution. This requires elicitation of both (i) the contaminating distribution that generates the outlier and (ii) prior distributions on its parameters. However, very little information is typically available about how the possible outlier could have been generated. Thus easy, preliminary checks in which these assessments can often be avoided may prove useful. Several such measures of surprise are derived for outlier detection in normal models. Results are applied to several examples. Default Bayes factors, where the contaminating…
Basing the Analysis of Comparative Bioavailability Trials on an Individualized Statistical Definition of Equivalence
1993
The conventional definition of bioequivalence in terms of population means only, is criticized for lacking relevance to the individual subject. Both approaches to bioequivalence assessment proposed here for avoiding this shortcoming, focus on the probability of an event induced by the response of a randomly selected subject to two formulations of a given active agent. The first approach leads to converting the basic idea underlying the well-known 75-rule into an exact statistical procedure. The second approach is of a parametric nature. It reduces bioequivalence assessment to testing against the alternative hypothesis that the standardized expected value of a Gaussian distribution is contai…
On powerful exact nonrandomized tests for the Poisson two-sample setting.
2020
In the case of two independent samples from Poisson distributions, the natural target parameter for hypothesis testing is the ratio of the two population means. The conditional tests which have been derived for this class of problems already in the 1940s are well known to be optimal in terms of power only when randomized decisions between hypotheses are admitted at the boundary of the respective rejection regions. The major objective of this contribution is to show how the approach used by Boschloo in 1970 for constructing a powerful nonrandomized version of Fisher’s exact test for hypotheses about the odds ratio between two binomial parameters can successfully be adapted for the Poisson c…
A multi-scale approach for testing and detecting peaks in time series
2020
An approach is presented that combines a statistical test for peak detection with the estimation of peak positions in time series. Motivated by empirical observations in neuronal recordings, we aim at investigating peaks of different heights and widths. We use a moving window approach to compare the differences of estimated slope coefficients of local regression models. We combine multiple windows and use the global maximum of all different processes as a test statistic. After rejection, a multiple filter algorithm combines peak positions estimated from multiple windows. Analysing neuronal activity recorded in anaesthetized mice, the procedure could identify significant differences between …
Assessing local differences between the spatio-temporal second-order structure of two point patterns occurring on the same linear network
2021
Abstract We introduce Local Indicators of Spatio-Temporal Association (LISTA) functions on linear networks and use them to build a statistical test for local second-order structure. This allows to identify differences in the spatio-temporal clustering behaviour of two point patterns, a point pattern of interest and a background one, both occurring on the same linear network. We assess the performance of the testing procedure for local second-order structure through simulation studies under a variety of scenarios that also account for different generating point processes. We show that the proposed local test is able to correctly identify the spatio-temporal difference in the local second-ord…
Residuenanalyse des Unabhängigkeitsmodells Zweier Kategorialer Variablen
1985
For the ‘cellwise’ analysis of independence of two categorial variables, Haberman (1973) proposes the method of ‘adjusted residuals’. Fuchs and Kenett (1980) use (the absolute value of) the maximal adjusted residual as a measure for the deviation from the null hypothesis.
Riemann-Type Definition of the Improper Integrals
2004
Riemann-type definitions of the Riemann improper integral and of the Lebesgue improper integral are obtained from McShane's definition of the Lebesgue integral by imposing a Kurzweil-Henstock's condition on McShane's partitions.