Home About us Contact
|
Home About us Contact | ||
|
|
||
Generalized Estimating Equations (generalized + estimating_equation)
Terms modified by Generalized Estimating Equations Selected AbstractsLongitudinal analysis of inpatient care utilization among people with intellectual disabilities: 1999,2002JOURNAL OF INTELLECTUAL DISABILITY RESEARCH, Issue 2 2007C.-H. Loh Abstract Background There has been no longitudinal study in Taiwan to identify the nature and the scale of medical care utilization of people with intellectual disabilities (IDs) up to the present. The aim of this study is to describe inpatient utilization among people under ID care in institutions in order to identify the pattern of medical care needs and the factors affecting utilization in Taiwan. Method The subject cohort was 168 individuals with ID who were cared for by a large public disability institution from 1999 to 2002 in Taipei, Taiwan. Results On the examination of the inpatient care that these persons underwent, it was found that these individuals had a heightened need (inpatient rate: 10.1,14.9%) for inpatient care compared with the general population with disabilities (9.37%) in Taiwan. The main reasons for hospitalization were pneumonia, gastrointestinal disorders, cellulites, orthopaedic problems, epilepsy and bronchitis. Using the full model of Generalized Estimating Equations for inpatient care utilization, the factors including low income family, living in an institution, being a subject with cerebral palsy and being a high outpatient user all influenced the use of inpatient care. Conclusions This study highlights that health authorities need to promote health planning more in order to ensure an excellent quality of health monitoring and health promotion among people with ID cared for by institutions. [source] Conditional Generalized Estimating Equations for the Analysis of Clustered and Longitudinal DataBIOMETRICS, Issue 3 2008Sylvie Goetgeluk Summary A common and important problem in clustered sampling designs is that the effect of within-cluster exposures (i.e., exposures that vary within clusters) on outcome may be confounded by both measured and unmeasured cluster-level factors (i.e., measurements that do not vary within clusters). When some of these are ill/not accounted for, estimation of this effect through population-averaged models or random-effects models may introduce bias. We accommodate this by developing a general theory for the analysis of clustered data, which enables consistent and asymptotically normal estimation of the effects of within-cluster exposures in the presence of cluster-level confounders. Semiparametric efficient estimators are obtained by solving so-called conditional generalized estimating equations. We compare this approach with a popular proposal by Neuhaus and Kalbfleisch (1998, Biometrics54, 638,645) who separate the exposure effect into a within- and a between-cluster component within a random intercept model. We find that the latter approach yields consistent and efficient estimators when the model is linear, but is less flexible in terms of model specification. Under nonlinear models, this approach may yield inconsistent and inefficient estimators, though with little bias in most practical settings. [source] Extended Generalized Estimating Equations for Binary Familial Data with Incomplete FamiliesBIOMETRICS, Issue 4 2002Patrick E. B. FitzGerald Summary. In this article, we assess the performance of two standard, but naive, methods for handling incomplete familial data in GEE2 analyses when the outcome is binary. We also propose a new method for analyzing such data using GEE2 when explanatory variables are discrete. Unlike the naive methods, the new method does not require the missing data process to be ignorable. We illustrate our method with an example that examines the familial aggregation of obesity. [source] Akaike's Information Criterion in Generalized Estimating EquationsBIOMETRICS, Issue 1 2001Wei Pan Summary. Correlated response data are common in biomedical studies. Regression analysis based on the generalized estimating equations (GEE) is an increasingly important method for such data. However, there seem to be few model-selection criteria available in GEE. The well-known Akaike Information Criterion (AIC) cannot be directly applied since AIC is based on maximum likelihood estimation while GEE is nonlikelihood based. We propose a modification to AIC, where the likelihood is replaced by the quasi-likelihood and a proper adjustment is made for the penalty term. Its performance is investigated through simulation studies. For illustration, the method is applied to a real data set. [source] Menopausal transition and the risk of urinary incontinence: results from a British prospective cohortBJU INTERNATIONAL, Issue 8 2010Gita D. Mishra Study Type , Aetiology (inception cohort) Level of Evidence 2b OBJECTIVE To investigate the effect of menopausal transition and age on symptoms of urinary incontinence in midlife. SUBJECTS AND METHODS The study included a nationally representative cohort of 1211 women followed up since their birth in 1946 and annually from 48,54 years; their menopausal transition status and symptoms of stress, urge, and severe urinary incontinence (UI) at 7 consecutive years from ages 48,54 were assessed. RESULTS From Generalized Estimating Equations, women who became perimenopausal (,pre-peri') or those experiencing perimenopause for >1 year (,peri-peri') were more likely to have symptoms of stress UI than were postmenopausal women; the odds ratio (95% confidence interval) was; pre-peri 1.39 (1.11,1.73); and peri-peri 1.39 (1.4,1.71). Menopausal transition status was not associated with urge or severe UI. These relationships were not explained by age, childhood enuresis, reproductive factors, previous health status, body mass index and educational qualifications. CONCLUSION This study is unique in being able to disentangle the effects of age, menopausal transitions, and other life-long risk factors on UI. Menopausal transition was only related to stress UI, while increasing age was related to both stress and urge UI. This study suggests that there are both shared and distinct aetiological pathways leading to each type of UI. [source] Influence of private practice setting and physician characteristics on the use of breast cancer adjuvant chemotherapy for elderly women,,CANCER, Issue 17 2009Dawn L. Hershman MD Abstract BACKGROUND: Although >70% of younger women with nonmetastatic breast cancer (BC) received adjuvant chemotherapy, only approximately 15% to 20% of elderly women with BC received chemotherapy. The decision to treat may be associated with nonmedical factors, such as patient, physician, or practice characteristics. In the current study, the association between oncologist characteristics and the receipt of chemotherapy in elderly women with BC was evaluated. METHODS: Women aged >65 years who were diagnosed with American Joint Committee on Cancer stages I to III BC between 1991 and 2002 were identified in the Surveillance, Epidemiology, and End Results-Medicare database. The Physician Unique Identification Number was linked to the American Medical Association Masterfile to obtain information on oncologists. Investigated was the association between demographic, tumor, and oncologist-related factors and the receipt of chemotherapy, using Generalized Estimating Equations to control for clustering. Patients were defined as low risk (estrogen/progesterone receptor positive, stage I/II disease) and high risk (estrogen/progesterone receptor-negative, stage II/III disease). RESULTS: Of 42,544 women identified, 8714 (20%) were treated with adjuvant chemotherapy. In a hierarchical analysis, women who underwent chemotherapy were more likely be treated by oncologists primarily employed in a private practice (odds ratio [OR], 1.40; 95% confidence interval [95% CI], 1.23-1.59) and who graduated after 1975 (OR, 1.12; 95% CI, 1.01-1.26) and were less likely to have an oncologist trained in the United States (OR, 0.83; 95% CI, 0.74-0.93). The association between a private practice setting and the receipt of chemotherapy was found to be similar for patients at high risk (OR, 1.55) and low risk (OR, 1.35) for cancer recurrence. CONCLUSIONS: Elderly women with BC treated by oncologists who were employed in a private practice were more likely to receive chemotherapy. Efforts to determine whether these associations reflected experience, practice setting, insurance type, or other economic incentives are warranted. Cancer 2009. Published 2009 by the American Cancer Society. [source] Effects of correlation and missing data on sample size estimation in longitudinal clinical trialsPHARMACEUTICAL STATISTICS: THE JOURNAL OF APPLIED STATISTICS IN THE PHARMACEUTICAL INDUSTRY, Issue 1 2010Song Zhang Abstract In longitudinal clinical trials, a common objective is to compare the rates of changes in an outcome variable between two treatment groups. Generalized estimating equation (GEE) has been widely used to examine if the rates of changes are significantly different between treatment groups due to its robustness to misspecification of the true correlation structure and randomly missing data. The sample size formula for repeated outcomes is based on the assumption of missing completely at random and a large sample approximation. A simulation study is conducted to investigate the performance of GEE sample size formula with small sample sizes, damped exponential family of correlation structure and non-ignorable missing data. Copyright © 2008 John Wiley & Sons, Ltd. [source] Candidate Molecular Pathway Genes Related to Appetite Regulatory Neural Network, Adipocyte Homeostasis and Obesity: Results from the CARDIA StudyANNALS OF HUMAN GENETICS, Issue 5 2010Yechiel Friedlander Summary Appetite regulatory neural network and adipocyte homeostasis molecular pathways are critical to long-term weight maintenance. Associations between obesity-related phenotypes and four genes in these pathways , leptin (LEP), leptin receptor (LEPR), neuropeptide Y2 receptor (NPY2R) and peptide YY (PYY) were examined in CARDIA Study participants (aged 18,30 at recruitment in 1985,6). Weight, BMI and waist circumference were measured at baseline and at years 2, 5, 7, 10, 15, and 20. Genotyping was conducted using tag SNPs characterising common genetic variations in these genes. Generalized estimating equation (GEE) models estimated associations between SNPs and repeated anthropometric measurements, controlling for sex and age. False discovery rate was used to adjust for multiple testing. In African-Americans, SNPs across the LEP gene demonstrated significant overall associations with all obesity-related phenotypes. The associations between LEP rs17151919 with weight tended to strengthen with time , the difference in weight associated with each additional minor allele increased from 2.6 kg at baseline to 4.8 kg at year 20 (SNP*time interaction p = 0.0193). NPY2R gene SNPs were associated with waist circumference among African-American men (p = 0.0462). In Caucasians, LEP SNPs also tended to be associated with weight (p = 0.0471), and PYY rs11684664 was associated with obesity-related phenotypes in women only (p = 0.010,0.026). Several LEP, and NPY2R and PYY SNPs were associated with obesity-related phenotypes in young adults, particularly among African-Americans. [source] The effect of social networks and social support on common mental disorders following specific life eventsACTA PSYCHIATRICA SCANDINAVICA, Issue 2 2010P. K. Maulik Maulik PK, Eaton WW, Bradshaw CP. The effect of social networks and social support on common mental disorders following specific life events. Objective:, This study examined the association between life events and common mental disorders while accounting for social networks and social supports. Method:, Participants included 1920 adults in the Baltimore Epidemiologic Catchment Area Cohort who were interviewed in 1993,1996, of whom 1071 were re-interviewed in 2004,2005. Generalized estimating equations were used to analyze the data. Results:, Social support from friends, spouse or relatives was associated with significantly reduced odds of panic disorder and psychological distress, after experiencing specific life events. Social networks or social support had no significant stress-buffering effect. Social networks and social support had almost no direct or buffering effect on major depressive disorder, and no effect on generalized anxiety disorder and alcohol abuse or dependence disorder. Conclusion:, The significant association between social support and psychological distress, rather than diagnosable mental disorders, highlights the importance of social support, especially when the severity of a mental health related problem is low. [source] Alcohol outlet density and university student drinking: a national studyADDICTION, Issue 7 2008Kypros Kypri ABSTRACT Aims To examine the geographic density of alcohol outlets and associations with drinking levels and related problems among university students. Design Cross-sectional survey study using geospatial data, with campus-level and individual-level analyses. Participants A total of 2550 students (mean age 20.2, 60% women) at six university campuses in New Zealand (63% response). Measurements Counts of alcohol outlets within 3 km of each campus were tested for their non-parametric correlation with aggregated campus drinking levels and related problems. Generalized estimating equations were used to model the relation between outlet counts within 1 km and 3 km of student residences and individual drinking levels/problems, with control for gender, age, ethnicity and high school binge drinking frequency, and adjustment for campus-level clustering. Findings Correlations for campus-level data were 0.77 (P = 0.07) for drinking and personal problems, and 0.31 (P = 0.54) for second-hand effects. There were consistent significant associations of both on- and off-licence outlet densities with all outcomes in student-level adjusted models. Effects were largest for 1 km densities and off-licence outlets. Conclusions There are positive associations between alcohol outlet density and individual drinking and related problems. Associations remain after controlling for demographic variables and pre-university drinking, i.e. the associations are unlikely to be due to self-selection effects. Increasing alcohol outlet density, and particularly off-licences, may increase alcohol-related harm among university students. [source] Candidate-gene association studies with pedigree data: Controlling for environmental covariatesGENETIC EPIDEMIOLOGY, Issue 4 2003S.L. Slager Abstract Case-control studies provide an important epidemiological tool to evaluate candidate genes. There are many different study designs available. We focus on a more recently proposed design, which we call a multiplex case-control (MCC) design. This design compares allele frequencies between related cases, each of whom are sampled from multiplex families, and unrelated controls. Since within-family genotype correlations will exist, statistical methods will need to take this into account. Moreover, there is a need to develop methods to simultaneously control for potential confounders in the analysis. Generalized estimating equations (GEE) are one approach to analyze this type of data; however, this approach can have singularity problems when estimating the correlation matrix. To allow for modeling of other covariates, we extend our previously developed method to a more general model-based approach. Our proposed methods use the score statistic, derived from a composite likelihood. We propose three different approaches to estimate the variance of this statistic. Under random ascertainment of pedigrees, score tests have correct type I error rates; however, pedigrees are not randomly ascertained. Thus, through simulations, we test the validity and power of the score tests under different ascertainment schemes, and an illustration of our methods, applied to data from a prostate cancer study, is presented. We find that our robust score statistic has estimated type I error rates within the expected range for all situations we considered whereas the other two statistics have inflated type I error rates under nonrandom ascertainment schemes. We also find GEE to fail at least 5% of the time for each simulation configuration; at times, the failure rate reaches above 80%. In summary, our robust method may be the only current regression analysis method available for MCC data. Genet Epidemiol 24:273,283, 2003. © 2003 Wiley-Liss, Inc. [source] An investigation into the relationship between apical root Impedance and canal anatomyINTERNATIONAL ENDODONTIC JOURNAL, Issue 9 2008S. M. Ardeshna Aim, To investigate a possible relationship between apical root impedance and canal anatomy. Methodology, Twenty-three roots from human extracted teeth (mostly single rooted but also from molars) with different apical anatomy were selected. The apical anatomy was initially classified by staining the root tip to identify number of canal exits; after impedance measurements, the anatomy was confirmed by staining and clearing the dentine. The roots were divided into two groups; 12 had simple (S) anatomy (Vertucci type 1 with a single exit) and 11 had complex (C) anatomy (various Vertucci canal types with multiple exist). Impedance measurements were taken using a frequency response analyser at seven levels in the root (0.0, 0.5, 1.0, 2.0, 3.0, 4.0 and 5.0 mm short of the apical terminus) at 14 frequencies ranging from 1120 to 100 000 Hz. Care was taken to control the temperature and other variables that could confound measurement accuracy. The impedance characteristics of individual roots were compared with 37 equivalent circuits (based on a pool created from a previous study); the best fitting equivalent circuit was selected. The equivalent circuits were used as the single outcome measure describing the impedance characteristics and correlated with the canal anatomy (S/C). Generalized estimating equations were used to perform logistic regression to analyse the data. Results, Canal anatomy had a significant (P = 0.046) effect on the equivalent circuit model. One circuit (model 10) was found to be the commonest and occurred significantly more commonly in the simple canals. The odds of prevalence of circuit model 10 were 2.2 times (odds ratio 2.17, 95% confidence interval 1.01,4.63) higher in canals with simple anatomy compared with canals with complex anatomy. Conclusions, Canal anatomy had a significant effect on the equivalent circuit describing its impedance characteristics. It should be possible to use impedance spectroscopy to clinically predict and image apical canal complexities. [source] Association Between Interleukin-6 and Lower Extremity Function After Hip Fracture,The Role of Muscle Mass and StrengthJOURNAL OF AMERICAN GERIATRICS SOCIETY, Issue 6 2008Ram R. Miller MDCM OBJECTIVES: To examine whether an effect on muscle mass or strength explains the association between interleukin-6 (IL-6) and lower extremity function in the year after hip fracture. DESIGN: Analysis of data from a longitudinal cohort study. SETTING: Two Baltimore-area hospitals. PARTICIPANTS: Community-dwelling women aged 65 and older admitted to one of two hospitals in Baltimore with a new, nonpathological fracture of the proximal femur between 1992 and 1995. MEASUREMENTS: At 2, 6, and 12 months postfracture, serum IL-6, appendicular lean muscle mass (aLM), and grip strength were measured, and the Lower Extremity Gain Scale (LEGS), a summary measure of performance of nine lower extremity tasks was calculated. Generalized estimating equations were used to model the longitudinal relationship between IL-6 tertile and LEGS. Whether muscle mass or strength explained the relationship between IL-6 and LEGS was examined by adding measures of aLM, grip strength, or both into the model. RESULTS: Subjects in the lowest IL-6 group performed better on the LEGS than those in the highest tertile by 4.51 (95% confidence interval (CI)=1.50,7.52) points at 12 months postfracture. Adjusting for aLM and grip strength, this difference was 4.28 points (95% CI=1.14,7.43) and 3.81 points (95% CI=0.63,7.00), respectively. Adjusting for both aLM and grip strength, the mean difference in LEGS score was 3.88 points (95% CI=0.63,7.13). CONCLUSION: In older women, after hip fracture, reduced muscle strength, rather than reduced muscle mass, better explains the poorer recovery of lower extremity function observed with higher levels of the inflammatory marker IL-6. [source] Urinary metal and polycyclic aromatic hydrocarbon biomarkers in boilermakers exposed to metal fume and residual oil fly ashAMERICAN JOURNAL OF INDUSTRIAL MEDICINE, Issue 6 2005Sutapa Mukherjee MBBS Abstract Background Boilermakers are occupationally exposed to known carcinogens. Methods The association of urinary 1-hydroxy-pyrene (1-OHP), a biomarker of polycyclic aromatic hydrocarbon (PAH) exposure, with biomarkers of metal exposure (vanadium, chromium, manganese, nickel, copper, and lead) in boilermakers exposed to metal fume from welding and dust particulates from residual oil fly ash (ROFA) was examined. A repeated measures cohort study was conducted during the overhaul of an oil-fired boiler. Twice-daily urine samples were obtained for 5 days and analyzed for cotinine, 1-OHP, and metals. Generalized estimating equations (GEE) were used to model the multivariate relationship of 1-OHP to the explanatory variables. Results Metal and 1-OHP levels were determined for 165 urine samples from 20 boilermakers and these levels increased during the workweek. However, the 1-OHP level was not significantly associated with any individual metal level at any time point. Conclusion This suggests that boilermakers were occupationally exposed to PAH and metals, but 1-OHP as a PAH biomarker was unable to serve as a surrogate marker of metal exposure for the metals measured in this study. Am. J. Ind. Med. 47:484,493, 2005. © 2005 Wiley-Liss, Inc. [source] Randomized Prospective Study to Evaluate Child Abuse Documentation in the Emergency DepartmentACADEMIC EMERGENCY MEDICINE, Issue 3 2009Elisabeth Guenther MD Abstract Objectives:, The objective was to determine whether an educational intervention for health care providers would result in improved documentation of cases of possible physical child abuse in children <36 months old treated in the emergency department (ED) setting. Methods:, This study had a statewide group-randomized prospective trial design. Participating EDs were randomized to one of three intervention groups: no intervention, partial intervention, or full intervention. Medical records for children <36 months of age were abstracted before, during, and after the intervention periods for specific documentation elements. The main outcome measure was the change in documentation from baseline. Generalized estimating equations (GEEs) were used to test for intervention effect. Results:, A total of 1,575 charts from 14 hospitals EDs were abstracted. Hospital and demographic characteristics were similar across intervention groups. There were 922 (59%) injury visits and 653 (41%) noninjury visits. For each specific documentation element, a GEE model gave p-values of >0.2 in independent tests, indicating no evidence of significant change in documentation after the intervention. Even among the 26 charts in which the possibility of physical abuse was noted, documentation remained variable. Conclusions:, The educational interventions studied did not improve ED documentation of cases of possible physical child abuse. The need for improved health care provider education in child abuse identification and documentation remains. Future innovative educational studies to improve recognition of abuse are warranted. [source] Rate of detoxification service use and its impact among a cohort of supervised injecting facility usersADDICTION, Issue 6 2007Evan Wood ABSTRACT Background Vancouver, Canada recently opened a medically supervised injecting facility (SIF) where injection drug users (IDU) can inject pre-obtained illicit drugs. Critics suggest that the facility does not help IDU to reduce their drug use. Methods We conducted retrospective and prospective database linkages with residential detoxification facilities and used generalized estimating equation (GEE) methods to examine the rate of detoxification service use among SIF participants in the year before versus the year after the SIF opened. In secondary analyses, we used Cox regression to examine if having been enrolled in detoxification was associated with enrolling in methadone or other forms of addiction treatment. We also evaluated the impact of detoxification use on the frequency of SIF use. Results Among 1031 IDU, there was a statistically significant increase in the uptake of detoxification services the year after the SIF opened. [odds ratio: 1.32 (95% CI, 1.11,1.58); P = 0.002]. In turn, detoxification was associated independently with elevated rates of methadone initiation [relative hazard = 1.56 (95% CI, 1.04,2.34); P = 0.031] and elevated initiation of other addiction treatment [relative hazard = 3.73 (95% CI, 2.57,5.39); P < 0.001]. Use of the SIF declined when the rate of SIF use in the month before enrolment into detoxification was compared to the rate of SIF use in the month after discharge (24 visits versus 19 visits; P = 0.002). Conclusions The SIF's opening was associated independently with a 30% increase in detoxification service use, and this behaviour was associated with increased rates of long-term addiction treatment initiation and reduced injecting at the SIF. [source] Bivariate association analyses for the mixture of continuous and binary traits with the use of extended generalized estimating equationsGENETIC EPIDEMIOLOGY, Issue 3 2009Jianfeng Liu Abstract Genome-wide association (GWA) study is becoming a powerful tool in deciphering genetic basis of complex human diseases/traits. Currently, the univariate analysis is the most commonly used method to identify genes associated with a certain disease/phenotype under study. A major limitation with the univariate analysis is that it may not make use of the information of multiple correlated phenotypes, which are usually measured and collected in practical studies. The multivariate analysis has proven to be a powerful approach in linkage studies of complex diseases/traits, but it has received little attention in GWA. In this study, we aim to develop a bivariate analytical method for GWA study, which can be used for a complex situation in which continuous trait and a binary trait are measured under study. Based on the modified extended generalized estimating equation (EGEE) method we proposed herein, we assessed the performance of our bivariate analyses through extensive simulations as well as real data analyses. In the study, to develop an EGEE approach for bivariate genetic analyses, we combined two different generalized linear models corresponding to phenotypic variables using a seemingly unrelated regression model. The simulation results demonstrated that our EGEE-based bivariate analytical method outperforms univariate analyses in increasing statistical power under a variety of simulation scenarios. Notably, EGEE-based bivariate analyses have consistent advantages over univariate analyses whether or not there exists a phenotypic correlation between the two traits. Our study has practical importance, as one can always use multivariate analyses as a screening tool when multiple phenotypes are available, without extra costs of statistical power and false-positive rate. Analyses on empirical GWA data further affirm the advantages of our bivariate analytical method. Genet. Epidemiol. 2009. © 2008 Wiley-Liss, Inc. [source] Multipoint analysis using affected sib pairs: Incorporating linkage evidence from unlinked regionsGENETIC EPIDEMIOLOGY, Issue 2 2001Kung-Yee Liang Abstract In this paper, we proposed a multipoint method to assess evidence of linkage to one region by incorporating linkage evidence from another region. This approach uses affected sib pairs in which the number of alleles shared identical by descent (IBD) is the primary statistic. This generalized estimating equation (GEE) approach is robust in that no assumption about the mode of inheritance is required, other than assuming the two regions being considered are unlinked and that there is no more than one susceptibility gene in each region. The method proposed here uses data from all available families to simultaneously test the hypothesis of statistical interaction between regions and to estimate the location of the susceptibility gene in the target region. As an illustration, we have applied this GEE method to an asthma sib pair study (Wjst et al. [1999] Genomics 58:1,8), which earlier reported evidence of linkage to chromosome 6 but showed no evidence for chromosome 20. Our results yield strong evidence to chromosome 20 (P value = 0.0001) after incorporating linkage information from chromosome 6. Furthermore, it estimates with 95% certainty that the map location of the susceptibility gene is flanked by markers D20S186 and D20S101, which are approximately 16.3 cM apart. Genet. Epidemiol. 21:105,122, 2001. © 2001 Wiley-Liss, Inc. [source] Doing Better to Do Good: The Impact of Strategic Adaptation on Nursing Home PerformanceHEALTH SERVICES RESEARCH, Issue 3p1 2007Jacqueline S. Zinn Objective. To test the hypothesis that a greater commitment to strategic adaptation, as exhibited by more extensive implementation of a subacute/rehabilitation care strategy in nursing homes, will be associated with superior performance. Data Sources. Online Survey, Certification, and Reporting (OSCAR) data from 1997 to 2004, and the area resource file (ARF). Study Design. The extent of strategic adaptation was measured by an aggregate weighted implementation score. Nursing home performance was measured by occupancy rate and two measures of payer mix. We conducted multivariate regression analyses using a cross-sectional time series generalized estimating equation (GEE) model to examine the effect of nursing home strategic implementation on each of the three performance measures, controlling for market and organizational characteristics that could influence nursing home performance. Data Collection/Abstraction Methods. OSCAR data was merged with relevant ARF data. Principal Findings. The results of our analysis provide strong support for the hypothesis. Conclusions. From a theoretical perspective, our findings confirm that organizations that adjust strategies and structures to better fit environmental demands achieve superior performance. From a managerial perspective, these results support the importance of proactive strategic leadership in the nursing home industry. [source] Familial aggregation in the night eating syndromeINTERNATIONAL JOURNAL OF EATING DISORDERS, Issue 6 2006Jennifer D. Lundgren PhD Abstract Objective: This study examined the extent to which the night eating syndrome (NES) affects first-degree relatives of NES and control probands. Method: NES participants and controls were assessed with the Night Eating Questionnaire (NEQ), the Night Eating Syndrome History and Inventory (NESHI), 10 day sleep and food records, the Eating Disorder Examination (EDE), the Structured Clinical Interview for DSM IV Axis I Disorders (SCID I), and a Family History Questionnaire (FHQ) to assess the presence of NES among first-degree relatives. A proband predictive model, using logistic regression analyses and the generalized estimating equation to control for correlation among observations within families was used to assess familial aggregation. Results: The odds of an NES proband having an affected first-degree relative were significantly greater than that of a control proband (odds ratio = 4.9, p < .001). A number of covariates were included in the model: proband body mass index (BMI) (kg/m2), proband gender, proband age, proband ethnicity, first-degree relative gender, relationship to proband (i.e., mother, father, or sibling), and the interaction between relationship to proband and proband status (night eater or control); none was statistically significant (p > .05). Conclusion: The study showed a strong aggregation of NES in families. © 2006 by Wiley Periodicals, Inc. Int J Eat Disord 2006 [source] Effect of an Educational Intervention on Optimizing Antibiotic Prescribing in Long-Term Care FacilitiesJOURNAL OF AMERICAN GERIATRICS SOCIETY, Issue 8 2007(See Editorial Comments by Dr. Lona Mody on pp 130, 1302) OBJECTIVE: To assess the effect of an educational intervention aimed at optimizing antibiotic prescribing in long-term care (LTC) facilities. DESIGN: Cluster randomized, controlled trial. SETTING: Eight public LTC facilities in the Montreal area. PARTICIPANTS: Thirty-six physicians. INTERVENTION: The educational intervention consisted of mailing an antibiotic guide to physicians along with their antibiotic prescribing profile covering the previous 3 months. Targeted infections were urinary tract, lower respiratory tract, skin and soft tissues, and septicemia of unknown origin. In the prescribing profile, each antibiotic was classified as adherent or nonadherent to the guide. Physicians in the experimental group received the intervention twice, 4 months apart, whereas physicians in the control group provided usual care. MEASUREMENTS: Data on antibiotic prescriptions were collected over four 3-month periods: preintervention, postintervention I, postintervention II, and follow-up. A generalized estimating equation (GEE) model was used to compare the proportion of nonadherent antibiotic prescriptions of the experimental and control groups. RESULTS: By the end of the study, nonadherent antibiotic prescriptions decreased by 20.5% in the experimental group, compared with 5.1% in the control group. Based on the GEE model, during postintervention II, physicians in the experimental group were 64% less likely to prescribe nonadherent antibiotics than those in the control group (odds ratio=0.36, 95% confidence interval=0.18,0.73). CONCLUSION: An educational intervention combining an antibiotic guide and a prescribing profile was effective in decreasing nonadherent antibiotic prescriptions. Repetition of the intervention at regular intervals may be necessary to maintain its effectiveness. [source] Are There Enough Doctors in My Rural Community?THE JOURNAL OF RURAL HEALTH, Issue 2 2009Perceptions of the Local Physician Supply ABSTRACT:,Purpose: To assess whether people in the rural Southeast perceive that there is an adequate number of physicians in their communities, assess how these perceptions relate to county physician-to-population (PtP) ratios, and identify other factors associated with the perception that there are enough local physicians. Methods: Adults (n = 4,879) from 150 rural counties in eight southeastern states responded through a telephone survey. Agreement or disagreement with the statement "I feel there are enough doctors in my community" constituted the principal outcome. Weighted chi-square analysis and a generalized estimating equation (GEE) assessed the strength of association between perceptions of an adequate physician workforce and county PtP ratios, individual characteristics, attitudes about and experiences with medical care, and other county characteristics. Findings: Forty-nine percent of respondents agreed there were enough doctors in their communities, 46% did not agree, and 5% were undecided. Respondents of counties with higher PtP ratios were only somewhat more likely to agree that there were enough local doctors (Pearson's correlation coefficient = 0.09, P < .001). Multivariate analyses revealed that perceiving that there were enough local physicians was more common among men, those 65 and older, whites, and those with lower regard for physician care. Perceptions that the local physician supply was inadequate were more common for those who had longer travel distances, problems with affordability, and little confidence in their physicians. Perceptions of physician shortages were more common in counties with higher poverty rates. Conclusions: County PtP ratios only partially account for rural perceptions that there are or are not enough local physicians. Perceptions of an adequate local physician workforce are also related to how much people value physicians' care and whether they face other barriers to care. [source] Attending and Resident Satisfaction with Feedback in the Emergency DepartmentACADEMIC EMERGENCY MEDICINE, Issue 2009Lalena M Yarris MD Abstract Objectives:, Effective feedback is critical to medical education. Little is known about emergency medicine (EM) attending and resident physician perceptions of feedback. The focus of this study was to examine perceptions of the educational feedback that attending physicians give to residents in the clinical environment of the emergency department (ED). The authors compared attending and resident satisfaction with real-time feedback and hypothesized that the two groups would report different overall satisfaction with the feedback they currently give and receive in the ED. Methods:, This observational study surveyed attending and resident physicians at 17 EM residency programs through web-based surveys. The primary outcome was overall satisfaction with feedback in the ED, ranked on a 10-point scale. Additional survey items addressed specific aspects of feedback. Responses were compared using a linear generalized estimating equation (GEE) model for overall satisfaction, a logistic GEE model for dichotomized responses, and an ordinal logistic GEE model for ordinal responses. Results:, Three hundred seventy-three of 525 (71%) attending physicians and 356 of 596 (60%) residents completed the survey. Attending physicians were more satisfied with overall feedback (mean score 5.97 vs. 5.29, p < 0.001) and with timeliness of feedback (odds ratio [OR] = 1.56, 95% confidence interval [CI] = 1.23 to 2.00; p < 0.001) than residents. Attending physicians were also more likely to rate the quality of feedback as very good or excellent for positive feedback, constructive feedback, feedback on procedures, documentation, management of ED flow, and evidence-based decision-making. Attending physicians reported time constraints as the top obstacle to giving feedback and were more likely than residents to report that feedback is usually attending initiated (OR = 7.09, 95% CI = 3.53 to 14.31; p < 0.001). Conclusions:, Attending physician satisfaction with the quality, timeliness, and frequency of feedback given is higher than resident physician satisfaction with feedback received. Attending and resident physicians have differing perceptions of who initiates feedback and how long it takes to provide effective feedback. Knowledge of these differences in perceptions about feedback may be used to direct future educational efforts to improve feedback in the ED. [source] Model Selection in Estimating EquationsBIOMETRICS, Issue 2 2001Wei Pan Summary. Model selection is a necessary step in many practical regression analyses. But for methods based on estimating equations, such as the quasi-likelihood and generalized estimating equation (GEE) approaches, there seem to be few well-studied model selection techniques. In this article, we propose a new model selection criterion that minimizes the expected predictive bias (EPB) of estimating equations. A bootstrap smoothed cross-validation (BCV) estimate of EPB is presented and its performance is assessed via simulation for overdispersed generalized linear models. For illustration, the method is applied to a real data set taken from a study of the development of ewe embryos. [source] Statistical methods for longitudinal research on bipolar disordersBIPOLAR DISORDERS, Issue 3 2003John Hennen Objectives: Outcomes research in bipolar disorders, because of complex clinical variation over-time, offers demanding research design and statistical challenges. Longitudinal studies involving relatively large samples, with outcome measures obtained repeatedly over-time, are required. In this report, statistical methods appropriate for such research are reviewed. Methods: Analytic methods appropriate for repeated measures data include: (i) endpoint analysis; (ii) endpoint analysis with last observation carried forward; (iii) summary statistic methods yielding one summary measure per subject; (iv) random effects and generalized estimating equation (GEE) regression modeling methods; and (v) time-to-event survival analyses. Results: Use and limitations of these several methods are illustrated within a randomly selected (33%) subset of data obtained in two recently completed randomized, double blind studies on acute mania. Outcome measures obtained repeatedly over 3 or 4 weeks of blinded treatment in active drug and placebo sub-groups included change-from-baseline Young Mania Rating Scale (YMRS) scores (continuous measure) and achievement of a clinical response criterion (50% YMRS reduction). Four of the methods reviewed are especially suitable for use with these repeated measures data: (i) the summary statistic method; (ii) random/mixed effects modeling; (iii) GEE regression modeling; and (iv) survival analysis. Conclusions: Outcome studies in bipolar illness ideally should be longitudinal in orientation, obtain outcomes data frequently over extended times, and employ large study samples. Missing data problems can be expected, and data analytic methods must accommodate missingness. [source] Social functioning and communication in children with cerebral palsy: association with disease characteristics and personal and environmental factorsDEVELOPMENTAL MEDICINE & CHILD NEUROLOGY, Issue 5 2010JEANINE M VOORMAN Aim, The objective of this longitudinal study was to describe the course of social functioning and communication in children with cerebral palsy (CP) over a 3-year period, its difference with the normative course, and its relationship with disease characteristics and personal and environmental factors. Method, Participants in this study were 110 children with CP (70 males, 40 females) with a mean age of 11 years and 3 months (SD 1y 8mo). Social functioning and communication were measured with the Vineland Adaptive Behavior Scales. Comparisons were made with normative data; data were analysed with generalized estimating equations. According to the Gross Motor Function Classification System (GMFCS), 50 of the 110 children were categorized as GMFCS level I, 16 as level II, 13 as level III, 13 as level IV, and 18 as level V. Results, The course of social functioning over a 3-year period showed an increase in restrictions in children with CP (p<0.001). Restrictions in communication increased more in children with the most severe forms of CP (p<0.001). In addition to disease characteristics (GMFCS category, presence of epilepsy, and speech problems), personal factors (externalizing behaviour problems) and environmental factors (having no siblings, low parental level of education, and parental stress) were associated with greater restrictions in social functioning and communication. Interpretation, The results indicate that it is important to focus not only on the medical treatment of children with CP, but also on their behavioural problems and social circumstances, and to support the parents so that social functioning and communication in these children may be improved. [source] Evidence of a complex association between dose, pattern and timing of prenatal alcohol exposure and child behaviour problemsADDICTION, Issue 1 2010Colleen M. O'Leary ABSTRACT Background There is a lack of evidence regarding the effect of dose, pattern and timing of prenatal alcohol exposure and behaviour problems in children aged 2 years and older. Methods A 10% random sample of women delivering a live infant in Western Australia (1995,96) were invited to participate in an 8-year longitudinal survey (78% response rate n = 2224); 85% were followed-up at 2 years, 73% at 5 years and 61% at 8 years. Alcohol consumption was classified by combining the overall dose, dose per occasion and frequency to reflect realistic drinking patterns. Longitudinal analysis was conducted using generalized estimating equations (GEE) to investigate the association between child behaviour as measured by the Child Behaviour Checklist at 2, 5 and 8 years of age and prenatal alcohol exposure collected 3 months postpartum for each trimester separately, adjusting for a wide range of confounding factors. Results Low levels of prenatal alcohol were not associated with child behaviour problems. There were increased odds of internalizing behaviour problems following heavy alcohol exposure in the first trimester; anxiety/depression [adjusted odds ratio (aOR) 2.82; 95% confidence interval (CI) 1.07,7.43] and somatic complaints (aOR 2.74; 95% CI 1.47,5.12) and moderate levels of alcohol exposure increased the odds of anxiety/depression (aOR 2.24; 95% CI 1.16,4.34). Conclusions Prenatal alcohol exposure at moderate and higher levels increased the odds of child behaviour problems with the dose, pattern and timing of exposure affecting the type of behaviour problems expressed. Larger studies with more power are needed to confirm these findings. [source] Incarceration and drug use patterns among a cohort of injection drug usersADDICTION, Issue 1 2009Kora DeBeck ABSTRACT Aims Drug law enforcement remains the dominant response to drug-related harm. However, the impact of incarceration on deterring drug use remains under-evaluated. We sought to explore the relationship between incarceration and patterns of drug use among people who inject drugs (IDU). Design Using generalized estimating equations (GEE), we examined the prevalence and correlates of injection cessation among participants in the Vancouver Injection Drug User Study followed over 9 years. In subanalyses, we used McNemar's tests and linear growth curve analyses to assess changes in drug use patterns before and after a period of incarceration among participants reporting incarceration and those not incarcerated. Findings Among 1603 IDU, 842 (53%) reported injection cessation for at least 6 months at some point during follow-up. In multivariate GEE analyses, recent incarceration was associated negatively with injection cessation [adjusted odds ratio (AOR) = 0.43, 95% confidence interval (CI) 0.37,0.50], whereas the use of methadone was associated positively with cessation (AOR = 1.38, 95% CI 1.22,1.56). In subanalyses assessing longitudinal patterns of drug use among incarcerated individuals and those not incarcerated over the study period, linear growth curve analyses indicated that there were no statistically significant differences in patterns of drug use between the two groups (all P > 0.05). Conclusions These observational data suggest that incarceration does not reduce drug use among IDU. Incarceration may inhibit access to mechanisms that promote injection cessation among IDU. In contrast, results indicate that methadone use is associated positively with injection cessation, independent of previous frequency of drug use. [source] Use of longitudinal data in genetic studies in the genome-wide association studies era: summary of Group 14GENETIC EPIDEMIOLOGY, Issue S1 2009Berit Kerner Abstract Participants analyzed actual and simulated longitudinal data from the Framingham Heart Study for various metabolic and cardiovascular traits. The genetic information incorporated into these investigations ranged from selected single-nucleotide polymorphisms to genome-wide association arrays. Genotypes were incorporated using a broad range of methodological approaches including conditional logistic regression, linear mixed models, generalized estimating equations, linear growth curve estimation, growth modeling, growth mixture modeling, population attributable risk fraction based on survival functions under the proportional hazards models, and multivariate adaptive splines for the analysis of longitudinal data. The specific scientific questions addressed by these different approaches also varied, ranging from a more precise definition of the phenotype, bias reduction in control selection, estimation of effect sizes and genotype associated risk, to direct incorporation of genetic data into longitudinal modeling approaches and the exploration of population heterogeneity with regard to longitudinal trajectories. The group reached several overall conclusions: (1) The additional information provided by longitudinal data may be useful in genetic analyses. (2) The precision of the phenotype definition as well as control selection in nested designs may be improved, especially if traits demonstrate a trend over time or have strong age-of-onset effects. (3) Analyzing genetic data stratified for high-risk subgroups defined by a unique development over time could be useful for the detection of rare mutations in common multifactorial diseases. (4) Estimation of the population impact of genomic risk variants could be more precise. The challenges and computational complexity demanded by genome-wide single-nucleotide polymorphism data were also discussed. Genet. Epidemiol. 33 (Suppl. 1):S93,S98, 2009. © 2009 Wiley-Liss, Inc. [source] Bivariate association analyses for the mixture of continuous and binary traits with the use of extended generalized estimating equationsGENETIC EPIDEMIOLOGY, Issue 3 2009Jianfeng Liu Abstract Genome-wide association (GWA) study is becoming a powerful tool in deciphering genetic basis of complex human diseases/traits. Currently, the univariate analysis is the most commonly used method to identify genes associated with a certain disease/phenotype under study. A major limitation with the univariate analysis is that it may not make use of the information of multiple correlated phenotypes, which are usually measured and collected in practical studies. The multivariate analysis has proven to be a powerful approach in linkage studies of complex diseases/traits, but it has received little attention in GWA. In this study, we aim to develop a bivariate analytical method for GWA study, which can be used for a complex situation in which continuous trait and a binary trait are measured under study. Based on the modified extended generalized estimating equation (EGEE) method we proposed herein, we assessed the performance of our bivariate analyses through extensive simulations as well as real data analyses. In the study, to develop an EGEE approach for bivariate genetic analyses, we combined two different generalized linear models corresponding to phenotypic variables using a seemingly unrelated regression model. The simulation results demonstrated that our EGEE-based bivariate analytical method outperforms univariate analyses in increasing statistical power under a variety of simulation scenarios. Notably, EGEE-based bivariate analyses have consistent advantages over univariate analyses whether or not there exists a phenotypic correlation between the two traits. Our study has practical importance, as one can always use multivariate analyses as a screening tool when multiple phenotypes are available, without extra costs of statistical power and false-positive rate. Analyses on empirical GWA data further affirm the advantages of our bivariate analytical method. Genet. Epidemiol. 2009. © 2008 Wiley-Liss, Inc. [source] | |||||||||||||||||||||||||||||||