Efficiencies in Variance Estimation for Complex Survey Data

Data from complex survey designs require special consideration, with regard to variance estimation and analysis, because of design components that include unequal selection probabilities, stratification, and clustering. Using data from the National Medical Care Expenditure Survey, which is characterized by a complex survey design, four variance estimation programs are compared: SESUDAAN/RATIOEST, SUPERCARP, PSALMS, and HESBRR. The comparisons concentrate on program capabilities, computational efficiency, and user facility.     

Expected Mean Squares for Hierarchical Factorial Layouts with Population Imbalance

We introduce an analysis of variance usable for two-factor hierarchical models where observations are incompletely sampled from unbalanced populations of finite effects. Our new approach enables unbiased estimation of the variance components for this type of model and allows hypothesis testing to identify significant effects/sub-class effects. An explanation of how these results can be generalized to factorial layouts with more than two factors is given.     

Child-related dimensions of placement stability in treatment foster care

Research shows increasing numbers of emotionally disturbed children entering foster care nationwide. As a result, there is growing interest in a special form of foster care known as therapeutic or treatment foster care. However, little information is currently available on the kinds of children who can benefit from this form of mental health care or on interactions between child characteristics and placement outcome. This paper begins to address this deficit in the knowledge base by proposing five psychosoical dimensions of child functioning associated with placement stability and outcome in treatment foster care. Current theory and research regarding each dimension are presented along with clinical examples.     

Relationships with waitresses: Gendered social distance in restaurant hierarchies

This paper explores the use of gendered social distance mechanisms by higher status male coworkers and employers as they participate with waitresses in ongoing restaurant activities. Formal and informal gendered interactional techniques, such as degrading uniforms and terms of address, skewed ideas about skill differences, and sexual harassment, are used by men as they attempt to gain or sustain power thereby reinforcing the sexual division of labor. Sometimes they are successful, other times they are not, as when women resist or fight back.The analysis is derived from participant observation in two New Jersey restaurants. Formal and informal interviews were also conducted with fifty servers employed in a wide variety of restaurants.     

How many names are enough? Identifying network effects with the least set of listed contacts

How many names are enough to reveal network effects using a name generator for network analysis? We analyze network data from two large organizations varying in complexity. We ask how much the network association with achievement is strengthened by adding another name to the recorded list of each person's sociometric citations. We conclude that five names is the cost effective number of sociometric citations to record. The network association with achievement weakens quickly with fewer names, especially in the more clustered network.     

Training in Depth Interviewing,William H. Banaka,New York: Harper and Row, 1971. 196 Pages, $3.95, Paperback

This paper reports on a communication assessment/development and evaluation program for directors, managers, and supervisors of a large metropolitan welfare department, with the involvement of the School of Social Work faculty at the University of Minnesota and a communications consultant, through the mechanism of a staff development project. In addition, it points out three significant future challenges oriented toward: (1) school of social work curriculum development, (2) responsibility of welfare agencies to provide training opportunities in management and communication, and (3) the support needs of governmental agencies.     

Casual sex among australian schoolies

This study of the casual sexual partnering of 570 male and 776 female Australian high school students on a “schoolies week” vacation expands on earlier research on factors that influence the sexual activity of vacationing youth. Over 60% of the men and nearly 40% of the women who engaged in sexual intercourse during schoolies week did so with a casual partner. We used logistic regression to test an expanded version of Triandis'Theory of Interpersonal Behavior (TIB) in explaining casual sexual partnering. Situational experiences (similar to what others have called situational disinhibition), prior sexual experiences and intentions (similar to what others have called spillover) influenced casual sexual partnering. Different causal pathways were demonstrated for men and women.