Results 241 to 250 of about 2,029,039 (288)

Location, location, location – Considering local neighborhood when analyzing large samples of UK catchments

2021
<p>Studying large samples of catchments has been an effective means for comparative hydrology as it provides a wide range of hydrological conditions which can be used to learn similarities and differences between places. Such analyses typically include an attempt to organize 
Melike Kiraz, Thorsten Wagener, Gemma Coxon   +2 more
openaire   +1 more source

Sampling Hard-to-Locate Populations

2017
This chapter discusses the challenges that researchers face when conducting surveys on hard-to-survey populations. It begins with an overview of the various conditions that can make it difficult to include some populations in studies or surveys. This includes the population’s being hard to identify and locate or hard to persuade or interview and even ...
Prakash Adhikari, Lisa A. Bryant
openaire   +1 more source

Two samples differing in location

1989
In this chapter we’ll develop the mathematical foundation and the asymptotic properties of suitable rank tests with estimated scores for the two-sample problem. We restrict the discussion to the two-sample model in order to present the basic ideas in the simplest form. The corresponding k -sample model will be treated in Section 4.2.
Konrad Behnen, Georg Neuhaus
openaire   +1 more source

Several-sample location problem

2010
In this chapter we consider tests and estimates based on identity, spatial sign, and spatial rank scores in the several independent samples setting. We get multivariate extensions of the Moods test, Wilcoxon-Mann-Whitney test, Kruskal- Wallis test and the two samples Hodges-Lehmann estimator.
openaire   +1 more source

Location-Shifts in Sampling with Unequal Probabilities

Journal of the Royal Statistical Society. Series A (General), 1986
The author studies the well-known problem of variance minimization in sampling for population mean estimation from a rather uncommon point of view. He shows that in sampling with unequal probabilities a location- shift of the variable of interest may cause variance reduction both in sampling with and without replacement (the latter case with a bit more
openaire   +1 more source

Infill sampling criteria to locate extremes

Mathematical Geology, 1995
Three problem-dependent meanings for engineering “extremes” are motivated, established, and translated into formal geostatistical (model-based) criteria for designing infill sample networks. (1) Locate an area within the domain of interest where a specified threshold is exceeded, if such areas exist.
Alan G. Watson, Randal J. Barnes
openaire   +1 more source

Estimation of location difference for fragmentary samples

Biometrika, 1981
Abstract : A class of simple and robust estimators of the difference between location parameters of correlated variables is proposed when some observations on either of the variables are missing. We show that these estimators are consistent, asymptotically normally distributed, and insensitive to outlying observations.
openaire   +1 more source

A two-sample test for location

Communications in Statistics - Theory and Methods, 1988
A new test that is based on U-statistics is oroposed for the two-sample local, on problem. This test is sensitive to heavy-tailed distributions.
I.D. Shelty, Z. Govindarajulu
openaire   +1 more source

Location estimates for single samples

1989
In Chapters 2 to 7 we consider data that are either measurements or ranks specifying order of magnitude or preference. The latter are called ordinal data. Chapters 2 and 3 are devoted to single samples. Most practical problems involve comparison of, or studying relations between, several samples, but many basic nonparametric notions are applicable also
openaire   +1 more source

Choosing a Two-Sample Location Test

The Journal of Experimental Education, 1994
Abstract Type I error rate and power for the t test, Wilcoxon-Mann-Whitney (U) test, van der Waerden Normal Scores (NS) test, and Welch-Aspin-Satterthwaite (W) test were compared for two independent random samples drawn from nonnormal distributions. Data with varying degrees of skewness (S) and kurtosis (K) were generated using Fleishman's (1978) power
openaire   +1 more source