Search

Cotton plants were infested with brown stink bug, Euschistus servus (Say), to define cotton boll age classes (based on heat unit accumulation beyond anthesis) that are most frequently injured during each of the initial 5 wk of flowering. Bolls from each week were grouped into discrete age classes and evaluated for the presence of stink bug injury. Brown stink bug injured significantly more bolls of age class B (approximately 165-336 heat units), age class C (approximately 330-504 heat units), and age class D (approximately 495-672 heat units) during the initial 3 wk in both years and in week 5 in 2002 compared with other boll ages. Generally, the frequency of injured bolls was lowest in age class A (or = 168 heat units) during these periods. The preference by brown stink bug for boll age classes B, C, and D within a week was similar when ages were combined across all 5 wk. Based on these data, bolls that have accumulated 165.2 through 672 heat units beyond anthesis (approximately 7-27-d-old) are more frequently injured by brown stink bug when a range of boll ages are available. The boll ages in our studies corresponded to a boll diameter of 1.161-3.586 cm with a mid-range of 2.375 cm. A general protocol for initiating treatments against stink bugs is to sample bolls for evidence of injury as an indicator of presence of infestations in cotton. Sampling bolls within a defined range, which is most likely to be injured, should improve the precision of this method in detecting economic stink bug infestations in cotton.

Brown stink bug, Euschistus servus (Say), was infested on cotton, Gossypium hirsutum L., plants during reproductive stages to determine the effects on boll injury and seedcotton yield. During each week in 2002 and 2003, significantly more bolls withor = 1 injured locule, bolls withor = 2 injured locules, and bolls with discolored lint were recorded on stink bug-infested plants compared with that on noninfested plants. Significantly fewer bolls displayed external injury on the boll exocarp compared with bolls with only internal locule injury. Boll injury was significantly underestimated by the presence of external symptomology. The boll population increased 6.6- and 5.1-fold from weeks 1-5 in 2002 and 2003, respectively. There was a corresponding 6.2- and 4.6-fold increase in 2002 and 2003, respectively, for total bolls injured from weeks 1-5. Percentage of boll injury ranged from 10.7 (week 4) to 27.4 (week 2) in 2002 and from 9.2 (week 3) to 16.0 (week 2) in 2003. Percentage of injury was greatest during weeks 1 and 2 in both years and also in week 5 in 2002. Brown stink bug significantly reduced seedcotton yield of bolls present on cotton plants during weeks 1, 2, and 5 in 2002 and in weeks 4 and 5 in 2003. However, total seedcotton yield, as a function of bolls exposed to brown stink bug and subsequent bolls produced on plant in the absence of stink bugs, was not significantly different for plots infested during weeks 1-4 in 2002 and weeks 1-3 in 2003. Flowering period and boll population influence the severity of stink bug injury on seedcotton yield. Infestation timing and number of bolls should be considered, in addition to insect densities, when initiating treatments against brown stink bug.

A number of criteria have been proposed for selecting the best subset or subsets of independent variables in linear regression analysis. Applying these criteria to all possible subsets is, in general, not feasible if the number of variables is large. Many of the criteria are monotone functions of the residual sum of squares hence the problem is reduced to identifying subsets for which this quantity is small. In an earlier paper (Selection of the Best Subset in Regression Analysis by R. R. Hocking and R. N. Leslie, 1967) a method was described for identifying such subsets without considering all possible subsets. However, the amount of computation required if more than fifteen independent variables were considered was excessive. The present paper extends the basic ideas in that paper so that moderately large problems can how be treated with what appears to be a minimum of computation.

Problems encountered in estimating variance components in mixed-effects analysis of variance (ANOVA) models have stimulated research in linear estimation. Pukelsheim (1976) noted that quadratics in the observations which are invariant to fixed effects follow a linear model in the variance components, and that results in linear estimation theory can then be applied directly to this derived linear model. However, this model has characteristics which do not permit application of earlier results on admissibility of linear estimators by Cohen (1966) and Rao (1976). Olsen, Seely and Birkes (1976) provided results on admissibility and completeness among unbiased linear estimators in a very general setting which encompasses the peculiar structure of linear models for invariant quadratics. In models with two variance components, they described the essentially complete class of admissible unbiased invariant quadratic estimators of linear combinations of the variance components. These results when combined with existing results on unbiased linear estimation, fairly completed the story on unbiased invariant quadratic estimation of variance components.

The report describes a computer program implementing the Hartley- Hocking convex programming algorithm. The two parts of this report are, respectively, a description of the Hartley-Hocking method as extracted from the original paper, and the documentation of the computer program.

In the report a method is developed for determining the optimal warhead design for an intercept missile. The problem posed is that of determining the fragment density pattern which will maximize the average probability of destroying an incoming aircraft when the flight parameters of the target are not assumed known but are assumed to follow a known probability law. The problem is formulated as a mathematical programming problem requiring as preliminary computation the determination of an 'intercept geometry' for each possible combination of target parameters. The formulas for these computations are developed, and an example is given.

Multinomial samples may be fully or partially classified. In this paper, procedures for optimally determining sample size allocations between fully and partially classified data sets are described and illustrated. Expressions for the large-sample variances of the maximum likeli-hood estimators using both completely and partially classified data are given which reduce the design problems to convex programming problems.