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^

HPV vaccine coverage in Texas counties: An application of multilevel, small area estimation

Health departments, research institutions, policy-makers, and healthcare providers are often interested in knowing the health status of their clients/constituents. Without the resources, financially or administratively, to go out into the community and conduct health assessments directly, these entities frequently rely on data from population-based surveys to supply the information they need. Unfortunately, these surveys are ill-equipped for the job due to sample size and privacy concerns. Small area estimation (SAE) techniques have excellent potential in such circumstances, but have been underutilized in public health due to lack of awareness and confidence in applying its methods. The goal of this research is to make model-based SAE accessible to a broad readership using clear, example-based learning. Specifically, we applied the principles of multilevel, unit-level SAE to describe the geographic distribution of HPV vaccine coverage among females aged 11-26 in Texas.^ Multilevel (3 level: individual, county, public health region) random-intercept logit models of HPV vaccination (receipt of ≥ 1 dose Gardasil® ) were fit to data from the 2008 Behavioral Risk Factor Surveillance System (outcome and level 1 covariates) and a number of secondary sources (group-level covariates). Sampling weights were scaled (level 1) or constructed (levels 2 & 3), and incorporated at every level. Using the regression coefficients (and standard errors) from the final models, I simulated 10,000 datasets for each regression coefficient from the normal distribution and applied them to the logit model to estimate HPV vaccine coverage in each county and respective demographic subgroup. For simplicity, I only provide coverage estimates (and 95% confidence intervals) for counties.^ County-level coverage among females aged 11-17 varied from 6.8-29.0%. For females aged 18-26, coverage varied from 1.9%-23.8%. Aggregated to the state level, these values translate to indirect state estimates of 15.5% and 11.4%, respectively; both of which fall within the confidence intervals for the direct estimates of HPV vaccine coverage in Texas (Females 11-17: 17.7%, 95% CI: 13.6, 21.9; Females 18-26: 12.0%, 95% CI: 6.2, 17.7).^ Small area estimation has great potential for informing policy, program development and evaluation, and the provision of health services. Harnessing the flexibility of multilevel, unit-level SAE to estimate HPV vaccine coverage among females aged 11-26 in Texas counties, I have provided (1) practical guidance on how to conceptualize and conduct modelbased SAE, (2) a robust framework that can be applied to other health outcomes or geographic levels of aggregation, and (3) HPV vaccine coverage data that may inform the development of health education programs, the provision of health services, the planning of additional research studies, and the creation of local health policies.^

Corporate decision-making: A case study of decision support systems and financial performance in health care organizations

The purpose of this study was twofold: (1) To describe the relation of the intensity of DSS implementation to financial performance as an empirical exploration of improved performance at the organizational level. (2) To describe the relation of the intensity of DSS implementation to the type of organizational decision culture. A multiple case study design was utilized to compare three groups of paired cases. A pattern matching strategy was applied in this study. Four predictions were specified and compared to the empirical data. A progressively upward trend in the scores was predicted for the following theoretical relationships. (1) The greater the number of DSSs, the higher the sophistication index. (2) The greater the number of DSSs, the higher the financial ratios. (3) The greater the number of DSSs, the higher the culture score. (4) The higher the culture score, the higher the financial ratios. The data did not support any of the predicted trends except the relation between the number of DSSs and the financial ratios. The Income/Revenue ratio indicates the efficiency of a company's operations. One would expect that this ratio would be most affected by the operational and financial decision support systems. The majority of the systems measured in the study supported decisions tangential to the patient service areas. The evidence suggested that the type and number of decision support systems affects the bottom line. ^

Correlation of tuberculosis and human immunodeficiency virus in Harris County, Texas from 2009 through 2010 using Geographic Information Systems

A population based ecological study was conducted to identify areas with a high number of TB and HIV new diagnoses in Harris County, Texas from 2009 through 2010 by applying Geographic Information Systems to determine whether distinguished spatial patterns exist at the census tract level through the use of exploratory mapping. As of 2010, Texas has the fourth highest occurrence of new diagnoses of HIV/AIDS and TB.[31] The Texas Department of State Health Services (DSHS) has identified HIV infected persons as a high risk population for TB in Harris County.[29] In order to explore this relationship further, GIS was utilized to identify spatial trends. ^ The specific aims were to map TB and HIV new diagnoses rates and spatially identify hotspots and high value clusters at the census tract level. The potential association between HIV and TB was analyzed using spatial autocorrelation and linear regression analysis. The spatial statistics used were ArcGIS 9.3 Hotspot Analysis and Cluster and Outlier Analysis. Spatial autocorrelation was determined through Global Moran's I and linear regression analysis. ^ Hotspots and clusters of TB and HIV are located within the same spatial areas of Harris County. The areas with high value clusters and hotspots for each infection are located within the central downtown area of the city of Houston. There is an additional hotspot area of TB located directly north of I-10 and a hotspot area of HIV northeast of Interstate 610. ^ The Moran's I Index of 0.17 (Z score = 3.6 standard deviations, p-value = 0.01) suggests that TB is statistically clustered with a less than 1% chance that this pattern is due to random chance. However, there were a high number of features with no neighbors which may invalidate the statistical properties of the test. Linear regression analysis indicated that HIV new diagnoses rates (β=−0.006, SE=0.147, p=0.970) and census tracts (β=0.000, SE=0.000, p=0.866) were not significant predictors of TB new diagnoses rates. ^ Mapping products indicate that census tracts with overlapping hotspots and high value clusters of TB and HIV should be a targeted focus for prevention efforts, most particularly within central Harris County. While the statistical association was not confirmed, evidence suggests that there is a relationship between HIV and TB within this two year period.^