Browsing by Author "Li, Jing"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Analysis of Repeated Measures in the Presence of Missing Observations due to Dropout
    (2013) Li, Jing; Smith, Paul J; Tsong, Yi; Mathematics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Incomplete data is common in both observational studies and clinical trials. Ignoring missing data may produce seriously biased estimators and could lead to misleading results. During the last three decades, a vast amount of work has been done in this area. The approaches can be classified into the following main categories: imputation methods, likelihood-based methods and inverse probability weighting methods. Longitudinal and crossover studies with repeated measures are particularly subject to missing observations. Various methods, including generalized estimating equations (GEE) (Liang and Zeger, 1986), weighted GEE (WGEE) (Robins, Rotnitzky and Zhao, 1995) and multiple imputations, have been proposed to cope with missing data in longitudinal studies. However, very few researchers have explored the missing data issue in crossover studies. In addition to reviewing and critiquing the methods dealing with missing observations in general and in repeated measures, in this dissertation, we propose a new weighting approach for GEE to estimate the regression parameters in crossover studies. The proposed method provides consistent and asymptotically normally distributed estimators. Simulation and asymptotic efficiency results indicate that the proposed estimators are more efficient than both regular GEE and WGEE. Applications of the proposed method are illustrated with real data.
  • Thumbnail Image
    Item
    A MULTISCALE APPROACH TO PARAMETERIZATION OF BURNING MODELS FOR POLYMERIC MATERIALS.
    (2014) Li, Jing; Stoliarov, Stanislav I.; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    A quantitative understanding of the processes that occur in the condensed phase of burning materials is critical for the prediction of ignition and growth of fires. A number of models have been developed to simulate these condensed phase processes. The main issue that remains to be resolved is the determination of parameters to be input into these models, which are formulated in terms of fundamental physical and chemical properties. This work is focused on developing and applying a systematic methodology for the characterization of polymeric materials based on milligram-scale and bench-scale tests to isolate specific chemical and/or physical processes in each scale level. The entire study is divided into two parts corresponding to two different scale tests and analysis. The first part is concentrated on the measurement of kinetics and thermodynamics of the thermal degradation of polymeric materials at milligram-scale. It employs a simultaneous thermal analysis instrument capable of thermogravimetric analysis (TGA) and differential scanning calorimetry (DSC). A numerical model is utilized to fit TGA data and obtain thermal degradation kinetics to a continuum pyrolysis model. This model is subsequently employed to analyze DSC heat flow and extract sensible, melting and degradation reaction heats. The extracted set of kinetic and thermodynamic parameters is shown to simultaneously reproduce TGA and DSC curves for a set of 15 widely used commercial polymers. Then the first part of this study was extended to bench-scale gasification experiments that were carried out in a controlled atmosphere pyrolysis apparatus (CAPA) which has been recently developed in our group. The CAPA is used to measure material gravimetric and thermal changes during thermal decomposition in an anaerobic atmosphere with a capability of analyzing material thermal transport properties. These properties, combined with material kinetics and thermodynamics from the first part of this study, were used as inputs for a pyrolysis model to simulate one-dimensional polymer gasification under wide range of external heat fluxes. The predictive power of this model and validity of its parameters are verified against the results of gasification experiments. 7 out of 15 polymers were validated in bench-scale and the parameterized simulations are in reasonable agreement with experimental data under wide range of conditions.