An alternative two stage least squares (2SLS) estimator for latent variable equations

The Maximum-likelihood estimator dominates the estimation of general structural equation models. Noniterative, equation-by-equation estimators for factor analysis have received some attention, but little has been done on such estimators for latent variable equations. I propose an alternative 2SLS estimator of the parameters in LISREL type models and contrast it with the existing ones. The new 2SLS estimator allows observed and latent variables to originate from nonnormal distributions, is consistent, has a known asymptotic covariance matrix, and is estimable with standard statistical software. Diagnostics for evaluating instrumental variables are described. An empirical example illustrates the estimator. I gratefully acknowledge support for this research from the Sociology Program of the National Science Foundation (SES-9121564) and the Center for Advanced Study in the Behavioral Sciences, Stanford, California. This paper was presented at the Interdisciplinary Consortium for Statistical Applications at Indiana University at Bloomington (March 2, 1994) and at the RMD Conference on Causal Modeling at Purdue University, West Lafayette, Indiana (March 3-5, 1994).     

Round-robin analysis of social interaction: Exact and estimated standard errors

Kenny has proposed a variance-components model for dyadic social interaction. His Social Relations model estimates variances and covariances from a round-robin of two-person interactions. The current paper presents a matrix formulation of the Social Relations model. It uses the formulation to derive exact and estimated standard errors for round-robin estimates of Social Relations parameters.We are grateful to George Gilbert for comments on an earlier draft.     

广告设计的思维过程及其影响因素

让１０个具有不同知识背景和工作经验的被试独立完成一个假设的广告设计任务,要求在设计过程中大声报告他们所想到的内容。根据被试的口语报告,分析广告设计思维的基本过程,并探讨设计者的工作经验和知识背景对设计思维过程的影响。实验结果表明：（１）广告设计活动可以看成是一种问题解决行为,设计要求规定了问题的初始状态和目标状态,设计就是经过一系列认知操作产生出符合设计要求的设计结果;（２）实际工作中的广告设计过程包括问题理解、整体策划以及方案构思等阶段,这种阶段性同样存在于个体的设计思维过程中;（３）由于工作经验和知识背景不同,不同被试的广告设计思维过程具有明显的差异,这些差异体现在使用规则、理解问题以及整体策划等方面。     

Coming together and remaining a part: Development of a group-as-a-whole compass. Part II

Group-as-a-whole theory is an attempt to explain the collaboration and synergy that results when patients share their care. The art and science of treating individuals within psychotherapy groups is enriched by an understanding of the unique mediums ³ through which a group comes into being and the more general domains within which it comes to be known. This paper continues the development of a group-as-a-whole compass, as an integration of extant models and theories (Ettin, 1996). The focus shifts from conceptual and spatial models to an exploration of the cultural and relational processes that make up whole-group functioning. The paper comes full circle with hypotheses drawn about how a psychotherapy group, as a holistic phenomenon, is composed and maintained.Private practice, East Brunswick, New Jersey.     

APPLIED BEHAVIOR ANALYSIS AND STATISTICAL PROCESS CONTROL?

This paper examines Pfadt and Wheeler's (1995) suggestions that the methods of statistical process control (SPC) be incorporated into applied behavior analysis. The research strategies of SPC are examined and compared to those of applied behavior analysis. I argue that the statistical methods that are a part of SPC would likely reduce applied behavior analysts' intimate contacts with the problems with which they deal and would, therefore, likely yield poor treatment and research decisions. Examples of these kinds of results and decisions are drawn from the cases and data Pfadt and Wheeler present. This paper also describes and clarifies many common misconceptions about SPC, including W. Edwards Deming's involvement in its development, its relationship to total quality management, and its confusion with various other methods designed to detect sources of unwanted variability.     

NONCONTINGENT ESCAPE AS TREATMENT FOR SELF-INJURIOUS BEHAVIOR MAINTAINED BY NEGATIVE REINFORCEMENT

We extended research on the role of noncontingent positive reinforcement following a functional analysis of attention-maintained self-injurious behavior to self-injury maintained by negative reinforcement in 2 young males with developmental disabilities. During a pretreatment functional analysis, each participant's self-injury was shown to be differentially sensitive to escape from instructional activities as negative reinforcement. During noncontingent escape, escape from learning activities was provided on a fixed-time schedule that was not influenced by the participant's behavior. One participant was also exposed to differential negative reinforcement of other behavior. During this condition, escape from instructional activities was provided contingent on the omission of self-injury for prespecified intervals. Results showed that the provision of escape, even when noncontingent, resulted in significant reductions in self-injury. These results are particularly interesting in light of the experimental history of noncontingent reinforcement as a control rather than as a therapeutic procedure. Noncontingent escape is discussed as a form of extinction that may be less likely than other forms of extinction to produce severe side effects.     

Curriculum bias in standardized tests of reading decoding

This study examined overlap between four basal reading programs and the phonetic analysis subtest of three standardized achievement measures. Raw scores, percentages of items correct, grade equivalents, and percentile scores were computed for a hypothetical student who had mastered all grapheme-phoneme correspondences taught at each grade level. The results indicated that (a) programs differed in the number and sequence of phonics skills taught; (b) percentile and grade-equivalent scores differed across programs at each grade level for a given test; and (c) the proportion of grade-equivalent scores falling at or above expected grade levels differed across tests for a given program (range of 29%–71%). The implications for selecting and interpreting standardized measures of reading decoding are discussed.     

Correspondence analysis and association models constrained by a conditional independence graph

The manner in which the conditional independence graph of a multiway contingency table effects the fitting and interpretation of the Goodman association model (RC) and of correspondence analysis (CA) is considered.Estimation of the row and column scores is presented in this context by developing a unified framework that includes both models. Incorporation of the conditional independence constraints inherent in the graph may lead to equal or additive scores for the corresponding marginal tables, depending on the topology of the graph. An example of doubly additive scores in the analysis of a Burt subtable is given.Thanks are due to anonymous referees who substantially improved the original draft of this paper.     

Maximization of sums of quotients of quadratic forms and some generalizations

Monotonically convergent algorithms are described for maximizing six (constrained) functions of vectors x, or matricesX with columns x₁, ..., x _r . These functions are h₁(x)= _k (xA _kx)(xC _kx)^–1, H₁(X)= _k tr (XA _k X)(XC _k X)^–1, h₁(X)= _{k l} (x _l A _kx _l ) (x _l C _kx _l )^–1 withX constrained to be columnwise orthonormal, h₂(x)= _k (xA _kx)²(xC _kx)^–1 subject to xx=1, H₂(X)= _k tr(XA _kX)(XA_kX)(XC_kX)^–1 subject toXX=I, and h₂(X)= _{k l} (x _l A _kx _l )² (x _l C _kX _l )^–1 subject toXX=I. In these functions the matricesC _k are assumed to be positive definite. The matricesA _k can be arbitrary square matrices. The general formulation of the functions and the algorithms allows for application of the algorithms in various problems that arise in multivariate analysis. Several applications of the general algorithms are given. Specifically, algorithms are given for reciprocal principal components analysis, binormamin rotation, generalized discriminant analysis, variants of generalized principal components analysis, simple structure rotation for one of the latter variants, and set component analysis. For most of these methods the algorithms appear to be new, for the others the existing algorithms turn out to be special cases of the newly derived general algorithms.This research has been made possible by a fellowship from the Royal Netherlands Academy of Arts and Sciences to the author. The author is obliged to Jos ten Berge for stimulating this research and for helpful comments on an earlier version of this paper.     

Perceptual unit formation in simple motion patterns

The present study investigated the proximal constraints that determine perceptual unit formation under minimal stimulus conditions. Projections of three moving dots, which could form two possible two-dot configurations, were presented to naive observers. In a forced-choice situation, their task was to report which two-dot configuration was perceived as a distinct perceptual unit. The results showed that common motions (arbitrary translations and rigid rotations in the frontoparallel plane) have stronger grouping power as compared to different relative motions (expansions/contractions, or simultaneous expansions/contractions and deformations in the frontoparallel plane). It was found that proximal changes of distances between elements in two-dot structures reduce grouping power. Changes of proximal directions, however, did not affect unit formation in two-dot structures at all. The effect of vector algebraic combinations on grouping power in three-dot strutures was also investigated. Evidently, visual vector analysis splits up motion combinations into their constituents, and in come cases this contributes to additive effects.