Imprecise Probability Models for Logistic Regression
View/Open
Date
20121030Author
Bataineh, Osama
Type
ThesisDegree Level
DoctoralAbstract
Imprecise probability models are applied to logistic regression to produce interval
estimates of regression parameters. The lengths of interval estimates are of
main interest. Shorter interval estimates correspond to less imprecision in regression
parameters estimates.
This thesis applies imprecise probabilistic methods to the logit model. Imprecise
logistic regression, briefly called ImpLogit model, is presented and established for
the first time. ImpLogit model is applied based on an inferential paradigm that
applies Bayes theorem to a family of prior distributions, yielding interval posterior
probabilities. The socalled interval estimates of regression parameters are computed
using MetropolisHastings algorithm.
Two imprecise prior probability models are applied to 2parameter ImpLogit
model : the imprecise Dirichlet model (IDM) and the imprecise logitnormal model
(ILnM). The 2parameter ImpLogit model is fitted using real life doseresponse data.
This takes into account the cases of increasing, decreasing and mixedbelief ImpLogit
models.
The relation between the lengths of interval estimates of regression parameters
and both of covariate values and imprecise prior hyperparameters, in 2parameter
ImpLogit model, is studied by simulation. Different designs are applied in order to
investigate a way to shorten the lengths of interval estimates of regression parameters.
Having covariate fixed values to surround the prior believed median value
of the logistic distribution results in reducing the imprecision in interval estimates.
Fixing covariate values around the prior believed median value in a short range
increases the lengths of interval estimates.
The number of fixed covariate values (say number of distinct dose levels in a
doseresponse experiment) affects the produced imprecision. A larger number of
fixed covariate values increases the lengths of interval estimates. Therefore, a good
design has a small number of fixed covariate values, located and spread out not in
a short range.
ImpLogit model designs that are recommended by the simulation study, are compared to optimal designs in the frequentist approach using Fisher information matrix
(FIM). Designs in FIM agree with designs that reduce imprecision in 2parameter
ImpLogit model, in the necessity of having covariate values to be fixed around the
prior believed median value of the logistic distribution, not in a short range.
Degree
Doctor of Philosophy (Ph.D.)Department
Mathematics and StatisticsProgram
MathematicsSupervisor
Bickis, Mikelis G.Committee
Soteros, Chris; Laverty, William H.; Liu, Juxin; Horsch, Michael C.; Augustin, ThomasCopyright Date
September 2012Subject
Imprecise probability model
imprecise Dirichlet model
imprecise
logitnormal model
aggregation property
ImpLogit model
interval estimate
Collections
Related items
Showing items related by title, author, creator and subject.

Modeling gene regulatory networks using a statespace model with time delays
Koh, Chu Shin (20080317)Computational gene regulation models provide a means for scientists to draw biological inferences from largescale gene expression data. The expression data used in the models usually are obtained in a time series in ... 
Agentbased modeling and System Dynamics modeling on transmission of Tuberculosis in Saskatchewan
Tian, Yuan (20120118)The desire to better understand the transmission of infectious disease in the real world has motivated the representation of epidemic diffusion processes in the context of qualitative simulation as a computational model ... 
Numerical modelling of unsaturated flow in vertical and inclined waste rock layers using the seep/w model
Wilson, Jaime Alexis (20030616)Conventional disposal of waste rock results in the construction of benches with interbedded fine and coarse layers dipping at the angle of repose. The waste rock benches are typically 20meters in height and are constructed ...