Alternative procedures for testing regression slope homogeneity when group error variances are unequal.

The test for regression slope homogeneity across groups (e.g., sex, race, and treatments) is used in such varied settings as the analysis of covariance, the study of aptitude by treatment interactions, and bias detection in differential prediction research. The accuracy of this test requires the seldom-considered assumption of equality of within-group error variances. This research studies the effect of violating that assumption on the power of the F test for regression slope equality and finds that the test may be substantially affected when sample sizes are equal and severely affected when sample sizes are unequal. Alternative procedures based on R. A. Alexander's (see record 1994-39680-001) normalized-t approximation, G. S. James's (1951) second-order approximation, the Welch-Aspin approximation, and the chi-square test are described and evaluated. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Tests for homogeneity of variance in factorial designs.

The variance portion of P. A. Games's (See PA, Vol 62:2685) 3-factor model of inference on independent groups is extended. Six procedures that convert tests of spread into tests of location are reviewed and explored in a Monte Carlo study of how to test variances in a factorial design. The statistic In s–2 is shown to be a slight improvement over the procedure outlined by J. E. Overall and J. A. Woodward (see record 1975-04313-001). The dependence of these 2 tests on the normality condition is illustrated. Four robust alternatives of somewhat lower power are contrasted. The jackknife test is the most powerful and is only slightly sensitive to leptokurtosis if the ns are equal. The median test described by M. B. Brown and A. B. Forsythe (1974) is acceptable, but it uses average deviations rather than variances. The Box-Scheffé test is always robust. No single test is ideal. A 2-stage process is recommended. (31 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Silicone breast implants and long-term health effects: when are data adequate?

STUDY OBJECTIVE: To determine whether ambulance transport time from the scene to the emergency department is faster with warning lights and siren than that without. DESIGN: In a convenience sample, transport times and routes of ambulances using lights and sirens were recorded by an observer. The time also was recorded by a paramedic who drove an ambulance without lights and siren over identical routes during simulated transports at the same time of day and on the same day of the week as the corresponding lights-and-siren transport. SETTING: An emergency medical service system in a city with a population of 46,000. PARTICIPANTS: Emergency medical technicians and paramedics. RESULTS: Fifty transport times with lights and siren averaged 43.5 seconds faster than the transport times without lights and siren [t = 4.21, P = .0001]. CONCLUSION: In this setting, the 43.5-second mean time savings does not warrant the use of lights and siren during ambulance transport, except in rare situations or clinical circumstances.     

Inference for odds ratio regression models with sparse dependent data

Suppose the number of 2 x 2 tables is large relative to the average table size, and the observations within a given table are dependent, as occurs in longitudinal or family-based case-control studies. We consider fitting regression models to the odds ratios using table-level covariates. The focus is on methods to obtain valid inferences for the regression parameters beta when the dependence structure is unknown. In this setting, Liang (1985, Biometrika 72, 678-682) has shown that inference based on the noncentral hypergeometric likelihood is sensitive to misspecification of the dependence structure. In contrast, estimating functions based on the Mantel-Haenszel method yield consistent estimators of beta. We show here that, under the estimating function approach, Wald's confidence interval for beta performs well in multiplicative regression models but unfortunately has poor coverage probabilities when an additive regression model is adopted. As an alternative to Wald inference, we present a Mantel-Haenszel quasi-likelihood function based on integrating the Mantel-Haenszel estimating function. A simulation study demonstrates that, in medium-sized samples, the Mantel-Haenszel quasi-likelihood approach yields better inferences than other methods under an additive regression model and inferences comparable to Wald's method under a multiplicative model. We illustrate the use of this quasi-likelihood method in a study of the familial risk of schizophrenia.     

光谱分析标准物质均匀性检验数据的EXCEL统计处理

依照方差分析法的原理,在Microsoft Excel中设计方差分析检验均匀性工作模板,并将该模板应用到钛合金光谱分析标准物质的均匀性检验中,取得了很好的效果,该模板也可用于其它标准物质的均匀性检验。     

Control of the temporal aspect when considering risk factors for acute otitis media

Laparoscopic cholecystectomy, initially performed in France in 1987, has rapidly spread to other European countries, the United States, and elsewhere. Of the techniques that have evolved, the "French" technique, in which the surgeon stands between the patient's legs, and the "American" technique, in which the surgeon stands on the patient's left side, are the most commonly used. In the former technique, the liver is retracted via the mid-clavicular cannula and the infundibulum of the gallbladder via the anterior axillary port. In the latter technique, the liver is retracted by axial traction on the gallbladder through the anterior axillary cannula and the infundibulum through the mid-clavicular cannula. This position may increase the risk of bile duct injury. The technique selected for operative cholangiography should be adapted to the problem at hand. Cystic duct cholangiography shows ductal calculi more reliably due to better filling of the common bile duct; direct puncture of the gallbladder is safer when the biliary anatomy is unclear. A number of European studies confirm the safety of laparoscopic cholecystectomy. Mortality rates vary between 0% and 0.1%, and duct injury rates range between 0.2% and 0.6%. Conversion, which is done in 3% to 8% of cases, may be necessary in the case of uncontrollable hemorrhage, bile duct injury unsuitable for laparoscopic repair, or if the gallbladder is densely scarred (scleroatrophic). It can also be done for safety reasons, when the anatomy is unclear. Complications include bile collections due to accessory duct or cystic duct stump leaks or less commonly to common duct injury. The average postoperative stay is longer in Europe (3.2 days) than in the United States. A decision tree is presented for the management of common bile duct stones. In general, preoperatively identified ductal stones are removed by endoscopic sphincterotomy, which is then followed by laparoscopic cholecystectomy to remove the source of the calculi. The techniques of laparoscopic choledochotomy and transcystic exploration for the removal of stones in the common bile duct are only beginning to be used, but they may well prove to be the most popular procedures. Results with these procedures will need to be evaluated against those obtained with endoscopic sphincterotomy.     

Depression and wealth in older people: when money makes the difference

The placement of rubber bands on a ligator is often difficult and frustrating, especially when the operator is wearing gloves. A newly designed rubber-band loader with grooves and a pusher places the bands on the ligator easily, simultaneously, and quickly even under these conditions.     

Issues for consideration when choosing a qualitative data management system

A primary issue in conducting qualitative research is the time required for data analysis. Qualitative research can be costly, since data analysis is generally labour intensive and our time factors into money. There is, unfortunately, no magic formula for hastening the conceptual tasks associated with qualitative analysis, yet effective qualitative data management systems (QDMS) expedite the mechanical tasks, those tasks associated with storing and retrieving qualitative data. Rapid and smooth data management increases the time one can allot to data analysis. Although computer QDMS are increasingly recommended for their time-saving potential in relation to data management, some significant issues associated with the adoption of a computer versus a manual QDMS have not yet been fully explored. The purpose of this paper is to present major issues researchers should consider in choosing a computer or a manual QDMS. These issues include availability and accessibility, comfort, appropriateness, efficiency, thoroughness and contextualization.     

Tests of dominance in sequential categorical data.

Presents procedures to test research questions related to dominance in cases such as marital and family interactions. Dominance is an important phenomenon in interactive patterns and is defined as an asymmetry in predictability of 2 members of a system. Unlike previous tests for dominance that are applicable to categorically coded data, these tests account for the dependence between the 2 unidirectional tests. (6 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Improved confidence intervals for the difference between binomial proportions based on paired data

Existing methods for setting confidence intervals for the difference theta between binomial proportions based on paired data perform inadequately. The asymptotic method can produce limits outside the range of validity. The 'exact' conditional method can yield an interval which is effectively only one-sided. Both these methods also have poor coverage properties. Better methods are described, based on the profile likelihood obtained by conditionally maximizing the proportion of discordant pairs. A refinement (methods 5 and 6) which aligns 1-alpha with an aggregate of tail areas produces appropriate coverage properties. A computationally simpler method based on the score interval for the single proportion also performs well (method 10).     

Estimation of left ventricular end-diastolic pressure with the difference in pulmonary venous and mitral A durations is limited when mitral E and A waves are overlapped

Previous studies showed that difference in pulmonary venous and mitral A-wave durations can be used for the estimation of left ventricular end-diastolic pressure, which is based on the assumption that the pulmonary venous A wave and mitral A wave start with the beginning of left atrial contraction. It is also assumed that the mitral A wave ends with the end of left atrial contraction. These assumptions may not be correct if left atrial contraction occurs before the early left ventricular filling is completed. Adequate Doppler mitral inflow and pulmonary venous flow signals were obtained simultaneously with left ventricular pressures at the cardiac catheterization laboratory in 50 patients who showed separated E and A waves in mitral inflow. After heart rate was increased by right atrial pacing to make the mitral E and A waves overlap, Doppler and hemodynamic measurements were repeated. When E and A waves are separated, pulmonary A-wave duration exceeding mitral A-wave duration has a sensitivity of 67% and specificity of 85% in the prediction of elevated left ventricular end-diastolic pressure (>/=20 mm Hg), whereas the pulmonary A wave ending later than mitral A wave has a sensitivity of 83% and a specificity of 45%. When the mitral E and A waves are overlapped, the pulmonary A wave ending later than mitral A wave is better for the prediction of elevated left ventricular end-diastolic pressure (sensitivity 55%, specificity 75%) than pulmonary A-wave duration exceeding mitral A-wave duration (sensitivity 9%, specificity 96%). However, overall, both methods are limited for clinical use.     

Use of the nonequivalent control group design when subjects are growing.

Many experimental programs aim to accelerate the growth of individuals on some dimension of interest. Typically, a group exposed to the program is compared with a control group. When it is feasible, random assignment of Ss to the program and control groups assures an unbiased comparison between treatments. Without randomization there may be important differences between groups, in terms of pretreatment characteristics and growth potential. In the nonequivalent control group design, pretest and posttest data on both groups are obtained. Statistical methods are used to adjust posttest comparisons, based mainly on pretest information. A variety of statistical techniques have been proposed, but there is much disagreement among methodologists as to which, if any, are adequate. This article examines the adequacy of these techniques, from an individual growth perspective. The performance of various commonly used methods is examined under alternative assumptions about the nature of growth. It is concluded that statistical adjustments are generally inadequate in the face of nonequivalent growth systems across treatment groups. (20 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Probabilities of identity-by-descent patterns in sibships when the parents are not genotyped

An assumption-free algorithm has been applied to compute the probabilities of all possible identity-by-descent (IBD) configurations when the parents have not been genotyped. These probabilities can be used to determine the amount of information that a particular sibship will bring to a nonparametric linkage analysis. It is shown that the number of possible configurations can be extremely large even when the markers are closely spaced and are rather polymorphic. Further, it is not always possible to reduce this number to a manageable one simply by consideration of the relative probabilities of the configurations.     

Simultaneous pairwise multiple comparison procedures for means when sample sizes are unequal.

Pairwise multiple comparison procedures (MCPs) are appropriate when the behavioral researcher is interested in comparing all possible pairwise mean differences. An exposition of the various simultaneous MCPs is presented that classifies those procedures as either (a) nonrobust to combinations of variance heterogeneity and unequal sample sizes because a pooled within-cell estimate of error variability is used to obtain the standard error of the contrast; or (b) robust to the homogeneity assumption because the standard error of the contrast is obtained via the Behrens-Fisher solution, and various approximate and/or conservative critical values that maintain the overall level of Type I error at "alpha" are used. A numerical example illustrating the latter MCPs is given. A choice among P. A. Games and J. F. Howell's (1976), C. W. Dunnett's (1980), and W. G. Cochran's (1964) procedures is recommended. (27 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Unequivocal determination of sire allele origin for multiallelic microsatellites when only the sire and progeny are genotyped

The effect of a segregating economic trait locus (ETL) can be detected with the aid of a linked genetic marker, if specific alleles of each locus are in association among the individuals genotyped for the genetic marker. For dairy cattle this can be achieved by application of the 'granddaughter design'. If only the sires and their sons are genotyped for the genetic markers, then the allele origin of sons having the same genotypes as their sires cannot be determined. Seven sires and 101 sons were genotyped for five microsatellites. The mean frequency of heterozygous sires was 77%. The mean number of alleles per locus was 8.2. Frequency of informative sons per locus ranged from 60% to 80% with a mean of 72%. With highly polymorphic microsatellites, at least 60% more grandsire families can be included in the analysis, and the number of sons assayed can be reduced by 40%, as compared to diallelic markers.     

Marital conflicts in the home when children are present versus absent.

Characteristics of marital conflict when children (8-16 years) were present versus absent were compared on the basis of 47 mothers' and fathers' reports during a 15-day period. Mothers described 669 incidents of marital conflict, and fathers described 551 incidents. About two thirds of the conflicts occurred in children's absence. Contrary to predictions, conflicts in which children were present were more negative (e.g., more negative emotions, more destructive conflict tactics) and more often about children than were child-absent conflicts. Although parents may attempt to protect children from conflict exposure, children tend to be exposed to a relatively hostile and emotionally negative subset of the marital conflicts that occur in the home. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Reactive sintering of porous tungsten for higher homogeneity

Abstract

One of the most important applications of tungsten is its use as a high current density cathode in the form of porous tungsten impregnated with electron emissive salts. Powder metallurgy is the usual processing route to make these parts since melting and casting of tungsten is very tedious due to its high melting point (3410±20°C). The overall porosity and porosity distribution are crucial parameters for the performance and lifetime of porous tungsten cathodes. Although there is an active debate over what constitutes the optimal porosity distribution, lack of homogeneity is observed in conventional parts. This may contribute to a shorter cathode and hence lamp lifetime. These parts are conventionally sintered at temperatures in excess of 2000°C. Furthermore, due to the high temperatures involved, the conventional sintering is very costly and energy consuming. This paper briefly looks into an alternative sintering process being developed for porous tungsten technology and its outcomes in terms of porosity distribution across the parts. As a result, the sintering temperature is dropped down to 1150°C and more homogeneous porous structures have been obtained. A characterisation method previously developed by the authors based on microhardness measurements is proved to be a good measure of the homogeneity of porous tungsten parts.