Michael C. Robbins

Mean Shift Testing in Correlated Data

Several tests for detecting mean shifts at an unknown time in stationary time series have been proposed, including cumulative sum (CUSUM), Gaussian likelihood ratio (LR), maximum of F(F) and extreme value statistics. This article reviews these tests, connects them with theoretical results, and compares their finite sample performance via simulation. We propose an adjusted CUSUM statistic which is closely related to the LR test and which links all tests. We find that tests based on CUSUMing estimated one‐step‐ahead prediction residuals from a fitted autoregressive moving average perform well in general and that the LR and F tests (which induce substantial computational complexities) offer only a slight increase in power over the adjusted CUSUM test. We also conclude that CUSUM procedures work slightly better when the changepoint time is located near the centre of the data, but the adjusted CUSUM methods are preferable when the changepoint lies closer to the beginning or end of the data record. Finally, an application is presented to demonstrate the importance of the choice of method.

Estimating original assemblage content to adjust for post‐depositional vertical artifact movement

Abstract Frequency curves of a particular class of artifacts, such as pottery, from each stratum assemblage have been used to derive relative chronologies and simultaneously models of cultural change. Such empirical counts do not usually take into account post‐depositional processes affecting archaeological remains. A distinctive type of ceramic, coin molds, from the Iron Age hillfort at the Titelberg in Luxembourg provides the model for presenting a method for estimating original assemblage content per stratum on the basis of the artifact frequency as actually recovered upon excavation.

Changepoint Detection in Climate Time Series with Long-Term Trends

Climate time series often have artificial shifts induced by instrumentation changes, station relocations, observer changes, etc. Climate time series also often exhibit long-term trends. Much of the recent literature has focused on identifying the structural breakpoint time(s) of climate time series—the so-called changepoint problem. Unfortunately, application of rudimentary mean-shift changepoint tests to scenarios with trends oftenleadstotheerroneousconclusionthatameanshiftoccurredneartheseries’center.Thispaperexamines this problem in detail, constructing some simple homogeneity tests for series with trends. The asymptotic distributionoftheproposedstatisticisderived;enroute,anattemptismadetounifytheasymptoticproperties of the changepoint methods used in today’s climate literature. The tests presented here are linked to the ubiquitous t test. Application is made to two temperature records: 1) the continental United States record and 2) a local record from Jacksonville, Illinois.

A Measure of Semantic Category Clustering in Free-Listing Tasks

A measure of semantic category (subset) clustering in free lists is presented that has several advantages over other cluster measures: (1) it is independent of interitem distances; (2) it expresses the degree of clustering of semantic subsets within a list, and overall, as proportions of a maximum that ranges from 0 to 1; and (3) this ratio can be used to compare the degree of clustering within semantic subsets in the same list, overall, and across lists, despite list inequalities in the number of items or subsets. An example of the measures use is illustrated here from a study of laterality in American kinship.

Part one: Problem‐drinking and the integration of alcohol in rural buganda 1

Abstract This paper summarizes the results of an anthropological study of alcohol use in a rural parish in the Buganda region of Uganda designed to examine the hypothesis that when alcohol is well integrated into the sociocultural system its positive social and physiological functions will tend to outweigh its role as a means of assuaging personal psychological problems. It focuses on the differential functions of a well‐integrated, traditional beverage, omwenge, a banana beer, and a more recently developed distillate of it, enguli, which is less integrated. The results of a statistical analysis provide modest support for the hypothesis. Enguli drinkers drink significantly more for personal psychological effects and omwenge drinkers drink significantly more for physiological reasons. No significant difference was found between the two groups in social reasons for drinking.

Statistics for anthropologists

David Hurst Thomas. Figuring Anthropology: First Principles of Probability and Statistics. New York: Holt, Rinehart and Winston, 1976. xi + 532 pp. Tables, figures, appendix, exercises, references, and index.

An Improved Measure of Cognitive Salience in Free Listing Tasks: A Marshallese Example.

13.50.

Fishing for Ideas: Teaching and Learning in a University Ichthyology Course

A new free-list measure of cognitive salience, B′, is presented, which includes both list position and list frequency. It surpasses other extant measures by being normed to vary between a maximum of 1 and a minimum of 0, thereby making it useful for comparisons irrespective of list length or number of respondents. An illustration of its properties, uses, and computation is provided with the aid of examples drawn from free lists of foods elicited from a sample of migrants from the Republic of the Marshall Islands.

Cultural Conservation of Medicinal Plant Use in the Ozarks

Abstract To teach students effectively about fishes, it is important to understand what perceptions they bring to a course and the degree to which these may be resistant to modification. We surveyed junior/senior-level students before and after completing a university ichthyology course to assess how students perceived fish relatedness prior to and following training in phylogenetics. We found that students generally classified fish based on size and sporting/non-sporting attributes prior to our class. After a semester of ichthyological training, these same students clearly embraced the phylogenetic perspective. However, morphological factors such as size, shape, and appearance still had a heavy residual influence on their perceptions.