Design and analysis for three level hierarchical structures with count response

In numerous intervention studies and education field trials, random assignment to treatment occurs in clusters rather than at the level of observation. This departure of random assignment of units may be due to logistics, political feasibility, or ecological validity. Data within the same cluster or grouping are often correlated. Application of traditional regression techniques, which assume independence between observations, to clustered data produce consistent parameter estimates. However such estimators are often inefficient as compared to methods which incorporate the clustered nature of the data into the estimation procedure (Neuhaus 1993).1 Multilevel models, also known as random effects or random components models, can be used to account for the clustering of data by estimating higher level, or group, as well as lower level, or individual variation. Designing a study, in which the unit of observation is nested within higher level groupings, requires the determination of sample sizes at each level. This study investigates the design and analysis of various sampling strategies for a 3-level repeated measures design on the parameter estimates when the outcome variable of interest follows a Poisson distribution. ^ Results study suggest that second order PQL estimation produces the least biased estimates in the 3-level multilevel Poisson model followed by first order PQL and then second and first order MQL. The MQL estimates of both fixed and random parameters are generally satisfactory when the level 2 and level 3 variation is less than 0.10. However, as the higher level error variance increases, the MQL estimates become increasingly biased. If convergence of the estimation algorithm is not obtained by PQL procedure and higher level error variance is large, the estimates may be significantly biased. In this case bias correction techniques such as bootstrapping should be considered as an alternative procedure. For larger sample sizes, those structures with 20 or more units sampled at levels with normally distributed random errors produced more stable estimates with less sampling variance than structures with an increased number of level 1 units. For small sample sizes, sampling fewer units at the level with Poisson variation produces less sampling variation, however this criterion is no longer important when sample sizes are large. ^ 1Neuhaus J (1993). “Estimation efficiency and Tests of Covariate Effects with Clustered Binary Data”. Biometrics , 49, 989–996^

Uncertainty analysis of cost effectiveness in a tailored intervention to promote screening for colorectal cancer

Background. Screening for colorectal cancer (CRC) is considered cost effective but screening compliance in the US remains low. There have been very few studies on economic analyses of screening promotion strategies for colorectal cancer. The main aim of the current study is to conduct a cost effectiveness analysis (CEA) and examine the uncertainty involved in the results of the CEA of a tailored intervention to promote screening for CRC among patients of a multispeciality clinic in Houston, TX. ^ Methods. The two intervention arms received a PC based tailored program and web based educational information to promote CRC screening. The incremental cost of implementing a tailored PC based program was compared to the website based education and the status quo of no intervention for each unit of effect after 12 months of delivering the intervention. Uncertainty analysis in the point estimates of cost and effect was conducted using nonparametric bootstrapping. ^ Results. The cost of implementing a web based educational intervention was $36.00 per person and the cost of the tailored PC based interactive intervention was $43.00 per person. The additional cost per person screened for the web-based strategy was $2374 and the effect of the tailored intervention was negative. ^

Improving the Quality of Life of spousal caregivers of stroke survivors: A cost effectiveness analysis

Back ground and Purpose. There is a growing consensus among health care researchers that Quality of Life (QoL) is an important outcome and, within the field of family caregiving, cost effectiveness research is needed to determine which programs have the greatest benefit for family members. This study uses a multidimensional approach to measure the cost effectiveness of a multicomponent intervention designed to improve the quality of life of spousal caregivers of stroke survivors. Methods. The CAReS study (Committed to Assisting with Recovery after Stroke) was a 5-year prospective, longitudinal intervention study for 159 stroke survivors and their spousal caregivers upon discharge of the stroke survivor from inpatient rehabilitation to their home. CAReS cost data were analyzed to determine the incremental cost of the intervention per caregiver. The mean values of the quality-of-life predictor variables of the intervention group of caregivers were compared to the mean values of usual care groups found in the literature. Significant differences were then divided into the cost of the intervention per caregiver to calculate the incremental cost effectiveness ratio for each predictor variable. Results. The cost of the intervention per caregiver was approximately $2,500. Statistically significant differences were found between the mean scores for the Perceived Stress and Satisfaction with Life scales. Statistically significant differences were not found between the mean scores for the Self Reported Health Status, Mutuality, and Preparedness scales. Conclusions. This study provides a prototype cost effectiveness analysis on which researchers can build. Using a multidimensional approach to measure QoL, as used in this analysis, incorporates both the subjective and objective components of QoL. Some of the QoL predictor variable scores were significantly different between the intervention and comparison groups, indicating a significant impact of the intervention. The estimated cost of the impact was also examined. In future studies, a scale that takes into account both the dimensions and the weighting each person places on the dimensions of QoL should be used to provide a single QoL score per participant. With participant level cost and outcome data, uncertainty around each cost-effectiveness ratio can be calculated using the bias-corrected percentile bootstrapping method and plotted to calculate the cost-effectiveness acceptability curves.^

Prediction of sepsis in the burn intensive care unit patient

Sepsis is a significant cause for multiple organ failure and death in the burn patient, yet identification in this population is confounded by chronic hypermetabolism and impaired immune function. The purpose of this study was twofold: 1) determine the ability of the systemic inflammatory response syndrome (SIRS) and American Burn Association (ABA) criteria to predict sepsis in the burn patient; and 2) develop a model representing the best combination of clinical predictors associated with sepsis in the same population. A retrospective, case-controlled, within-patient comparison of burn patients admitted to a single intensive care unit (ICU) was conducted for the period January 2005 to September 2010. Blood culture results were paired with clinical condition: "positive-sick"; "negative-sick", and "screening-not sick". Data were collected for the 72 hours prior to each blood culture. The most significant predictors were evaluated using logistic regression, Generalized Estimating Equations (GEE) and ROC area under the curve (AUC) analyses to assess model predictive ability. Bootstrapping methods were employed to evaluate potential model over-fitting. Fifty-nine subjects were included, representing 177 culture periods. SIRS criteria were not found to be associated with culture type, with an average of 98% of subjects meeting criteria in the 3 days prior. ABA sepsis criteria were significantly different among culture type only on the day prior (p = 0.004). The variables identified for the model included: heart rate>130 beats/min, mean blood pressure<60 mmHg, base deficit<-6 mEq/L, temperature>36°C, use of vasoactive medications, and glucose>150 mg/d1. The model was significant in predicting "positive culture-sick" and sepsis state, with AUC of 0.775 (p < 0.001) and 0.714 (p < .001), respectively; comparatively, the ABA criteria AUC was 0.619 (p = 0.028) and 0.597 (p = .035), respectively. SIRS criteria are not appropriate for identifying sepsis in the burn population. The ABA criteria perform better, but only for the day prior to positive blood culture results. The time period useful to diagnose sepsis using clinical criteria may be limited to 24 hours. A combination of predictors is superior to individual variable trends, yet algorithms or computer support will be necessary for the clinician to find such models useful. ^