Showing papers by "John Lawson published in 1988"
TL;DR: Structure of the microhabitat used by four species of rodents in a montane environment was investigated using principal-component analysis of trap-site characteristics, and females of each species occupied more structured microhabITat than males of the same species.
Abstract: Structure of the microhabitat used by four species of rodents in a montane environment was investigated using principal-component analysis of trap-site characteristics. Most species of rodents were associated with fallen logs and brush during June but microhabitat use shifted to areas of more herbaceous growth in July–August. This shift was concurrent with rapid herbaceous growth. Females of each species occupied more structured microhabitat than males of the same species. Differential segregation of habitat by sex may be a function of the variability of resource use by the species as a whole. Unused microhabitat does not differ from random with respect to vegetative structure, and reasons for nonuse probably differ among sites.
30 citations
TL;DR: In this article, a joint Bayesian prior distribution is presented for the experimental error variance of an effect, σ2, and the probability that each effect is non-zero, along with a posterior marginal distribution for σ 2.
Abstract: Saturated fractional factorial experimental designs and orthogonal main effect plans are extremely valuable tools in quality engineering. However, one problem with these designs is that there are no replicate runs to be used for estimating experimental error. This note develops an estimator of the experimental error based on the hypothesis that not all factor effects will be non-zero. A joint Bayesian prior distribution is presented for the experimental error variance of an effect, σ2, and the probability that each effect is non-zero. From this prior distribution a posterior marginal distribution for σ2 is derived along with a direct estimate of σ2. This method is compared with the traditional methods of estimating σ2 in unreplicated designs through a numerical example.
6 citations
TL;DR: In an electric furnace smelting process, there was a large potential for savings in operation costs by switching to a cheaper supply of carbonaceous reducing agent for the furnace as mentioned in this paper. But the plant operation staff resisted such a switch for years thinking it w
Abstract: In an electric furnace smelting process, there was a large potential for savings in operation costs by switching to a cheaper supply of carbonaceous reducing agent for the furnace. The plant operation staff resisted such a switch for years thinking it w..
5 citations
TL;DR: In this article, a 2k-p fractional factorial design matrix and traditional data analysis techniques associated with this design can be used effectively to achieve the goal of parameter design while reducing the total number of experiments required.
Abstract: This article shows that a single 2k-p fractional factorial design matrix and the traditional data analysis techniques associated with this design can be used effectively to achieve the goal of parameter design while reducing the total number of experiments required. A real example is used to compare Taguchi's two-part design, and S/N analysis to a 2k-p design and its associated analysis. Also, a flow diagram is presented to guide a practitioner through the parameter design process using a 2k-p design. This flow diagram provides an annoted guide to the literature on 2k-p decision and shows the design processes leading to proper choice of design and appropriate data analysis techniques.
2 citations