Likelihood estimation of missing cell means in the fixed model analysis of variance

This paper examines the formation of maximum likelihood estimates of cell means in analysis of variance problems for cells with missing observations. Methods of estimating the means for missing cells has a long history which includes iterative maximum likelihood techniques, approximation techniques and ad hoc techniques. The use of the EM algorithm to form maximum likelihood estimates has resolved most of the issues associated with this problem. Implementation of the EM algorithm entails specification of a reduced model. As demonstrated in this paper, when there are several missing cells, it is possible to specify a reduced model that results in an unidentifiable likelihood. The EM algorithm in this case does not converge, although the slow divergence may often be mistaken by the unwary as convergence. This paper presents a simple matrix method of determining whether or not the reduced model results in an identifiable likelihood, and consequently in an EM algorithm that converges. We also show the EM algorithm in this case to be equivalent to a method which yields a closed form solution.     

Revisiting Beal's Confidence Intervals for the Difference of Two Binomial Proportions

Confidence interval construction for the difference of two independent binomial proportions is a well-known problem with a full panoply of proposed solutions. In this paper, we focus largely on the family of intervals proposed by Beal (1987 Beal , S. ( 1987 ). Asymptotic confidence intervals for the difference between two binomial parameters for use with small samples . Biometrics 43 : 941 – 950 . [CSA] [CROSSREF] [Crossref], [PubMed], [Web of Science ®] , [Google Scholar]). This family, which includes the Haldane and Jeffreys–Perks intervals as special cases, assumes a symmetric prior distribution for the population proportions p ₁ and p ₂. We propose new methods that allow the currently observed data to set the prior distribution by taking a parametric empirical-Bayes approach; in addition, we also provide an investigation of the new interval' behaviors in small-sample situations. Unlike other solutions, our intervals can be used adaptively for experiments conducted in multiple stages over time. We illustrate this notion using data from an Argentinean study involving the Mal Rio Cuarto virus and its transmission to susceptible maize crops.     

Tables for the Lilliefors and Modified Cramer–von Mises Tests of Normality

We present new tabulations of the Lilliefors distribution and the modified Cramer–von Mises distribution, which are used to test for normality when the population mean and variance are unknown. Some practical remarks and an example are given.     

原始荒野的双重神秘性：非情境性语言对荒野法案的误读

近年来,＂荒野＂这个词在传统意义上的定义逐渐开始被许多著名的环境哲学家和历史学家所批判。他们强烈批判已有的＂荒野观＂,指出这种观念在实际上是有二元论倾向,是带有种族中心主义,是处于静止不变状态的错误观念。而面对这样的指责,传统的荒野观却从1964年的荒野法案中找到了能够为自己明确解释和辩护的证据。但是,尽管如此,被荒野法案强力支撑的荒野观仍在这些批判者们精明地解构之下,与荒野法案中对荒野的理解大相径庭了。这些批判家们认为,与荒野法案中动态历史性的、用情境性语言进行的相对性解释的荒野观相对比,已有荒野观对荒野的定义是静态不变,以纯粹逻辑和语言进行的绝对性解释,尽管他们也承认,荒野法案中对荒野的定义和理解对于随后荒野的立法、管理和巡查和提供了经验资料和理论指导。实际上,在荒野法案中,荒野这个词更多意义上是指人与自然之间建立的一种契约关系,而并非原始自然所保留下来的＂残余物＂。从这个角度看,荒野实际上是人类一个潜在的休憩地,或者,我们也可以从与我们的生活工作休戚相关、相互作用这个关系上去理解荒野的终极意义。其实,并不需要改变我们在地球上较为创造性、持续性的生活方式来还原一个原始的荒野,因为荒野本身就属于人类与自然这个生生相息、关系复杂多样的综合体,它是这个体系中重要而不可忽视的角色。     

Using Audio Computer-Assisted Self-Interviewing and Interactive Voice Response to Measure Elder Mistreatment in Older Adults: Feasibility and Effects on Prevalence Estimates

Demographic trends indicate an aging population, highlighting the importance of collecting valid survey data from older adults. One potential issue when surveying older adults is use of technology to collect data on sensitive topics. Survey technologies like A-CASI and IVR have not been used with older adults to measure elder mistreatment. We surveyed 903 adults age 60 and older in Allegheny County, Pennsylvania (U.S.) with random assignment to one of four survey modes: (1) CAPI, (2) A-CASI, (3) CATI; and (4) IVR. We assessed financial, psychological, and physical mistreatment, and examined feasibility of A-CASI and IVR, and effects on prevalence estimates relative to CAPI and CATI. Approximately 83% of elders randomized to A-CASI/IVR used each technology, although 28% of respondents in the A-CASI condition refused to use headphones and read the questions instead. A-CASI produced higher six month prevalence rates of financial and psychological mistreatment than CAPI. IVR produced higher six month prevalence rates of psychological mistreatment than CATI. We conclude that, while IVR may be useful, A-CASI offers a more promising approach to the measurement of elder mistreatment.     

Nineteenth century African-American and White biological living conditions in Texas

Using a source of 19th century Texas state prison inmate records, the present study contrasts the biological living conditions of comparable 19th century African and European Americans. Average Black stature ironically increased during the antebellum period and decreased immediately after emancipation, while average White stature declined throughout the second half of the 19th century. Texas Black BMI values declined during the late 19th and early 20th centuries; however, White BMI values increased, indicating considerable 19th century biological inequality by race. Therefore, the known material inequality that existed in the 19th century American South is reinforced with biological markers.     

Assessing Asset Indices

The use of asset indices in welfare analysis and poverty targeting is increasing, especially in cases in which data on expenditures are unavailable or hard to collect. We compare alternative approaches to welfare measurement. Our analysis shows that inferences about inequalities in education, health care use, fertility, and child mortality, as well as labor market outcomes, are quite robust to the economic status measure used. Different measures—most significantly per capita expenditures versus the class of asset indices—do not, however, yield identical household rankings. Two factors stand out in predicting the degree of congruence in rankings. First is the extent to which expenditures can be explained by observed household and community characteristics. Rankings are most similar in settings with small transitory shocks to expenditure or with little random measurement error in expenditure. Second is the extent to which expenditures are dominated by individually consumed goods, such as food. Asset indices are typically derived from indicators of goods that are effectively public at the household level, while expenditures are often dominated by food, an almost exclusively private good. In settings in which individually consumed goods are the main component of expenditures, asset indices and per capita consumption yield the least similar results.