Bayesian Alternatives to the F Test for Two Population Variances

Bayesian alternatives to the classical F test comparing two population variances are explored. Shoemaker (2003 Shoemaker , L. H. ( 2003 ). Fixing the F test for equal variances . The Amer. Statistician 57 : 105 – 114 .[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) suggested two adjustments to the F test due to it being very sensitive to the normal assumption of the two populations. A simulation study is performed to compare the Bayesian alternatives to the F test and Shoemaker's adjusted F tests as well as to the Levene/Brown–Forsythe and the squared rank nonparametric tests. The Bayesian alternatives assume a normal parent distribution and non informative priors and the conjugate prior for the variances; in addition, an exponential power distribution is considered as the parent distribution with a non informative prior for the variances. The latter looks to be very promising provided that a suitable value of a parameter which measures the extent of non normality is chosen.     

Subjective efficacy and ideal family size as predictors of favorability toward birth control

This study is an assessment of the relevance of subjective efficacy and ideal family size as predictors of favorability toward birth control. The samples considered are male factory workers in five developing nations. The effects of ideal family size and subjective efficacy are generally strong relative to those of education and the other social variables that are considered. The focus of the study is an analysis of whether subjective efficacy and ideal family size function more as independent determinants or more as intervening variables. Overall these psychological variables function more as independent determinants than as intervening variables, but in some samples these two functions are equally important.     

Breastfeeding women and family planning programs: special needs and opportunities

Although breastfeeding makes a major contribution to fertility control and child spacing in many developing countries, the implications of this are not widely recognized. Terminology may be part of the reason. Contraception may imply something modern, whereas the contraceptive effect of breastfeeding is a natural biological mechanism. Also, many family planning program managers are educated in the West, where breastfeeding is of little contraceptive importance. Regardless of where they were educated, they may consider the pregnancy-postponing effects of breastfeeding as mythology, or may consider breastfeeding as sufficiently effective at the individual level. Breastfeeding as a family planning method cannot be "delivered" to women by family planning methods, and requires an educational approach rather than a clinical or medical approach. A women might use breastfeeding more confidently in avoiding an unplanned pregnancy if she begins using a contraceptive method as soon as she resumes menses, when she begins giving her baby food supplements, or by 6 months post partum--whichever comes first. She can achieve high effectiveness in avoiding pregnancy by keeping the baby nearby and feeding on demand, feeding frequently, sleeping near the baby and maintaining nightfeedings, not giving the baby bottles or pacifiers, and giving the baby only breastmilk for at least 4 months. Breastfeeding can only be used by new mothers and cannot be used to postpone the 1st birth. Nor is it appropriate for women who have attained their desired family size, or who wish to avoid or postpone pregnancy at any cost.     

Restricted Indian buffet processes

Latent feature models are a powerful tool for modeling data with globally-shared features. Nonparametric distributions over exchangeable sets of features, such as the Indian Buffet Process, offer modeling flexibility by letting the number of latent features be unbounded. However, current models impose implicit distributions over the number of latent features per data point, and these implicit distributions may not match our knowledge about the data. In this work, we demonstrate how the restricted Indian buffet process circumvents this restriction, allowing arbitrary distributions over the number of features in an observation. We discuss several alternative constructions of the model and apply the insights to develop Markov Chain Monte Carlo and variational methods for simulation and posterior inference.     

Ties That Bind: Public Foundations in Dyadic Partnerships

VOLUNTAS: International Journal of Voluntary and Nonprofit Organizations - Public Ancillary Funds (PubAFs) are grantmaking philanthropic foundations, largely held to be independent. However, some...     

PERSONAL AUTHORITY IN THE FAMILY SYSTEM: DEVELOPMENT OF A QUESTIONNAIRE TO MEASURE PERSONAL AUTHORITY IN INTERGENERATIONAL FAMILY PROCESSES*

This paper reports a series of studies on the development of the Personal Authority in the Family System (PAFS) questionnaire. The PAFS questionnaire is designed to measure family processes based on aspects of current intergenerational family theory (Williamson, 1981, 1982b). Eight scales which measure concepts such as differentiation/fusion, intimacy/isolation, and personal authority/intimidation in the three-generational context comprise the questionnaire. Study 1 indicates that the scales have good internal consistency and good test-retest reliability. Correlations with other measures of family processes provide validity for some of the PAFS scales. Study 2 confirms the underlying factor structure of the PAFS questionnaire and supports the construct validity of the scales. Implications for intergenerational family theory and applications in research and clinical practice are discussed.     

On approximating optimal weight “no”-certificates in weighted difference constraint systems

This paper is concerned with the design and analysis of approximation algorithms for the problem of determining the least weight refutation in a weighted difference constraint system. Recall that a difference constraint is a linear constraint of the form \(x_{i}-x_{j} \le b_{ij}\) and a conjunction of such constraints is called a difference constraint system (DCS). In a weighted DCS (WDCS), a positive weight is associated with each constraint. Every infeasible constraint system has a refutation, which attests to its infeasibility. In the case of a DCS, this refutation is a subset of the input constraints, which when added together produces a contradiction of the form \(0 \le -b\), \(b> 0\). It follows that every refutation acts as a “no”-certificate. The length of a refutation is the number of constraints used in the derivation of a contradiction. Associated with a DCS \(\mathbf{D: A\cdot x \le b}\) is its constraint network \(\mathbf{G= \langle V,E, b \rangle }\). It is well-known that \(\mathbf{D}\) is infeasible if and only if \(\mathbf{G}\) contains a simple, negative cost cycle. Previous research has established that every negative cost cycle of length k in \(\mathbf{G}\) corresponds exactly to a refutation of \(\mathbf{D}\) using k constraints. It follows that the shortest refutation of \(\mathbf{D}\) (i.e., the refutation which uses the fewest number of constraints) corresponds to the length of the shortest negative cycle in \(\mathbf{G}\). The constraint network of a WDCS is represented by a constraint network \(\mathbf{G = \langle V, E, b, l \rangle }\), where \(\mathbf{l}:\mathbf{E \rightarrow \mathbb {N}}\) represents a function which associates a positive, integral length with each edge in \(\mathbf{G}\). In the case of a WDCS, the weight of a refutation is defined as the sum of the lengths of the edges corresponding to the refutation. The problem of finding the minimum weight refutation in a WDCS is called the weighted optimal length resolution refutation (WOLRR) problem and is known to be NP-hard. In this paper, we describe a pseudo-polynomial time algorithm for the WOLRR problem and convert it into a fully polynomial time approximation scheme (FPTAS).     

College Health as a Partner in the Care of Pediatric Cancer Survivors

Abstract

Objective: This study reviews an initiative to educate providers on pediatric cancer survivor care and to establish a cancer survivor registry in a college health center. Participants: Participants were University of Georgia (UGA) college health providers. Methods: Providers attended lectures on survivor care and were encouraged to register on Cancer SurvivorLink. Changes in provider familiarity and practice were measured using baseline and follow-up surveys. A survivor registry was created using health entrance forms and medical records abstraction. Results: Twenty-four providers registered on SurvivorLink, and 16 completed both surveys. Familiarity with survivor care (p = .003) and a survivor health care plan (p = .016) increased. Likelihood to deliver survivor care increased (p = .01). UGA follows 95 survivors; 71 diagnosed at < 21 years. Among survivors diagnosed at < 21 years, 91% reported their diagnosis on entrance forms. Conclusions: Through education and optimization of health informatics, college health centers can identify and provide survivor care to this medically vulnerable population.     

Individualized Educational Approach to Fieldwork in a Community Mental Health Center

Social work educators have voiced differing views about the best preparation for practice. Some feel that two types of social workers are needed: one to help people in trouble and one to work toward changing society. Other educators advise that programs be aimed at developing general skills. The authors discovered that by concentrating on producing truly educated individuals this conflict was avoided and graduating interns were prepared for a multitude of careers. This individualized educational approach involved the interns in all educational decisions, which helped develop a mature, creative thinking style.