摘要:

AbstractI applied principal components analysis to Humphrey central 24‐2 threshold values from both eyes of 304 clinically normal persons selected by simple random sample from Barbados, WI. The first component, accounting for 62 per cent of the variation, is equivalent to the average threshold value within persons. The first eigenvector, when represented by grey scale maps depicting a pair of eyes, reveals that, as average threshold increases, the visual field rises and flattens, like an umbrella that, initially closed, is simultaneously opened and thrust upwards. I verify three numerical predictions based upon this umbrella description. Much less important sources of variation involve disparity between fellow eyes, and hemimeridional and other symmetric differences within eyes. I discuss briefly possible physiologic explanatory mechanism

ISSN:0277-6715    

DOI:10.1002/sim.4780110902

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

摘要:

AbstractThe most common instance of multivariate observations is the case of repeated measures over time. The two most widely used methods for the analysis ofKrepeated measures for two groups are theKdegrees of freedom (d.f.)T2MANOVAF‐test and the within‐subjects 1 degree of freedom ANOVAF‐test. Both require complete samples from normally distributed populations. In this paper, I describe alternativeKand 1 d.f. distribution‐free procedures which allow for randomly missing observations. These include a large‐sample analysis of means, the Wei and Lachin multivariate Wilcoxon test with estimates of the Mann‐Whitney parameter, and a multivariate Hodges‐Lehmann location shift estimator based on the multivariateU‐statistic of Wei and Johnson. Each of these methods provides a distribution‐freeK‐variate estimate of the magnitude of group differences which can be used as the basis for an overall test of group differences. These tests include theKd.f. omnibusT2‐like test, 1 d.f. tests of restricted hypotheses, such as the Wei‐Lachin multivariate one‐sided test of stochastic ordering, and the test of general association based on a minimum variance generalized least squares (GLS) estimate of the average group difference. I then describe covariate stratified‐adjusted GLS estimates and tests of group differences. This approach also provides tests of homogeneity (interaction) for within‐subjects and between‐subjects effects. I illustrate these analyses with an analysis of repeated cholesterol measurements in two groups of patients, stratified by sex. Such analyses provide an overall distribution‐free summary estimate and test of the treatment effect obtained by combining the group differences over both ti

ISSN:0277-6715    

DOI:10.1002/sim.4780110903

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

摘要:

AbstractObjective and detailed neurological assessments are essential in studies of the treatment and the epidemiology of acute spinal cord injuries. In practice, investigators use the expanded score, found by taking the total of the individual determinations, but this summary obscures important detail as to the level and the overall severity of injury. To address this issue, we present a method for estimating level and net severity of injury that makes use of isotonic regression and the Spearman‐Kärber estimator. We describe the method for both sensory and motor assessments of neurologic function. In the special case where one gives an identical weight to the response at each level, these estimators algebraically partition the expanded score into separate contributions due to level and net severity. We provide a numerical example using data from the first National Acute Spinal Cord Injury Study, and we present a summary of the distribution of these parameters for this populati

ISSN:0277-6715    

DOI:10.1002/sim.4780110904

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

摘要:

AbstractThe correlation coefficient between initial and subsequent blood pressure (BP) measurements is referred to as the tracking correlation. Childhood BP tracking correlations, although positive, have been considered too low to make accurate predictions for an individual. These correlations, however, can be raised substantially by averaging BP over multiple weekly visits in each year, which partially accounts for withinperson variability.In a cohort of 333 school children, we measured BP 3 times on each of 4 successive weekly visits, in each of 4 consecutive years, using a random‐zero sphygmomanometer. Approximately 90 per cent of subjects had data for one or more follow‐up years, and 75 per cent of subjects who entered in the first year had data for all four years.With a model that allows estimation of correlations and that uses all available longitudinal data, we calculated tracking correlations completely corrected for within‐person variability, the statistical equivalent of measuring BP on an infinite number (∞) of visits and measurements per visit. Age‐sex adjusted tracking correlations for 3 years of follow‐up based on the means from 1, 2, 3, 4, and ∞ visits are, for systolic BP, 0.43, 0.56, 0.62, 0.66, and 0.73, respectively, and for diastolic BP, 0.20, 0.37, 0.46, 0.50, and 0.70, respectively. With longer follow‐up, the use of corrected tracking correlations would allow determination of the maximal extent to which childhood BP can predict adult levels, and therefore the usefulness of screening to identify children at high risk of developi

ISSN:0277-6715    

DOI:10.1002/sim.4780110905

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

摘要:

AbstractOmitted variable bias is discussed in the context of linear models. It is shown that the effect of omitted variables can be controlled in linear models for metric dependent variables by using data from follow‐up studies. Two different models for analysing such data are proposed. In the first model the omitted variables are assumed to be uncorrelated with the explanatory variables in the model and to be constant over time. These assumptions lead to a special structure of the covariance matrix of the errors over time. Efficient estimation of the parameters in the linear model has to take this special covariance matrix of the errors into account by using appropriate generalized least squares or maximum likelihood methods. In the second model the omitted variables are assumed to be time constant. Additionally, they are allowed to be correlated with the explanatory variables, that is these variables are omitted confounders in the usual epidemiological sense. It is shown that even in this case the parameters of the linear model can be estimated consistently with ordinary least squares if a follow‐up study is available. The differences between the parameter estimates under the first and the second model may be used to construct a Hausman test for misspecification. The models, the estimation methods and the Hausman test are illustrated by the example that explores the determinants of serum cholesterol in German adoloscents of both se

ISSN:0277-6715    

DOI:10.1002/sim.4780110906

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

摘要:

AbstractSeveral authors have shown that ecologic estimates can be biased by effect modification and misclassification in a different fashion from individual‐level estimates. This paper reviews and discusses ecologic biases induced by model misspecification; confounding; non‐additivity of exposure and covariate effects (effect modification); exposure misclassification; and non‐comparable standardization. Ecologic estimates can be more sensitive to these sources of bias than individual‐level estimates, primarily because ecologic estimates are based on extrapolations to an unobserved conditional (individual‐level) distribution. Because of this sensitivity, one should not rely on a single regression model for an ecologic analysis. Valid ecologic estimates are most feasible when one can obtain accurate estimates of exposure and covariate means in regions with internal exposure homogeneity and mutual covariate comparability; thus, investigators should seek out such regions in the design and analysis of ecologi

ISSN:0277-6715    

DOI:10.1002/sim.4780110907

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

摘要:

AbstractA digit preference model is developed to describe the preference for estimating gestational age at birth as an even week during the 20th to 36th week of gestation. The model incorporates a probability of misclassification to adjacent even weeks at odd gestational ages, while even gestational ages are assumed correctly classified. The model is extended to allow the misclassification probabilities to decrease linearly with week during the period. A piecewise exponential model is used to model relative risks of delivery associated with a previous spontaneous abortion and a model incorporating digit preference is fitted as a generalized bilinear model in GLIM. The estimates of relative risk in the underlying survival model are virtually the same whether the misclassification is incorporated in the model or ignored.

ISSN:0277-6715    

DOI:10.1002/sim.4780110908

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

摘要:

AbstractVarious expressions have appeared for sample size calculation based on the power function of McNemar's test for paired or matched proportions, especially with reference to a matched case‐control study. These differ principally with respect to the expression for the variance of the statistic under the alternative hypothesis. In addition to the conditional power function, I identify and compare four distinct unconditional expressions. I show that the unconditional calculation of Schlesselman for the matched case‐control study can be expressed as a first‐order unconditional calculation as described by Miettinen. Corrections to Schlesselman's unconditional expression presented by Fleiss and Levin and by Dupont, which use different models to describe exposure association among matched cases and controls, are also equivalent to a first‐order unconditional calculation. I present a simplification of these corrections that directly provides the underlying table of cell probabilities, from which one can perform any of the alternative sample size calculations. Also, I compare the four unconditional sample size expressions relative to the exact power function. The conclusion is that Miettinen's first‐order expression tends to underestimate sample size, while his second‐order expression is usually fairly accurate, though possibly slightly anti‐conservative. A multinomial‐based expression presented by Connor, among others, is also fairly accurate and is usually slightly conservative. Finally, a local unconditional expression of Mitra, among others, tends to be excessive

ISSN:0277-6715    

DOI:10.1002/sim.4780110909

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

摘要:

AbstractWe propose a new basis for adjusting the results of virus neutralization assays. These assays consist of two separate experiments performed in parallel: a virus titration experiment and a serum dilution assay. In the virus titration experiment, one estimates the amount of virus used in the assay (the virus challenge dose). In a typical virus neutralization assay, the virus challenge dose may range over an order of magnitude. In the serial dilution assay, one measures the serum neutralizing activity against a particular virus. Most standard methods use the virus titration results only to ensure that the overall experiment is acceptable; the specific results of the virus titration experiment are not used to adjust the estimate of serum neutralizing activity. Although adjustment based on calibration with reference sera could be done, this seldom occurs in practice. We use results from recent studies of the kinetics and stoichiometry of polio virus neutralization with monoclonal antibodies to develop a method to use results from the virus titration experiment to adjust the serum neutralizing activity directly. Our results also indicate that a simplead hocprocedure can improve the accuracy of the estimated serum neutralizing activity.

ISSN:0277-6715    

DOI:10.1002/sim.4780110910

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY

ISSN:0277-6715    

DOI:10.1002/sim.4780110911

出版商:Wiley Subscription Services, Inc., A Wiley Company    

年代:1992

数据来源: WILEY