Statistics and Probability Commons^™

Least Absolute Value Vs. Least Squares Estimation And Inference Procedures In Regression Models With Asymmetric Error Distributions, Terry E. Dielman

Journal of Modern Applied Statistical Methods

A Monte Carlo simulation is used to compare estimation and inference procedures in least absolute value (LAV) and least squares (LS) regression models with asymmetric error distributions. Mean square errors (MSE) of coefficient estimates are used to assess the relative efficiency of the estimators. Hypothesis tests for coefficients are compared on the basis of empirical level of significance and power.

Variance-Mean Relationships To Analyze Large Survey Data With Application To Health Expenditure Data, Wenli Luo

Legacy Theses & Dissertations (2009 - 2024)

A great deal of work has been done in cost analysis in the last several decades. However, relatively little has been done to learn how efficiently to address the relationship between the variance and mean of the response distribution and how this will affect the choice of an appropriate generalized linear model.

An Adaptive Bayesian Approach To Bernoulli-Response Clinical Trials, Andrew W. Stacey

Theses and Dissertations

Traditional clinical trials have been inefficient in their methods of dose finding and dose allocation. In this paper a four-parameter logistic equation is used to model the outcome of Bernoulli-response clinical trials. A Bayesian adaptive design is used to fit the logistic equation to the dose-response curve of Phase II and Phase III clinical trials. Because of inherent restrictions in the logistic model, symmetric candidate densities cannot be used, thereby creating asymmetric jumping rules inside the Markov chain Monte Carlo algorithm. An order restricted Metropolis-Hastings algorithm is implemented to account for these limitations. Modeling clinical trials in a Bayesian framework …

A Simulation-Based Approach For Evaluating Gene Expression Analyses, Carly Ruth Pendleton

Theses and Dissertations

Microarrays enable biologists to measure differences in gene expression in thousands of genes simultaneously. The data produced by microarrays present a statistical challenge, one which has been met both by new modifications of existing methods and by completely new approaches. One of the difficulties with a new approach to microarray analysis is validating the method's power and sensitivity. A simulation study could provide such validation by simulating gene expression data and investigating the method's response to changes in the data; however, due to the complex dependencies and interactions found in gene expression data, such a simulation would be complicated and …

Choosing Smoothing Parameters For Exponential Smoothing: Minimizing Sums Of Squared Versus Sums Of Absolute Errors, Terry E. Dielman

Journal of Modern Applied Statistical Methods

When choosing smoothing parameters in exponential smoothing, the choice can be made by either minimizing the sum of squared one-step-ahead forecast errors or minimizing the sum of the absolute onestep- ahead forecast errors. In this article, the resulting forecast accuracy is used to compare these two options.

Combining Information From Two Surveys To Estimate County-Level Prevalence Rates Of Cancer Risk Factors And Screening, Trivellore E. Raghuanthan, Dawei Xie, Nathaniel Schenker, Van Parsons, William W. Davis, Kevin W. Dodd, Eric J. Feuer

The University of Michigan Department of Biostatistics Working Paper Series

Cancer surveillance requires estimates of the prevalence of cancer risk factors and screening for small areas such as counties. Two popular data sources are the Behavioral Risk Factor Surveillance System (BRFSS), a telephone survey conducted by state agencies, and the National Health Interview Survey (NHIS), an area probability sample survey conducted through face-to-face interviews. Both data sources have advantages and disadvantages. The BRFSS is a larger survey, and almost every county is included in the survey; but it has lower response rates as is typical with telephone surveys, and it does not include subjects who live in households with no …

Modeling And Simulation Of Value -At -Risk In The Financial Market Area, Xiangyin Zheng

Doctoral Dissertations

Value-at-Risk (VaR) is a statistical approach to measure market risk. It is widely used by banks, securities firms, commodity and energy merchants, and other trading organizations. The main focus of this research is measuring and analyzing market risk by modeling and simulation of Value-at-Risk for portfolios in the financial market area. The objectives are (1) predicting possible future loss for a financial portfolio from VaR measurement, and (2) identifying how the distributions of the risk factors affect the distribution of the portfolio. Results from (1) and (2) provide valuable information for portfolio optimization and risk management.

The model systems chosen …

A Comparison For Longitudinal Data Missing Due To Truncation, Rong Liu

Theses and Dissertations

Many longitudinal clinical studies suffer from patient dropout. Often the dropout is nonignorable and the missing mechanism needs to be incorporated in the analysis. The methods handling missing data make various assumptions about the missing mechanism, and their utility in practice depends on whether these assumptions apply in a specific application. Ramakrishnan and Wang (2005) proposed a method (MDT) to handle nonignorable missing data, where missing is due to the observations exceeding an unobserved threshold. Assuming that the observations arise from a truncated normal distribution, they suggested an EM algorithm to simplify the estimation.In this dissertation the EM algorithm is …

Jmasm16: Pseudo-Random Number Generation In R For Some Univariate Distributions, Hakan Demirtas

Journal of Modern Applied Statistical Methods

An increasing number of practitioners and applied researchers started using the R programming system in recent years for their computing and data analysis needs. As far as pseudo-random number generation is concerned, the built-in generator in R does not contain some important univariate distributions. In this article, complementary R routines that could potentially be useful for simulation and computation purposes are provided.

Pseudo-Random Number Generation In R For Commonly Used Multivariate Distributions, Hakan Demirtas

Journal of Modern Applied Statistical Methods

An increasing number of practitioners and applied statisticians have started using the R programming system in recent years for their computing and data analysis needs. As far as pseudo-random number generation is concerned, the built-in generator in R does not contain multivariate distributions. In this article, R routines for widely used multivariate distributions are presented.

Not All Effects Are Created Equal: A Rejoinder To Sawilowsky, J. Kyle Roberts, Robin K. Henson

Journal of Modern Applied Statistical Methods

In the continuing debate over the use and utility of effect sizes, more discussion often helps to both clarify and syncretize methodological views. Here, further defense is given of Roberts & Henson (2002) in terms of measuring bias in Cohen’s d, and a rejoinder to Sawilowsky (2003) is presented.

You Think You’Ve Got Trivials?, Shlomo S. Sawilowsky

Journal of Modern Applied Statistical Methods

Effect sizes are important for power analysis and meta-analysis. This has led to a debate on reporting effect sizes for studies that are not statistically significant. Contrary and supportive evidence has been offered on the basis of Monte Carlo methods. In this article, clarifications are given regarding what should be simulated to determine the possible effects of piecemeal publishing trivial effect sizes.

A Simulation Study Of The Impact Of Forecast Recovery For Control Charts Applied To Arma Processes, John N. Dyer, B. Michael Adams, Michael D. Conerly

Journal of Modern Applied Statistical Methods

Forecast-based schemes are often used to monitor autocorrelated processes, but the resulting forecast recovery has a significant effect on the performance of control charts. This article describes forecast recovery for autocorrelated processes, and the resulting simulation study is used to explain the performance of control charts applied to forecast errors.

Jmasm3: A Method For Simulating Systems Of Correlated Binary Data, Todd C. Headrick

Journal of Modern Applied Statistical Methods

An efficient algorithm is derived for generating systems of correlated binary data. The procedure allows for the specification of all pairwise correlations within each system. Intercorrelations between systems can be specified qualitatively. The procedure requires the simultaneous solution of a system of equations for obtaining the threshold probabilities to generate each system of binary data. A numerical example is provided to demonstrate that the procedure generates correlated binary variables that yield correlations in close agreement with the specified population correlations.

Optimum Preventive Maintenance Policies For The Amraam Missile, Scott J. Ruflin

Theses and Dissertations

The overall objective of this research effort was to formulate a preventive maintenance strategy for AMRAAM missiles subject to extended captive carry flight time. A preventive maintenance policy is only applicable if the item in question is aging, or deteriorating with time. Therefore, a supporting objective of this research is to characterize the aging process of the missile system through a non-parametric analysis of its Mean Residual Life (MRL) function. Three non-parametric, censored-data MRL function estimation techniques discussed in the literature are examined via a numerical example. All three estimation techniques provide MRL functions that exhibit greatly exaggerated decreasing trends …

Monte Carlo Simulation In Environmental Risk Assessment--Science, Policy And Legal Issues, Susan R. Poulter

RISK: Health, Safety & Environment (1990-2002)

Dr. Poulter notes that agencies should anticipate judicial requirements for justification of Monte Carlo simulations and, meanwhile, should consider, e.g., whether their use will make risk assessment policy choices more opaque or apparent.

Regionalization Of Flood Data Using Probability Distributions And Their Parameters, Nageshwar Rao Bhaskar, Carol Alf O'Connor, Harold Andrew Myers, William Paul Puckett

KWRRI Research Reports

The U. S. Geological survey recently used the method of residuals to delineate seven flood regions for the State of Kentucky. As an alternative approach, the FASTCLUS clustering procedure of the Statistical Analysis system (SAS) is used in this study to delineate five to six cluster regions in conjunction with statistical properties of the AMF series, like the coefficient of variation as estimated using method of L-moments, LCV, the parameters of the EVl and GEV flood frequency distributions, and the specific mean annual flood, QSP. For both cluster and USGS flood regions, regionalized flood frequency growth curves are developed and …

Monte Carlo Simulation Of The Game Of Twenty-One, Douglas E. Loer

All Graduate Plan B and other Reports, Spring 1920 to Spring 2023

The purpose of this paper is to demonstrate the application of computer simulation to the game of Twenty-One to predict a player's expected return from the game. Twenty-One has traditionally been one of the most popular casino games and has attracted much effort to accurately estimate the house's true advantage. Probability theory has been tried, but the thousands of different combinations of cards possible in all hands throughout the entire pack make it practically impossible to apply probability theory without overlooking some possibilities. For this reason, Twenty-One is a perfect candidate for simulation. By blocking several simulations, normal theory can …

The Practical Solutions And Computer Program Of Two Statistical Problems In Simulation, Yee Fong

All Graduate Plan B and other Reports, Spring 1920 to Spring 2023

In the last several years monte-carlo simulation has become a major tool for the analysis of complex queuing systems which are no readily amenable to analysis by conventional mathematical methods. By a complex queueing system is mean a system composed of, physically or by analogy, a network of stations or servers with traffic units moving through all or some of the servers, into the system and out or around within the system. A traffic unit desiring service by a server may either have to enter a queue first or may be served immediately. Such systems have been simulated often with …

Simulating Regional Interindustry Models For Western States, William A. Schaffer, Kong Chu

Applications

Although regional input-output models are now most frequently constructed on the basis of reasonably adequate surveys, simulation (estimating) techniques not based on original survey data are still in use by many regional scientists for quick and less costly results. We will modify our original aggregation procedures, examine our results through several statistical tests of tables constructed for three Western states, and discuss a possible correction procedure for improving raw estimates of interindustry transactions.