Testing residual normality in the ANOVA model

The use of single group skewness and kurtosis critical values for the assessment of residual normality in the ANOVA model is examined. Using single group critical values gives a conservative test of residual normality in multiple group designs. As the sample size per group increases, the empirical Type I error rates for the skewness and kurtosis tests of residual normality approach a. These results supplement previous work which has focused on testing residual normality in the linear regression model.     

Economic dissatisfaction, potential unionism, and attitudes toward unions in Canada

Cet article examine une première tentative mise au point dans le but d'évaluer le lien entre le mécontentement économique et l'appui accordé aux syndicats en ayant recours à des données provenant de diverses réunions-débats qui ont eu lieu à travers le pays. Un modèle de variable latent (LISREL) est utilisé pour étudier les positions prises par un échantillon représentatif de canadiens entre 1977 et 1981. Selon les résultats, il existe en général une stabilityé considérable pour ce qui est de l'attitude à l'endroit des droits syndicaux et des pouvoirs. Une période de mécontentement économique tend à noircir l'image des syndicats aux yeux des membres. Des tendances nettement différentes séparent, d'une part, les membres actifs et éventuels des syndicats, et, d'une autre part, ceux qui ne sont pas membres en puissance.
This paper represents the first attempt to assess the relationship between economic dissatisfaction and support for unions, using panel data collected at the national level. A latent variable (LISREL) model is employed to examine the attitudes of a representative sample of Canadian respondents during the period from 1977 to 1981. The findings indicate considerable stability in attitudes about union rights and powers over time. There is some tendency for economic dissatisfaction to produce more negative perceptions of unions among union members. Significantly different patterns are found for union members and 'potential' union members, on the one hand, and individuals who are not potential members, on the other hand.     

“I Amn Not a Utistivc on Thje Typ” (“I'm Not Autistic on the Typewriter”)

Facilitated communication involves hand-over-hand or hand-on-forearm support of students as they communicate through pointing at pictures, letters or other objects. Over time, it is expected that the hand and arm support can be faded back. This observational study describes an effort to introduce facilitated communication to 22 students, ranging in age from 3 years 10 months to 21 years, in several US public schools. The students are all labeled autistic and do not speak or speak only with echolalic phrases. The findings include observations of the students communicating with facilitation, language samples, and conversations by the students. The students reveal unexpected literacy and numeracy skills. The appearance of these abilities raises a number of questions concerning prior assumptions about autism, communication, independence and interdependence, and the education of students with and without disabilities.     

The Emotional Environment of Families Experiencing Chronic Poverty in India

The emotional environment of families living in chronic poverty in India was explored. We hypothesized that the poor (when compared to the nonpoor) would report more aversive interaction and would report less family and life satisfaction. Results showed partial support for our hypotheses. Poor husbands expressed love to wives in fewer ways than the nonpoor men, and they were more likely to use physical or verbal abuse with wives and children. Poor wives showed anger more frequently to husbands and children than the nonpoor wives. However, there were no differences between the poor and the nonpoor on family and life satisfaction. Thus, income alone was not a sufficient predictor of the family's emotional environment.     

Population estimates from longitudinal records in otherwise data-deficient settings

Existing methods for estimating population parameters in settings of data deficiency do not provide techniques for analysis of commonly available longitudinal data. In setting where complete population data is unavailable, longitudinal data recorded for only a subset of the total population are often available (e.g., event registers, genealogies). In this article we present and evaluate models which derive population parameters for the population subgroup underlying such longitudinal data. Using the distribution of individual times until first recorded event within a measurement interval, population parameters are estimated which provide basic denominator data for analyzing event occurrence. The models which we derive are especially suited to records which may include migration and population growth trends. The use of the models is demonstrated and evaluated through an application to genealogical records for a nineteenth-century population. Possible extensions of these models and their major limitations are also discussed.     

An extension of geisser's discrimination model to proportional covariance matrices

The predictive discrimination model of Geisser is derived for the case in which the covariance matrices of the different populations are assumed proportional, with unknown constants of proportionality. It is shown that this model provides a better fit to a set of data than does the usual homoscedastic model.     

A K-SAMPLE EXTENSION TO FLIGNER'S CLASS OF TESTS FOR SCALE

The parameteric tests for equality of variance are well known. The classical F-test is typically used to test the hypothesis of equality of two variances, while tests such as those developed by Bartlett (1937) are commonly used for the k-sample hypothesis. These tests assume an underlying normal distribution and are quite sensitive to departures from normality (Box, 1953). Thus, when considering data that are from non-normal distributions, alternative nonparametric tests must be employed.
Fligner (1979) has proposed a class of two-sample distribution-free tests which possess very desirable properties and are attractive alternatives to other nonparametric tests for scale. The present paper extends the Fligner class of tests to the more general k-sample case.     

Landlord Involvement in Environmental Decision-Making on Rented Missouri Cropland: Pesticide Use and Water Quality Issues1

Abstract The need to better understand landlord involvement in decision-making related to pesticide use and water quality issues is evidenced by several trends. These trends include the increasing documentation of water pollution by farm pesticides, the changing characteristics of farm ownership and operator tenure, and evolutions in resource policy and protection planning. This paper utilizes a theoretical approach to the sociology of land tenure to interpret results from an investigation of landlord involvement in environmental decision making regarding pesticide selection on rented land. Eight counties with high susceptibility of water contamination by pesticides were selected for study. Structured, in-person interviews were administered to in-county landlords, and a mail survey was used to poll out-of-county landlords. Results indicate that participation is generally low with very little difference between landlord groups. Renters make most of the organizational and operational decisions on rented farmland. Landlord participation is predominantly based on economic, rather than on social or environmental, factors. Furthermore, while economic variables are important predictors of participation for both groups, gender and social ties to the renter tend to increase local landlord involvement, but not absentee involvement These results have important implications for both federal programs and further research on land tenure and environmental stewardship.     

An evaluation of brass mortality estimates under conditions of declining mortality

An evaluation of the Brass childhood mortality estimates under conditions of declining mortality shows them to overestimate current mortality. Error increases as the rate of mortality decline increases, as the childhood age up to which cumulative mortality is being estimated increases, and as age at onset of childbearing decreases. We use the results to develop a method for correcting the Brass estimates for the effects of quasistability. The method requires an estimate of the rate of mortality decline within the population in addition to information on the pattern of childbearing in the population.     

Ethical, legal and professional issues in family therapy: a graduate level course

This paper reports on the curricular components of a course entitled "Ethical, Legal and Professional Issues in Family Therapy." To aid in replication and assessment, selected teaching strategies are also presented.