Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

1996

Statistics and Probability

Conference on Applied Statistics in Agriculture

Articles 1 - 14 of 14

Full-Text Articles in Physical Sciences and Mathematics

Wavelet Nonparametric Regression With Dependent Data, Chengjie Xiong, George A. Milliken Apr 1996

Wavelet Nonparametric Regression With Dependent Data, Chengjie Xiong, George A. Milliken

Conference on Applied Statistics in Agriculture

Estimation of the regression function has many applications in agriculture and industry. Usually, the regression function is assumed a known functional form which depends on unknown parameters. Nonparametric regression theory makes no such assumption and often uses some kernel functions to form the so-called Watson Nadaraya type estimators. Such estimators were extensively studied by Watson (1964), Nadaraya (1964, 1989) and Collomb (1981, 1985). When the data are independent, these estimators have nice asymptotic convergence properties. When the data are dependent, Gyorfi et al (1989) gave some large sample properties for the Watson-Nadaraya estimators. In this paper, the recently developed theory …

Go to article

Validity Of 95% T-Confidence Intervals Under Some Transect Sampling Strategies, Stephen N. Sly, Jeffrey S. Pontius, James J. Higgins Apr 1996

Validity Of 95% T-Confidence Intervals Under Some Transect Sampling Strategies, Stephen N. Sly, Jeffrey S. Pontius, James J. Higgins

Conference on Applied Statistics in Agriculture

Soil pH data were used to assess the capture rates of 95 % t-confidence intervals based on five different transect sampling strategies. Two different sampling methods were considered, "deterministic" and "two-stage simple random sampling". The data used were pH readings at 15 and 30 centimeter depths from two local agricultural fields in the Manhattan, Kansas area. The data provided three distinct populations with three different distributions - skewed left, symmetric, and bimodal. The total number of transects randomly sampled was 2, 5, and 10. The total number of points sampled along each transect was 2, 7 and 14. The 95% …

Go to article

Designing Speech Interface Applications For Acquisition Of Agricultural Information, Jeffrey Willers, Susan Bridges, Xiaofeng Ma, James Mckinion, Jean Liang Apr 1996

Designing Speech Interface Applications For Acquisition Of Agricultural Information, Jeffrey Willers, Susan Bridges, Xiaofeng Ma, James Mckinion, Jean Liang

Conference on Applied Statistics in Agriculture

It will be argued that customary software design strategies, by themselves, fall short when designing speech recognition applications. Concepts of experimental design and analysis are also necessary for developing speech interface software. This study demonstrates that these tools can be advantageous to the software developer, especially if the prototype methodology model of software development is applied. A case study for the problem of developing a speech interface for collecting, or mapping, information on cotton plant growth is presented. The acquisition of cotton plant map data is a 'hands and eyes' busy task that requires considerable investment to record and convert …

Go to article

A New Approach To Teaching Natural Resource Sampling, Kenneth M. Portier, Loukas G. Arvanitis, Daniel Brackett Apr 1996

A New Approach To Teaching Natural Resource Sampling, Kenneth M. Portier, Loukas G. Arvanitis, Daniel Brackett

Conference on Applied Statistics in Agriculture

A basic undergraduate course in statistics is often not adequate for students in renewable natural resource programs such as wildlife, forestry, fisheries, and related subjects. A strong foundation in the basics of sampling in time and space of forest, vegetation, wildlife and fish populations is needed. A brief account of our experience in teaching such a course over the last three years along with progress on developing course-related material and activities is reported. This includes the development of: 1) computer-based simulations; 2) in-class participation simulations to illustrate the basic concepts of sampling in space and time; 3) exercises to introduce …

Go to article

Experimentation Science: A Process Approach For The Complete Design Of An Experiment, D. D. Kratzer, K. A. Ash Apr 1996

Experimentation Science: A Process Approach For The Complete Design Of An Experiment, D. D. Kratzer, K. A. Ash

Conference on Applied Statistics in Agriculture

Experimentation Science is introduced as a process through which the necessary steps of experimental design are all sufficiently addressed. Experimentation Science is defined as a nearly linear process of objective formulation, selection of experimentation unit and decision variable(s), deciding treatment, design and error structure, defining the randomization, statistical analyses and decision procedures, outlining quality control procedures for data collection, and finally analysis, presentation and interpretation of results. The protocol description form (PDF) is introduced as an instrument to guide the implementation and documentation of the Experimentation Science process.

Go to article

Markov Chain Monte Carlo Methods For Modeling The Spatial Pattern Of Disease Spread In Bell Pepper, Jonathan M. Graham Apr 1996

Markov Chain Monte Carlo Methods For Modeling The Spatial Pattern Of Disease Spread In Bell Pepper, Jonathan M. Graham

Conference on Applied Statistics in Agriculture

With exponential family models for dependent data, such as the autologistic model for binary spatial lattice data, maximum likelihood estimates can be obtained using Markov chain sampling methods by simulating an ergodic Markov chain which converges weakly to the equilibrium distribution of the model. This Markov chain Monte Carlo maximum likelihood (MCMCML) procedure provides a competitor to the usual pseudolikelihood estimation method often used for modeling discrete lattice data. Within this MCMCML framework, it is also possible to conduct formal inference using MCMC analogues to the usual likelihood ratio, Wald, and Lagrange multiplier tests, for which the asymptotic distributions are …

Go to article

Confidence Intervals For The Coefficient Of Variation, Mark E. Payton Apr 1996

Confidence Intervals For The Coefficient Of Variation, Mark E. Payton

Conference on Applied Statistics in Agriculture

The coefficient of variation (CV), defined as the ratio of the standard deviation to the mean, is often used in experimental situations. The exact distribution of the sample CV from a normally distributed population is complicated and obtaining a confidence interval for the population CV in this situation would require using the non-central t distribution and sequential techniques (Koopmans, et al., 1964). This paper explores the use of approximate distributions in determining confidence limits for the CV. The gamma distribution is used to model data appropriate for the calculation of the CV. A Monte Carlo simulation is performed to evaluate …

Go to article

Estimation Of Kinetic Parameters Associated With Nutrient Uptake By An Intact Plant Root System, Edward Gbur, Craig Beyrouty Apr 1996

Estimation Of Kinetic Parameters Associated With Nutrient Uptake By An Intact Plant Root System, Edward Gbur, Craig Beyrouty

Conference on Applied Statistics in Agriculture

Several mechanistic models have been developed for the prediction of nutrient uptake at low concentrations from the soil by a plant root system. Claassen and Barber (1974 Plant Physiology 54, 564-568; 1976 Agronomy Journal 68, 961-964) presented an experimental procedure to obtain data from intact plants to fit an ion depletion curve and used the data in a model which they developed to predict nutrient uptake. Their model assumed that nutrient absorption from the soil solution followed Michaelis-Menten kinetics. In this paper, we develop a stochastic version of the Claassen-Barber model and illustrate its application to the estimation of the …

Go to article

Analysis Of Unbalanced Mixed Model Data: Traditional Anova Versus Contemporary Methods, Ramon C. Littell Apr 1996

Analysis Of Unbalanced Mixed Model Data: Traditional Anova Versus Contemporary Methods, Ramon C. Littell

Conference on Applied Statistics in Agriculture

Analysis of unbalanced data and analysis of mixed model data are important topics of statistical discussion. Analysis of unbalanced data with fixed effects gives rise to the different types of sums of squares in analysis of variance. Mixed model riata raises issues of determining appropriate error terms for test statistics and standard errors Clf estimates. The situation is even more difficult when the two topics occur together, resulting in unbalanced mixed model data. These problems have plagued users ofPROC GLM in the SAS System. Now, with PROC MIXED available, some of the problems are resolved while others remain. This paper …

Go to article

Analysis Of Proportions From Split-Plot And Repeated Measures Experiments, Kenneth J. Koehler Apr 1996

Analysis Of Proportions From Split-Plot And Repeated Measures Experiments, Kenneth J. Koehler

Conference on Applied Statistics in Agriculture

Several methods for analyzing proportions from split-plot and repeated measures experiments are illustrated and compared. One approach simply uses analysis of variance for the usual linear mixed model fit to split-plot and repeated measures experiments. Alternatively, logistic regression analysis is considered and a so-called robust estimate of the covariance matrix is used to adjust for possible correlations among responses. Finally, a quasi-likelihood approach to logistic regression analysis that requires more explicit specification of the covariance structure for the observed proportions is considered. These methods are illustrated with the analyses of data from a repeated measures study of acorn consumption by …

Go to article

Estimation Of Cardinal Temperatures In Germination Data Analysis, Cindy Roche, Bahman Shafii, Donald C. Thill, William J. Price Apr 1996

Estimation Of Cardinal Temperatures In Germination Data Analysis, Cindy Roche, Bahman Shafii, Donald C. Thill, William J. Price

Conference on Applied Statistics in Agriculture

Seed germination is a complex biological process which is influenced by various environmental and genetic factors. The effects of temperature on plant development are the basis for models used to predict the timing of germination. Estimation of the cardinal temperatures, including base, optimum, and maximum, is essential because rate of development increases between base and optimum, decreases between optimum and maximum, and ceases above the maximum and below the base temperature. Nonlinear growth curves can be specified to model the time course of germination at various temperatures. Quantiles of such models are regressed on temperature to estimate cardinal quantities. Bootstrap …

Go to article

Long-Term Tillage Effects On Continuous Corn Yields, T. B. Bailey, J. B. Swan, R L. Higgs, W. H. Paulson Apr 1996

Long-Term Tillage Effects On Continuous Corn Yields, T. B. Bailey, J. B. Swan, R L. Higgs, W. H. Paulson

Conference on Applied Statistics in Agriculture

Long-term comparisons of alternative tillage systems are needed to evaluate their effect on corn (Zea mays L.) yield under the variable temperature and rainfall conditions of the Corn Belt. Our objective was to evaluate long-term effects of alternative tillage systems on corn growth and yield on low organic matter silt loam soils. The effect of no-tillage (NT), chisel plow (CP), and moldboard plow (MP) treatments on plant density and grain yield was measured from 1981 through 1990 on Palsgrove and Rozetta silt loam (fine-silty, mixed mesic Typic Hapludalfs) soils. Tillage treatments were randomly allocated to plots in 1981 …

Go to article

An Introduction To Generalized Linear Mixed Models, Charles E. Mcculloch Apr 1996

An Introduction To Generalized Linear Mixed Models, Charles E. Mcculloch

Conference on Applied Statistics in Agriculture

The generalized linear mixed model (GLMM) generalizes the standard linear model in three ways: accommodation of non-normally distributed responses, specification of a possibly non-linear link between the mean of the response and the predictors, and allowance for some forms of correlation in the data. As such, GLMMs have broad utility and are of great practical importance. Two special cases of the GLMM are the linear mixed model (LMM) and the generalized linear model (GLM). Despite the utility of such models, their use has been limited due to the lack of reliable, well-tested estimation and testing methods. I first describe and …

Go to article

Editor's Preface, Table Of Contents, And List Of Attendees, George A. Milliken Apr 1996

Editor's Preface, Table Of Contents, And List Of Attendees, George A. Milliken

Conference on Applied Statistics in Agriculture

These proceedings contain papers presented in the eighth annual Kansas State University Conference on Applied Statistics in Agriculture, held in Manhattan, Kansas, April 28-30, 1996..

Go to article