Physical Sciences and Mathematics Commons^™

A Nonparametric Solution For Finding The Optimum Useful Life Of Equipment, Barry T. Stoll

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

It is often the case that equipment used by industry must be replaced with new equipment from time to time either because frequent malfunctions make it too costly to repair, or because the equipment has simply worn out. The new equipment often has the nature of either malfunctioning soon after installation due to manufacturing defects, or functioning for an extended period of time because it is free of these defects. For this reason, equipment is often given a preliminary running called the burn-in which gives no useful output but merely tests for manufacturing defects. Also, after a given amount of …

Computer Programs Supporting The Teaching Of Statistics, Chien-Hwa Liu

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

During the past few years there has been an increasing interest in developing computer packages to enhance the teaching of elementary statistics. The conventional ways of teaching statistics have used such devices as desk calculators, tables of functions, short-cut calculating formulas and electronic calculators, etc. to manipulate the involved computations. Electronic computers, in the past decade, have been broadly used in universities and colleges in many ways. It is only natural to extend the use of computers to the teaching function. Remote terminals can now be installed in any classroom and bring the computer to the students.

Canonical Analysis Of Several Sets Of Variables, Chong S. Kim

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

Many procedures have been proposed for analyzing and describing multivariate dependence structure.

Partial correlation, multiple correlation, canonical correlation, principal component and factor analysis are used to analyze the dependence structures of a multinormal population.

For a partial correlation analysis it is necessary to decide which variables are to be correlated and which of the remaining variables must be held constant.

Multiple correlation demands that one variable be dependent upon some or all of the remaining variates.

For a canonical correlation, the variables must be collected into two or more sets. The factor analysis technique is for explaining the covariances of …

A Monte Carlo Comparison Of Nonparametric Reliability Estimators, Jia-Jinn Yueh

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

It is very difficult to construct a reliability model for a complex system. However, the reliability model for a series configuration is relatively simple. In the simplest case in which the components are mutually independent, the system reliability can be represented as follows:

R_s(x) = ∑ⁿ_i=1R_i(x),

where R_i is the reliability for the i^th component. It is also known that for moderate levels of system reliability for large systems, the component reliability must be high.

Extreme Value Theory indicates that under very general conditions, the initial form of the distribution function …

U. S. U. Mathematical Programming Package, R. Gary Goodwin

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

Solving mathematical programming problems without the aid of electronic computers is very time consuming even for a mathematical model consisting of only a few constraints and variables. The objective of this report is to illustrate the use of mathematical programming computer routines available at Utah State University. Computer routines discussed are the International Business Machines (IBM), Mathematical Programming System (MPS) package, a quadratic programming routing, a zero-one integer programming routing, and a transportation code. The MPS package is a product of IBM; the quadratic programming routing was develop by the author: the last three routines were obtained from the IBM …

A Monte Carlo Evaluation Of A Nonparametric Technique For Estimating The Hazard Function, Sheng Jia Lin

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

This research is primarily concerned with the estimation of the Hazard functions, the Hazard function is the failure rate at time t, and is defined as -R '(t)/R(t), so it plays an important role in Reliability.

In order to compare and evaluate the estimation methods, it is convenient to select one distribution in this research. Since the Weibull distribution is a useful distribution in Reliability, the Weibull distribution is used in this paper.

A Bayes Rule For The Symmetric Multiple Comparisons Problem, Aban Nawabi

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

Many procedures have been proposed for the symmetric multiple comparisons problem in recent years. These include a "protected" least significant difference procedure due to Fisher (FSD), a multiple range rule by Duncan, and HSD (honest significant difference) procedure by Tukey, and a procedure for testing all contrasts by Scheffe.

The tests which are mentioned above are either comparison-wise or experiment-wise approaches. The probability of Type I error is intended to be a for all comparisons made when an experiment-wise approach is used. Whereas, the probability of Type I error referred to each comparison is a comparison-wise approach. Both approaches can …

A Non-Parametric Sequential Signed-Rank Test And Comparison With The Sequential T-Test, Kuei-Mei Even Sher

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

Sequential analysis is a method of statistical inference whose characteristic feature is that the number of observations required by the procedure is not determined in advance of the experiment. The decision to terminate the experiment depends, at each stage, on the results of the observations previously made.

So far the general sequential t-test (without truncation) is a standard test for the mean of a normal distribution. A truncated sequential t-test has been developed by Suich and Iglewicz (1970). The difference between these two tests is that the former has a fixed critical value whenever the type I error (α) and …

Solutions Of The Problem Of Finding Confidence Intervals For The Two Normal Population With Unequal Variances, Ing-Haur Liu

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

Comparison of the means of two normal populations is a simpler problem when the variance (if unknown) are assumed to be equal than it is when they are not equal. The main concern of this report is the latter case also called the Behrens [4] - Fisher [5] problem.

In this report the solutions proposed by Behrens-Fisher, Scheffe [10], Welch [12], Banerjee [3] and Hajek [8], will be described and compared. To this problem Scheffe proposed a solution which has the advantage that no special table is necessary for its use, since the variate has an exact "Student's t" distribution. …

Nonparametric Test Of Fit, Frena Nawabi

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

Most statistical methods require assumptions about the populations from which samples are taken. Usually these methods measure the parameters, such as variance, standard deviations, means, etc., of the respective populations. One example is the assumption that a given population can be approximated closely with a normal curve. Since these assumptions are not always valid, statisticians have developed several alternate techniques known as nonparametric tests. The models of such tests do not specify conditions about population parameters.

Certain assumptions, such as (1) observations are independent and (2) the variable being studied has underlying continuity, are associated with most nonparametric tests. However, …

Bayesian Estimate Of System Reliability, Naresh Shah

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

A Bayesian estimate of reliability for each component in the system of n-components, each exponentially distributed, is developed which utilizes the basic notion of loss in estimation theory. Here we assume that each component is independently dis­tributed. In reliability estimation, the loss associated with over­estimation is usually greater than the loss associated with under­estimation; and hence loss function can be a very useful tool. The prior distribution and loss function of reliability considered in this paper are flexible to be compatible with other situations in which reliability estimates are required. When the loss function is symmetric and no prior information …

Bayesian Inference For Decision Making, Ming-Yih Kao

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

In recent years, Bayesian inference has become very popular in applied statistics. This study will present the fundamental concept of Bayesian inference and the basic techniques of application to statistical quality control, marketing research, and other related fields.

Stochastic Processes Model And Its Application In Operations Research, Chun Yuan Hsu

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

Just as the probability theory is regarded as the study of mathematical models of random phenomena, the theory of stochastic processes plays an important role in the investigation of random phenomena depending on time. A random phenomenon that arises through a process which is developing in time and controlled by some probability law is called a stochastic process. Thus, stochastic processes can be referred to as the dynamic part of the probability theory. We will now give a formal definition of a stochastic process.

Let T be a set which is called the index set (thought of as time), then, …

Computer Programs For Incomplete Block Designs, Fred Miller

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

In most disciplines where research is involved, there exists an occasional problem of having minimal facilities and/or funds for conducting experiments. This often necessitates the use of designs known as incomplete block designs.

Since the calculations needed to provide an appropriate statistical analysis are somewhat tedious, particularJ..y in the larger designs, it is advantageous to have computer programs to do the necessary calculations.

There are several computer programs at Utah State University written in Fortran II language with Forcom subroutines that perform the analyses for incomplete block designs. These programs, for the most part, were authored by Justus Seely and …

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 …

A Study Of The Exponential Distirbutions And Their Applications, Michael Chang-Yu Wang

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

The exponential distribution is a widely known distribution i n statistical theory. It can be regarded as the continuous analogue of the Poisson distribution, discussed by S. D. Poisson in 1837. The Poisson is a limiting form of the Binomial distribution which can be t race d back as early as 1700, discussed by James Bernoulli. A paper by Marsden and Barratt (1911) on the radioactive disintegration of thorium gives a typical frequency distribution which follows the exponential law (8, p. 89). The exponential distribution has achieved importance recently in connection with the theory of stochastic process and has found …

Partially Balanced Incomplete Block Designs, Yaw-Tarng Shih

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

In balanced incomplete block designs, each pair of treatments is compared with equal precision, and each treatment is paired with every other treatment an equal number of times with in a common block; A is a constant for all treatments. There is one associate class for each treatment in balanced incomplete block designs. These are the most important balanced incomplete block designs, but the need sometimes arises for others; either because no suitable balanced incomplete block design exists, or because, for example, it is necessary to make some comparisons more precisely than others. We can see balanced incomplete block designs …

Computer Analysis Of Consumer Attitude And Consumption Data For Fluid Milk Products, James Reed Fisher

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

The American public, with a per capita disposable income currently at an all time high, has become a source of vital concern to dairy market researchers. The unique socio-economic structure of the present generation causes the dairy industry to be concerned with how the consumer view its products. Effective education and advertising programs must be developed to attract the taste and meet the demands of the consumer.

Two factors which greatly influence market research and advertising programs are the attitude of the consumer toward a given product and the relationship of attitude to the degree of actual milk consumption. To …

Estimation Of Parameters Of Normal Populations From Truncated Samples, Kuo-Chung Liang

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

In statistical experiments, if a random sample of items drawn from a population is tested until all items fail, conventional statistical techniques may be employed but normal frequency distributions may not be satisfied. Failure of the data to satisfy the assumption of normality may lead to an invalid result. Some statistical results, however, have been shown to be robust to the failure of the data to meet normality. When using conventional experimental methods, considerable time and money are required to produce failure of all samples. To be economical, many experiments are concluded before all test items fail. A sample obtained …

Numerical Approximations To The Cumulative Chi-Square Distribution, The Cumulative T-Distribution And The Cumulative F-Distribution For Digital Computers, Grace Yuan-Chuen Wang

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

There are good tables of the frequently used cumulative frequency distributions. These tables have some limitations with respect to the number of percentage points that are available. The main drawback in computer usage of these tables is that large amounts of storage and elaborate search and interpolation techniques are necessary for their use.

It is the purpose of this study to present associated numerical methods for digital computer which are satisfactorily accurate and which are reasonably economical in both time and machine memory capacity. To carry out this objective the following procedures were used:

1. A review of literature on …