Suppose we use generalized estimating equations to estimate a marginal regression model for repeated binary observations. There are no established summary statistics available for assessing the adequacy of the fitted ...
详细信息
Suppose we use generalized estimating equations to estimate a marginal regression model for repeated binary observations. There are no established summary statistics available for assessing the adequacy of the fitted model. In this paper we propose a goodness-of-fit test statistic which has an approximate chi-squared distribution when we have specified the model correctly. The proposed statistic can be viewed as an extension of the Hosmer and Lemeshow goodness-of-fit statistic for ordinary logistic regression to marginal regression models for repeated binary responses. We illustrate the methods using data from a study of mental health service utilization by children. The repeated responses are a set of binary measures of service use. We fit a marginal logistic regression model to the data using generalized estimating equations, and we apply the proposed goodness-of-fit statistic to assess the adequacy of the fitted model. Copyright (C) 1999 John Wiley & Sons, Ltd.
Background. Children are better served by radiologists and technical personnel trained in the care of pediatric patients. However, a variety of obstacles may limit the access of children to dedicated pediatric imaging...
详细信息
Background. Children are better served by radiologists and technical personnel trained in the care of pediatric patients. However, a variety of obstacles may limit the access of children to dedicated pediatric imaging facilities. Objective. We designed and implemented two models for providing community-based imaging by academic pediatric radiologists. Materials and methods. The first site was an outpatient clinic staffed by physicians from the university-affiliated children's hospital. Imaging services included radiography, fluoroscopy, and ultrasound. The second site was a full-service community hospital radiology department staffed by a group practice, with pediatric imaging covered by the children's hospital radiologists. Facility, equipment, and protocol modifications were required to maintain quality standards. Success of these models was determined by volume statistics, referring physician/patient satisfaction surveys, and quality-assurance (QA) programs. Results. The outpatient satellite had a 48 % increase in total examinations from the first year to the second year and 87 % the third year. Pediatric examinations in the community hospital increased over 1000 % the first 7 months. Referring physicians reported increased diagnostic information and patient satisfaction compared to previous service. QA efforts revealed improved image quality when pediatric radiologists were present, but some continuing difficulties off-hours. Conclusion. We successfully implemented pediatric imaging programs in previously underserved communities. This resulted in increased pediatric radiologist supervision and interpretation of examinations performed on children and improved referring physician and patient satisfaction.
In recent years Lot quality assurance sampling (LQAS), a method derived from production-line industry, has been advocated as an efficient means to evaluate the coverage rates achieved by child immunization programmes....
详细信息
In recent years Lot quality assurance sampling (LQAS), a method derived from production-line industry, has been advocated as an efficient means to evaluate the coverage rates achieved by child immunization programmes. This paper examines the assumptions on which LQAS is based and the effect that these assumptions have on its utility as a management tool. It shows that the attractively low sample sizes used in LQAS are achieved at the expense of specificity unless unrealistic assumptions are made about the distribution of coverage rates amongst the immunization programmes to which the method is applied. Although it is a very sensitive test and its negative predictive value is probably high in most settings, its specificity and positive predictive value are likely to be low. The implications of these strengths and weaknesses with regard to management decision-making are discussed.
This study was conducted to determine whether implementing a program aimed at providing a variety of incentives to physicians who provide immunizations to preschool-aged children would help to improve immunization rat...
详细信息
This study was conducted to determine whether implementing a program aimed at providing a variety of incentives to physicians who provide immunizations to preschool-aged children would help to improve immunization rates and reduce fragmented care for patients. Twenty physicians from 14 private practices that provide care to preschool-aged children from low income families in suburban Cook County, Illinois participated in the project. A randomly selected subset of patient case records from the physicians' offices were audited after the implementation of the project to determine the immunization status of children in the practices and the nature of services provided. These 310 records of children under three years of age who were treated between 1991-1994 (the intervention sample) were compared to 310 charts from a 1988-1990 cohort of records (baseline sample). The groups did not differ on race or gender;however, significantly more families in the 1988 through 1990 cohort of children under 3 years of age were insured privately when compared to the 1991 through 1994 cohort Seventy percent (218) of the records in the intervention sample were up to date for age on immunizations compared to 45% (141) of the baseline records, reflecting a statistically significant difference (p<.00001). The intervention sample showed significantly more well child visits where immunizations were given and follow up visits where immunizations were given when compared to the baseline sample. Physicians completed surveys before and after implementation of the project. They were questioned about their knowledge and practices regarding immunizations as well as their opinion of specific project components. All of the physicians viewed the project as an effective means to improve immunization services to low income children. The project demonstrates a potential means of enhancing immunization levels and continuity of care among preschool-aged children. It also highlights the workable nature of the
We surveyed 62 school administrators from three midatlantic (MD, VA, WV) and one northeastern (CT) state on factors relevant to developing school-based mental health programs. Administrators were from schools that var...
详细信息
We surveyed 62 school administrators from three midatlantic (MD, VA, WV) and one northeastern (CT) state on factors relevant to developing school-based mental health programs. Administrators were from schools that varied on education level (elementary, middle, and high) and geographic location turban, suburban, and rural, with equivalent numbers in each subgroup. Administrators provided ratings to questions grouped in five categories: (a) Stressful Conditions, (b) Internalizing Behavioral Problems, (c) Externalizing Behavioral Problems, (d) Substance Abuse, and (e) Barriers to Mental Health Care, and provided open-ended comments on needs of youth and mental health programs for them. They rated behavioral and substance abuse problems as progressively more serious as students advanced in school level. Urban youth were reported to encounter higher stress and present more severe internalizing problems than suburban or rural youth. Suburban and rural schools provided more health and mental health services than urban schools. Across geographic locales, physical health services far outnumbered mental health services. Findings related to barriers to mental health care, and the viability of schools as delivery sites for comprehensive mental health services, are discussed.
暂无评论