Population Marginal Means in the Linear Model: An Alternative to Least Squares Means

The parameter concept in the term least squares mean is defined and given the more meaningful name population marginal mean; and its estimation is discussed.     

A Note on Estimating Covariance Components

A well-known formula for expressing a covariance in terms of variances is shown to hold true for estimating components of covariance.     

Parallel Lines in Residual Plots

Attention is drawn to a little-known feature of residuals plotted against predicted values: When observed values of y are repeated in the data, then the plot exhibits a series of parallel lines having slope — 1.     

Statistical Computing Packages: Some Words of Caution

Three situations are cited when caution is needed in using statistical computing packages: (a) when analyzing data and having insufficient statistical knowledge to completely understand the output; (b) when teaching the use of packages in a statistics course, to the exclusion of teaching statistics; and (c) when using packages in subject-matter teaching, without teaching the statistical methods underlying the packages.     

Helping people to sort it out: The role of social support in the Job Strain Model

This paper reports three studies of occupational stress investigating the role of social support as an intervening variable in the Job Strain Model (Karasek, 1979). A computer simulated mail-sorting work environment was used to assess the effect of demands, control and social support on measures of strain, satisfaction, and perceived and actual task performance. The first experiment ( N =60) tests the basic Job Strain Model by manipulating levels of task demand and control. The second experiment ( N =120) compares high and low levels of two types of social support (informational support and emotional support) to determine whether and how they interact with extreme conditions of the Job Strain Model (high strain and low strain). The final experiment ( N =90) investigates positive and negative forms of social support (praise and criticism) in relation to extreme job strain conditions. Results show that the job strain model is consistent with the stress and performance data, although stress showed no Demand 2 Control interaction. Social supports increased arousal, satisfaction and perceived performance, but did not affect stress or task performance. Moreover, contrary to buffer theories, social supports did not interact with the job strain variables. Congruence between preferred and experienced emotional support levels also predicted performance.     

虚构话语的逻辑地位

塞尔认为可以从言语行为理论对"以言行事行为"的规定展开对"虚构"的哲学定义。通过与非虚构话语的对比,塞尔发现虚构话语不具备正常断言式以言行事行为所必须的基本原则、准备原则和真诚原则,进而推论虚构行为并非真正的以言行事行为,而是一种"伪装"的以言行事行为。在塞尔看来,虚构行为是一种特别的语言游戏,需要一种特别的惯例。而这种语言游戏并不能涵盖所有的以言行事的语言游戏,而只是对后者的一种寄生。     

Properties of maximum likelihood estimators of variance components in the one-way classification,balanced data

We studied properties of maximum likelihood estimators (MLEs) of the variance components obtained from balanced data of the one-way classification. Exact and asymptotic expected values and variances of these MLEs were derived under the usual normality assumptions. Numerical studies illustrate these expected values and variances, and also illustrate the probability of obtaining a negative solution to the maximum likelihood (ML) equation for the between-class variance component. Simulations were used to study the robustness of the ML estimators under non-normal distributions.     

Minicommunications

M23. Analysis of variance with unbalanced data (including empty cells) : comments on a paper

M24. Foms for the distribution of a ratio in terms of characteristic functions     

Establishing χ2 Properties of Sums of Squares Using Induction

The between-classes sum of squares in a between- and within-classes analysis of variance has, under normality, a χ² distribution. Although “substantial mathematical machinery” (Stigler 1984) is often used in classroom derivation of this distribution, it can be avoided by using induction and independence properties of standard normal variables. This is the derivation given here for unequal subclass numbers data. Independence of the between- and within-classes sums of squares is also shown.     

On Publishing Extended Abstracts,and Reviews

A suggestion is made that scientific journals should publish only extended abstracts of research papers and full-length review-style papers.