CAUSAL EFFECTS OF TREATMENTS FOR INFORMATIVE MISSING DATA DUE TO PROGRESSION/DEATH

In longitudinal clinical trials, when outcome variables at later time points are only defined for patients who survive to those times, the evaluation of the causal effect of treatment is complicated. In this paper, we describe an approach that can be used to obtain the causal effect of three treatment arms with ordinal outcomes in the presence of death using a principal stratification approach. We introduce a set of flexible assumptions to identify the causal effect and implement a sensitivity analysis for non-identifiable assumptions which we parameterize parsimoniously. Methods are illustrated on quality of life data from a recent colorectal cancer clinical trial.     

Bootstrap power of the generalized correlation coefficient

We present a bootstrap Monte Carlo algorithm for computing the power function of the generalized correlation coefficient. The proposed method makes no assumptions about the form of the underlying probability distribution and may be used with observed data to approximate the power function and pilot data for sample size determination. In particular, the bootstrap power functions of the Pearson product moment correlation and the Spearman rank correlation are examined. Monte Carlo experiments indicate that the proposed algorithm is reliable and compares well with the asymptotic values. An example which demonstrates how this method can be used for sample size determination and power calculations is provided.     

Class Position,Class Ideology and Class Voting: Mobilization of Support for the New Democratic Party in the Canadian Election of 1984*

La recherche canadienne sur le vote des classes a surtout fait ressortir l'importance des forces structurelles qui contribuent à faire naître l'appui au Nouveau Parti démocratique (NPD) en insistant moins sur l'idéologie des classes. Le présent article contient un modèle LISREL faisant état des relations entre les positions des classes, leur idéologic et le vote en faveur du NPD selon la base de données provenant de l'étude des élections nationales du Canada de 1984. Les observations soulignent l'importance que revêtent, en tant que sources des suffrages des classes, trois dimensions de l'idéologie des classes qui repré-sentent en partie le résultat de la position de ces dernières. L'idéologie égalitaire et l'appui au maintien des syndicate forts ont des effete directs et prononcés sur le vote en faveur du NPD alors que l'identifi-cation à une classe exerce un effet indirect par le biais de deux autres variables. Même si la position objective des classes agit indépendam-ment sur les suffrages accordés au NPD, ses répercussions semblent limitées comparativement à celles que produisent les trois variables liées à l'étude. En modélisant les effete de la position et de l'idéologie des classes, les auteurs ont employé trois variables non encore utili-sées dans les analyses précédentes des suffrages des classes, soit l'appui des père et mère au NPD, la présence d'un syndiqué (autre que le répondant) dans le ménage et l'appartenance à une «classe nouvelle». Chacune de ces variables a un effet majeur sur le soutien donné au NPD. Quant aux répercussions attribuables à la région, elles semblent assez limitées une fois que l'on a tenu compte du vote des père et mère en faveur du NPD et de l'appui accordéà ce dernier à l'occasion des élections de 1980. Canadian research on class voting has primarily emphasized structural forces that produce support for the NDP, with less attention to class ideology. This paper presents a LISREL model of relationships among class position, class ideology, and voting for the NDP, based on data from the Canadian National Election Study of 1984. The findings point to the importance of three dimensions of class ideology, produced in part by class position, as sources of class voting. Egalitarian ideology and support for union strength have strong direct effects on NDP voting, and class identification exerts an indirect effect through the other two variables. Although objective class position has an independent effect on NDP voting, its impact appears to be modest in relation to that of the three attitudinal variables. In modelling the effects of class position and ideology, three variables not used in previous Canadian analyses of class voting have been employed: parental support for the NDP, presence of a union member (other than the respondent) in the household, and membership in a “New Class.” Each has a solid effect on NDP support. The effects of region appear as quite modest, after controlling for parental support for the NDP and for NDP support in the 1980 election.     

The Forest-Related Content of Children's Textbooks: 1950–1991*

This study utilizes content analysis to measure the prominence of six environmental themes in children's science and social studies textbooks over the period 1950–1991. Regression analysis of data from a sample of 118 textbooks reveals that textbook space devoted to forest issues has decreased since 1950. Within this shrinking space, treatments of ecological issues with regard to forests have increased, but only in science texts. All other environmental themes have decreased in prominence. The decreasing attention to forest issues in texts may be due in part to the trend of “mentioning,” the replacement of narrative text with strings of facts, in the production of textbooks. The finding that newer, more proenvironmental themes have not replaced the classical economic view of forests as commodities suggests that the growth in environmentalism in the United States since 1950 has not yet been sufficiently integrated into our culture to affect the formal education of children.     

Families formed as a result of donor insemination: the views of semen donors

This paper reports the views and feelings of semen donors at two London donor insemination (Dl) programmes regarding the recipients of Dl and the families created by this method. In particular it reports on: the types of recipients that donors wish to assist; their understanding of the legal position of donors and Di fathers; their views on the'matching' of donors and Dl fathers; their perception of Dl offspring's need or desire for information about the donor; their views on whether parents should tell their offspring about their Dl conception and regarding the secrecy surrounding Dl in general; and what they believe the community thinks about Dl. Overall, the donors perceive Dl families as being normal, and are very supportive of the autonomy and privacy of these families, but they also have concerns about the needs of the offspring. The authors draw attention to the need to take into account the views of donors in forming assisted reproduction policies, and also the need for the interests of the child to be paramount, as they are in the case of adoption.