|
1. |
Bayesian Faces via Hierarchical Template Modeling |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1151-1163
D.B. Phillips,
A.F. M. Smith,
Preview
|
PDF (5482KB)
|
|
摘要:
We consider the problem of directly extracting high-level shape information from images of scenes involving faces. The approach adopted owes much to the work of Grenander and colleagues at Brown University on pattern analysis and involves designing stochastic deformable templates for objects in the underlying image scenes. A wide range of realistic object poses can be captured by imposing a prior probability distribution over the space of allowable deformations. We show how hierarchical models can be used to organize the prior information into a coherent structure. Markov chain Monte Carlo methods are exploited to recover the deformation given observed image data.
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476855
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
2. |
A Space-Time Survival Point Process for a Longleaf Pine Forest in Southern Georgia |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1164-1174
StephenL. Rathbun,
Noel Cressie,
Preview
|
PDF (1068KB)
|
|
摘要:
A marked spatial point pattern of trees and their diameters is the result of a dynamic biological process that takes place over time as well as space. Such patterns can be modeled as realizations of marked space-time survival point processes, where trees are born at some random location and time and then live, grow, and produce offspring in a random fashion. A model for a marked space-time survival point process is fit to data from a longleaf pine (Pinus palustris) forest in southern Georgia. The space-time survival point process is divided into three components: a birth process, a growth process, and a survival process. Each of the component processes is analyzed individually, from which conclusions regarding the dynamic ecological processes can be made. By using this reductionist approach, questions concerning each individual process can be addressed that might not have been answerable otherwise.
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476856
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
3. |
Stochastic Population Forecasts for the United States: Beyond High, Medium, and Low |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1175-1189
RonaldD. Lee,
Shripad Tuljapurkar,
Preview
|
PDF (1600KB)
|
|
摘要:
Conventional population projections use “high,” “medium,” and “low” scenarios to indicate uncertainty, but probability interpretations are rarely given, and in any event the resulting ranges for vital rates, births, deaths, age groups sizes, age ratios, and population size cannot possibly be probabilistically consistent with one another. This article presents and implements a new method for making stochastic population forecasts that provide consistent probability intervals. We blend mathematical demography and statistical time series methods to estimate stochastic models of fertility and mortality based on U.S. data back to 1900 and then use the theory of random-matrix products to forecast various demographic measures and their associated probability intervals to the year 2065. Our expected total population sizes agree quite closely with the Census medium projections, and our 95 percent probability intervals are close to the Census high and low scenarios. But Census intervals in 2065 for ages 65+ are nearly three times as broad as ours, and for 85+ are nearly twice as broad. In contrast, our intervals for the total dependency and youth dependency ratios are more than twice as broad as theirs, and our ratio for the elderly dependency ratio is 12 times as great as theirs. These items have major implications for policy, and these contrasting indications of uncertainty clearly show the limitations of the conventional scenario-based methods.
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476857
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
4. |
A Probabilistic Model for the Spatial Distribution of Party Support in Multiparty Electorates |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1190-1197
Samuel Merrill,
Preview
|
PDF (818KB)
|
|
摘要:
Spatial models of electoral competition locate voters and parties at points in euclidean space—representing issue positions—and specify utility of voters for parties as functions of these positions. Utility functions may also have stochastic components unassociated with issues. In this article probabilistic models are compared in which the utility function incorporates distance between voter and party positions (proximity model) or a scalar product (directional model). Model specification is significant because of its relation to party strategy and the resulting spatial distribution of parties. Maximum likelihood is used to estimate parameters of a mixed directional and proximity model—with stochastic and strategic components—from data in Norwegian and Swedish election studies. Expected spatial distributions of voters by party support are determined for the multiparty electorates of Norway and Sweden. Unlike previous deterministic work, which strongly favors the directional model, the results obtained here suggest that a mixture of proximity and directional probabilistic models may provide a substantially better fit than either pure model or a deterministic model.
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476858
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
5. |
Discussion |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1198-1198
Andrew Gelman,
Preview
|
PDF (137KB)
|
|
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476859
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
6. |
Rejoinder |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1199-1199
Samuel Merrill,
Preview
|
PDF (80KB)
|
|
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476860
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
7. |
Statistical Quality Control of HIV-1 ELISA Test Performance |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1200-1208
R.C. Gentleman,
M.S. Hamada,
D.E. Matthews,
A.R. Wilson,
Preview
|
PDF (818KB)
|
|
摘要:
Ensuring the quality and performance of human immunodeficiency virus, type 1 (HIV-1) enzyme-linked immunosorbent assay (ELISA) testing in routine laboratory situations is an important practical concern. In this article we develop statistical quality control procedures designed to monitor test performance of the microplates being processed. First, the logarithm of measured optical density is shown to be a more appropriate scale on which to work. Shewhart control charts are considered but are not entirely satisfactory because of between-plate variation. Correct classification depends more on within-plate variation than on between-plate variation. Range charts are useful, but they do not directly indicate whether the results from any particular microplate are reliable. Consequently, a new statistical control chart—the separation chart—is proposed, and the assumptions on which it is based are empirically verified. Retrospective analysis of nearly 1,300 microplates, using separation and range charts, demonstrates that these statistical process control methods may represent a potentially useful supplement to the manufacturer's recommended quality control procedures.
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476861
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
8. |
Characterization and Optimization of a Wave-Soldering Process |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1209-1217
Peter Mesenbrink,
Jye-Chyi Lu,
Richard McKenzie,
Javad Taheri,
Preview
|
PDF (910KB)
|
|
摘要:
A case study for improving the quality of a wave-soldering process that produced printed circuit boards (PCB's) is presented. A mixed-level fractional factorial design was implemented in a high-volume production system during normal operational hours. The observed ordered-categorical data from the bottom-side soldered leads were weighted to formulate the average, spatial uniformity, and dispersion process performance measurements. For lead classes like the integrated circuit and printed grid array, a polynomial model was established using the least squares method with weights provided by a dispersion function. The main-effect and interaction model terms were selected by forward and all-subsets regressions. Production quotas, topside defects, presoldering board temperature, and variance models were used to set the constraints for simultaneously optimizing predictions from the average and the uniformity models of all leads. A nonlinear optimization routine was used to determine the best and most robust settings for the continuous and discrete process variables. Results from a confirmatory experiment showed an improvement of mean soldering quality by 33% and of uniformity by 39%.
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476862
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
9. |
Modeling Household Purchase Behavior with Logistic Normal Regression |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1218-1231
GregM. Allenby,
PeterJ. Lenk,
Preview
|
PDF (1452KB)
|
|
摘要:
The successful development of marketing strategies requires the accurate measurement of household preferences and their reaction to variables such as price and advertising. Manufacturers, for example, often offer products at a reduced price for a limited period. One reason for this practice is that it induces households to try the promoted product with the hope of retaining them as permanent customers. The successful implementation of this strategy requires knowledge of the extent of price sensitivity in the population, effective methods of advertising, and the existence of a carry-over effect in the household's evaluation of the product. Logistic regression models are often used to relate household demographics, prices, and advertising variables to household purchase decisions. In this article we extend the standard model to include cross-sectional and serial correlation in household preferences and provide algorithms for estimating the model with random effects. The model is applied to scanner panel data for ketchup purchases, and substantive insights into household preference, brand switching, and autocorrelated purchase behavior are obtained.
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476863
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
10. |
Some Applications of Radial Plots |
|
Journal of the American Statistical Association,
Volume 89,
Issue 428,
1994,
Page 1232-1242
RexF. Galbraith,
Preview
|
PDF (1125KB)
|
|
摘要:
A radial plot is a graphical display for comparing estimates that have differing precisions. It is a scatter plot of standardized estimates against reciprocals of standard errors, possibly with respect to a transformed scale, designed so that the original estimates can be compared and interpreted. The estimates may be means, regression coefficients, proportions, rates, odds ratios, random effects, or indeed any parameter estimates that merit comparison between individuals or groups. This article illustrates some uses of radial plots by discussing a variety of data examples taken from the literature. The statistical application areas include interlaboratory trials, point process event rates, empirical Bayes estimation, modeling of counting data, analysis of overdispersed and underdispersed binomial and Poisson data, mixture modeling and meta-analysis.
ISSN:0162-1459
DOI:10.1080/01621459.1994.10476864
出版商:Taylor & Francis Group
年代:1994
数据来源: Taylor
|
|