Gary W. Oehlert

A Note on the Delta Method

Abstract The delta method is an intuitive technique for approximating the moments of functions of random variables. This note reviews the delta method and conditions under which delta-method approximate moments are accurate.

Influence of Ecological and Social Factors on Body Mass of Wild Chimpanzees

The chimpanzees (Pan troglodytes schweinfurthii) of Gombe National Park, Tanzania, were weighed regularly over a period of 33 yr, resulting in 1286 measurements on 31 males and 26 females aged 2–43 yr. Female growth slowed at 10 yr and that of males at 13 yr. Median adult body mass is 39 kg for males and 31.3 kg for females. Body mass varied between years. Chimpanzees were heaviest during a period of frequent banana provisioning. They were also heavier when community range size was large and population density within the range was low. Chimpanzees were heavier in the wet than in the dry season and body mass tracked rainfall in the preceding mo except for May in which mass was anomalously low. Dominance rank is significantly correlated with body mass for females but not males. High-ranking individuals tended to maintain more stable mass. Variability in body mass was greater for young and old individuals than for prime adults.

Factors affecting the emulsifying and rheological properties of gum acacia in beverage emulsions

Abstract Gum acacia, a natural hydrocolloid, is extensively used as an emulsifier/stabilizer in beverage emulsions. Factors that may affect emulsion formation, emulsion stability and viscosity of the emulsion concentrate were studied to assess their significance, including proximal composition of the gum (protein content and mineral content), gum processing prior to emulsion preparation (pasteurization and demineralization), and pH of the dilute emulsion. Protein content was not related to emulsion stability, whereas minerals decreased stability presumably due to an electrostatic screening effect. Both pasteurization and demineralization favored stability, most likely by promoting protein unfolding and eliminating the screening effect, respectively. Emulsions were less stable at pH=2.5 than at higher pH levels (4.5 and 5.5). There was a significant difference between the two gum species studied (Senegal and Seyal) in their sensitivity to these treatments. The viscosity of the emulsion concentrate was decreased by pasteurization and increased by demineralization. Protein load at the O/W interface and thickness of the adsorbed layer of emulsifier were not related to emulsion stability. The most important colloidal interactions in dilute beverage emulsions are van der Waals, electrostatic and polymeric steric.

Regional Trends in Sulfate Wet Deposition

Abstract I propose a multiple time series model for data from a network of monitoring stations that have both temporal and spatial correlation. The model includes a separate mean and trend for each monitoring station and obtains spatial estimates of mean and trend by smoothing the observed values over a rectangular grid using a discrete smoothing prior. Smoothing parameters and covariance estimates can be chosen subjectively or selected using indirect generalized cross-validation. The gridded values and their standard errors can be used for several purposes, including inference on regional means or trends and improving monitoring networks via station rearrangement.

Clinical feature profile of spinocerebellar ataxia type 1-8 predicts genetically defined subtypes

An increasing number of genetically defined types of spinocerebellar ataxia (SCA) have been reported in the past decade. Phenotype–genotype correlation studies have suggested a broad overlap between SCA types. The aim of the present study was to identify patterns of clinical features that were likely to distinguish between SCA types and to test the specificity and sensitivity of these signs and symptoms using a Bayesian classifier. In total, 127 patients from 50 families with SCA types 1 to 8 were examined using a worksheet with a panel of 33 symptoms and signs. By computing the probabilities of each trait for each SCA type, we rated the predictive value of each feature for each form of ataxia and then combined the probabilities for the entire panel of traits to construct a Bayesian classifier. Results of this analysis were summarized in a simpler, more operator‐based algorithm. Patients with SCA5, SCA6, and SCA8 demonstrated a predominant cerebellar syndrome, whereas patients with SCA1, SCA2, SCA3, SCA4, and SCA7 frequently had clinical features indicating an extracerebellar involvement. The Bayesian classifier predicted the SCA type in 78% of patients with sensitivities between 60 and 100% and specificities between 94 and 98.2%. The highest sensitivity to correctly predict the true SCA type was found for SCA5, SCA7, and SCA8. Sensitivities and specificities found in the present study validate the use of algorithms to help to prioritize specific SCA gene testing, which will help to reduce costs for gene testing.

Influence of time–temperature treatments on the emulsifying properties of gum acacia in beverage emulsions

Abstract Response surface was used to evaluate the significance of time–temperature treatments on gum acacia solutions with respect to the stability of gum acacia-based dilute beverage emulsions. Treatments ranked from a minimum of pasteurization (30 min at 62.5°C) to a maximum just before inducing protein precipitation from the gum (90 min at 100°C). Heat treatment improved emulsion stability to a greater extent in Acacia seyal than Acacia senegal samples, with optimum values around 80°C and 60 min for both species. Response surface was statistically significant in Seyal but not in Senegal.

An Analysis of the Influence of Annual Thermal Variables on the Occurrence of Fifteen Warmwater Fishes

Abstract Multisource fish-sampling data and U.S. Geological Survey temperature data from streams throughout the United States were used to investigate the influence of derived thermal regime variables on the presence or absence of 15 common warmwater fish species. The 3-year average annual thermal regime was calculated for streams where presence or absence was known for these 15 species. Six variables estimated to be of biological importance to the winter and summer survival and recruitment of a species, including measures of feeding and nonfeeding periods, were calculated from these thermal regimes. Stepwise discriminant analysis and multiple regression were used to select optimal variables for creating multivariate models. Parametric and nonparametric multivariate discriminant analyses were then performed to test our ability to correctly classify presence or absence using the thermal variables. These statistical empirical models were able to correctly predict presence or absence with greater than 90% ac...

Shrinking a wet deposition network

Abstract Suppose that we must delete stations from a monitoring network. Which stations should be deleted if we wish the remaining network to have the smallest possible trend estimate variances? We use the spatial-temporal model described in Oehlert (1993, J. Am. Statist. Assoc., 88, 390–399), to model concentration of sulfate in wet deposition. Based on this model and three criteria, we choose good sets of candidate stations for deletion from the NADP/NTN network. We use the criteria: that the sum of 11 regional trend estimate variances be as small as possible, that the sum of local trend estimation variance be as small as possible, and that the sum of local mean estimation variance be as small as possible. Good choices of stations for deletion result in a modest increase in criteria (about 7 to 34%) for 100 stations deleted from the network, while random sets of 100 stations can increase criteria by a factor of two or more.

RED-SHOULDERED HAWK NEST SITE SELECTION IN NORTH-CENTRAL MINNESOTA

Abstract We evaluated characteristics at Red-shouldered Hawk (Buteo lineatus) nest sites at two study areas with different topography and forest types in north-central and central Minnesota to identify nest site commonalities across geographically distinct areas. During the breeding seasons of 1994–1995, we located nests of Red-shouldered Hawks at the Camp Ripley Army National Guard Training Site and the Chippewa National Forest using a combination of broadcast surveys, helicopter searches, and systematic foot searches. All 38 nests at Camp Ripley and 18 nests in the Chippewa National Forest were in upland hardwood stands; the remaining two nests in the Chippewa National Forest were in aspen (Populus spp.) stands. We aged cores from 19 nest trees at Camp Ripley and measured habitat characteristics in a 0.04 ha circle centered on each nest tree and at a paired random site within the nest stand. We compared habitat variables at nest and random sites to identify habitat characteristics that were consistent predictors of nest sites versus random sites for each study area and for all nests combined. Compared to random sites, nest sites in the Chippewa National Forest had larger diameters at breast height (dbh) of the nest tree, taller nest tree height, and higher canopy height. At Camp Ripley, nest sites differed from random sites with regard to many more variables; nests were located in portions of the stand with larger trees and closer to surface water. Nest trees ranged in age from 50–89 years. Logistic regression models indicated that, for both study areas combined, nest tree dbh, basal area, canopy height, and distance to water were the most important variables in distinguishing nest sites from random sites.

Long-term trends in NADP/NTN precipitation chemistry data: Results of different statistical analyses

This paper summarizes the results of four statistical approaches for the estimation of long-term trends (1983–92) in sulfate concentration data from 90 monitoring sites across the United States. Least squares regression models and nonparametric techniques were applied to these data. Sulfate concentrations were found to be generally decreasing on the order of 0–4% at most sites. There was general agreement that trends were significant in the Great Lakes, Pacific northwest, and southwest regions. Although strengths and weaknesses are described for each approach, all of these approaches are useful for long-term trend estimation. Visualization techniques are recommended for displaying trend patterns and associated levels of statistical significance.