David R. Thomas

Confidence Interval Estimation of Survival Probabilities for Censored Data

Abstract The likelihood ratio method for confidence interval estimation of survival or life-time probabilities is investigated for censored data. This approach depends on a constrained product-limit estimator for the survival function. The likelihood method is compared with two alternative methods based on normal approximations to the product-limit estimator for several cases of uncensored and randomly censored samples. The methods are generalized for the ratio of two survival probabilities.

Linear Order Statistic Estimation for the Two-Parameter Weibull and Extreme-Value Distributions from Type II Progressively Censored Samples

Point estimation for the scale and location parameters of the extreme-value (Type I) distribution by linear functions of order statistics from Type II progressively censored samples is investigated. Four types of linear estimators are considered: the best linear unbiased (BLU), an approximation to the BLU, unweighted regression, and a linearized maximum likelihood. Linear transformations of the estimators are also considered for reducing mean square errors. Exact bias, variance, and mean square error comparisons of the estimators are made for several censoring patterns. Since the natural logarithms of Weibull variates have extreme-value distributions, the investigation is applicable to estimation for Weibull distributions.

Neyman's Smooth Goodness-of-Fit Test When the Hypothesis is Composite

Abstract A method is given for adjustment of the Neyman smooth goodness-of-fit test to allow for estimation of parameters in a composite hypothesis. With this method the limiting distribution under the hypothesis is chi-squared, in contrast to a method given by Barton for this problem. The basis of the method is a standard modification of the quadratic score statistic.

Livestock grazing effects on forage quality of elk winter range

Carefully-managed livestock grazing has been offered as a tool to improve the forage quality of graminoids on big game winter range. Formal testing of this theory has thus far been done using hand clippers rather than livestock grazing. We report winter standing reproductive culm, crude protein, in vitro dry matter digestibility, and standing crop responses of bluebunch wheatgrass (Agropyron spicatum [Pursh] Scribn. &Smith), Idaho fescue (Festuca idahoensis Elmer), and elk sedge (Carex geyeri Boott) to late-spring domestic sheep grazing. The study was conducted in 1993 and 1994 on a big game winter range in the Blue Mountains of northeastern Oregon. Sheep grazing and exclusion treatments were applied to 20-ha plots at 3 sites on the study area Targeted utilization for grazed plots was 50% graminoid standing crop removal during the boot stage of bluebunch wheatgrass. Grazing did not influence the number of standing reproductive culms per plant in bluebunch wheatgrass. Crude protein and in vitro dry matter digestibility of bluebunch wheatgrass in grazed plots increased by 1.0 and 4.3 percentage points, respectively over ungrazed plots. Grazing reduced the standing crop of bluebunch wheatgrass by 116.9 kg ha-1 DM. Standing Idaho fescue reproductive culms decreased by 0.7 culms plant-1 under grazing. Crude protein of Idaho fescue in grazed plots was 1.3 percentage points greater than in unglazed plots. Crude protein and in vitro dry matter digestibility responses of elk sedge were inconsistent between years and may be related to utilization or growth differences between years. The levels of forage quality improvement in bluebunch wheatgrass and Idaho fescue obtained in this study could benefit the nutritional status of wintering Rocky Mountain elk (Cervus elaphus nelsoni Bailey). More research is needed regarding the effects of grazing on the winter forage quality of elk sedge. DOI:10.2458/azu_jrm_v53i1_clark

Deconvolution of a Distribution Function

Abstract We consider the estimation of a distribution function when observations from this distribution are contaminated by measurement error. The unknown distribution is modeled as a mixture of a finite number of known distributions. Model parameters can be estimated and confidence intervals constructed using well-known likelihood theory. We show that it is also possible to apply this approach to estimation of a unimodal distribution. An application is presented using data from a dietary survey. Simulation results are given to indicate the performance of the estimators and the confidence interval procedures.

Nutrient quality of bluebunch wheatgrass regrowth on elk winter range in relation to defoliation.

Effects of defoliating bluebunch wheatgrass (Agropyron spicatum [Pursh] Scribn. & Smith) to increase the quality of regrowth available on Rocky Mountain elk (Cervus elaphus nelsoni Bailey) winter range were studied from 1988 through 1990. Percent calcium, phosphorus, in vitro dry matter digestibility (IVDMD), and available forage (kg/ha DM) of regrowth present on control, spring-defoliated, and fall-defoliated plots were determined in November of 1988 and 1989, and April of 1989 and 1990. Spring conditioning did not affect the percentage of calcium and phosphorus, or available forage compared to the current years growth in either November or April. Fall conditioning increased digestibility and increased the phosphorus concentration, but decreased available forage compared to the control and spring-conditioned forage in November. Fall conditioning may create a deficit of forage if regrowth is not achieved. Additional research is needed on defoliation during the early phenological time-period of bluebunch wheatgrass to improve the forage quality of elk winter ranges.

Effect of several stress factors on the susceptibility of the predatory mite, Metaseiulus occidentalis (Acari: Phytoseiidae), to the weak bacterial pathogen Serratia marcescens

Abstract A Metaseiulus occidentalis bioassay procedure that approaches incubation conditions for maximum host susceptibility to Serratia marcescens is presented. Preinoculation temperature and/or starvation pulses, chronic RH and crowding (or food search area) stressors, and an age (or instar) modulator were used singly and in combination to observe effects on the egg production and mortality (LC 50 s) of a predatory mite, M. occidentalis , inoculated with a weak bacterial pathogen, S. marcescens . Susceptibility of the mature host to the bacterium increased significantly after 4 days of incubation when the mite was exposed to a preinoculation high-temperature pulse and the containment area was increased. By day 6, these factors combined with incubation at high RH and some of their interactions significantly affected mite mortality and accounted for most of the variability in the experimental data. Although some of the stress factors significantly affected fecundity, measured by egg production rate, inoculation with S. marcescens at doses up to 10 8 colony-forming units/ml did not.

Simultaneous tolerance intervals for the linear regression model

Abstract Statistical tolerance intervals are developed for the normal regression model. These intervals are constructed to guarantee at least P content for all possible values of the predictor variates. The confidence-set approach suggested by Wilson (1967) is used. Wilson used an ellipsoidal confidence set for the regression coefficients, β, and standard deviation of the residuals, σ, which imposes an unnecessary lower bound on σ. By modifying the ellipsoidal confidence set to remove the lower bound imposed on σ, we obtain narrower tolerance intervals. Another confidence set formed from the product set of confidence sets for β and σ is used to construct tolerance intervals. The tolerance intervals of the two new procedures are compared with those of the Wilson method for a simple linear regression example. The tolerance intervals based on the product confidence set are found to be efficient and easy to compute compared with those constructed from the ellipsoidal and the modified ellipsoidal confidence sets.

Spring defoliation effects on bluebunch wheatgrass. I. Winter forage quality.

The winter forage quality of bluebunch wheatgrass (Agropyron spicatum [Pursh] Scribn. &Smith) is generally inadequate for maintenance of wintering Rocky Mountain elk (Cervus elaphus nelsoni Bailey). Previous attempts to improve the winter forage quality of bluebunch wheatgrass by clipping and livestock grazing have achieved mixed results. We report crude protein (CP), (in vitro dry matter digestibility (IVDMD), and dry matter (DM) yield responses of bluebunch wheatgrass to 3 phenological stage/defoliation intensity treatment combinations. The study was conducted in 1993 and 1994 at 2 sites in the Blue Mountains of northeastern Oregon. Bluebunch wheatgrass was hand clipped 1 to a 7.6-cm stubble height in early June under 1 of 3 treatment combinations: 1) mid-boot/whole-plant clipped, 2) mid-boot/one-half of the plants basal area clipped, and 3) inflorescence emergence/whole-plant clipped. Early November levels of CP and IVDMD were greater under all 3 treatments compared to an unclipped control. Mean forage quality improvement over the control was greatest in the inflorescence emergence treatment with an improvement of 1.3 percentage points for CP and 5.8 percentage points for IVDMD. Dry matter yield of the control exceeded that of all clipping treatments. Increases in forage quality resulting from forage conditioning treatments may be important to the viability of elk populations wintering on rangelands where forage quality, rather than quantity, is limiting.

Confidence Bands for Percentiles in the Linear Regression Model

Abstract Simultaneous confidence intervals for percentiles of the normal regression model similar to those given by Steinhorst and Bowden (1971) are considered. Kanofskys (1968) confidence band for a single normal distribution is modified and extended to the regression model. The confidence bands that are simultaneous in all percentiles provide corresponding confidence bands for the cumulative conditional normal distribution functions. The various procedures are compared with respect to bandwidth.