Virgil L. Anderson

Extreme Vertices Design of Mixture Experiments

The extreme vertices design is developed as a procedure for conducting experiments with mixtures when several factors have constraints placed on them. The constraints so imposed reduce the size of the factor space which would result had the factor levels been restricted to only 0 to 100 per cent. The selection of the vertices and the various centroids of the resulting hyper-polyhedron as the design is a method of determining a unique set of treatment combinations. This selection is motivated by the desire to explore the extremes as well as the center of the factor space. A non-linear programming procedure is used in determining the optimum treatment combination.

Avoidance response of Midge Larvae (Chironomus Tentans) to sediments containing heavy metals

Avoidance reactions of chironomid larvae to contaminated sediment taken from a heavy metal impacted lake were studied. Heavy metal levels in the test sediment ranged from background of 0.6 parts per million (ppm) cadmium, 77 ppm zinc and 17 ppm chromium to a maximum of 1,029 ppm cadmium, 17,262 ppm zinc and 2,106 ppm chromium. A linear relationship was established between cadmium and zinc levels in the sediment and avoidance by chironomids.An approximate threshold avoidance of metals in the sediment was determined to be between 213–422 ppm cadmium, 4385–8330 ppm zinc and 799–1513 ppm chromium.

Sediment contamination and benthic macroinvertebrate distribution in a metal-impacted lake

Abstract Sediment contamination and benthic macroinvertebrate distribution were studied in Palestine Lake, Indiana, a public 80-ha system contaminated by effluents from a nearby electroplating plant. Trace metal levels in the upper 3 cm of sediment ranged from a high of 969 ppm cadmium, 14,032 ppm zinc and 2106 ppm chromium (dry weight basis) near the influent ditch, to a low of 4 ppm cadmium, 139 ppm zinc and 38 ppm chromium in the uncontaminated eastern basin of the lake. The midge Chironomus tentans was absent from areas of highest contamination; how ver, midge numbers increased to an average of 28 individuals/grab sample in the eastern basin. Specimens of the aquatic oligochaete Limnodrilus sp. were abundant (89/sample) in the most heavily impacted areas of the lake and scarce (3·4/sample) in the eastern basin.

A Statistical Approach for the Development of an Oral Controlled-Release Matrix Tablet

Tablet matrix compositions for optimized prolonged release were selected by surface response methodology. The extreme vertices experimental design was used to develop a surface response model which mathematically defined the release of active component from the tablet matrix as controlled by the percentage of the excipient components. The model, a statistical quadratic equation with a standard error of 3.3, was validated for accurate prediction of drug release profiles and used to identify optimum formulations. This study demonstrated a new application of the extreme vertices experimental design, an efficient method for evaluating a complex mixture system for controlled release, where specific constraints are placed on one or more of the components.

STATISTICAL MODELS FOR THE ESTIMATION OF BRIDGE REPLACEMENT COSTS

Abstract Making accurate estimates of bridge replacement costs is essential to assess present and future bridge funding needs. A series of analyses of variance was performed on bridge replacement costs to evaluate the effects of bridge attributes. Replacement cost prediction models were then developed by regression techniques. Bridge attributes which can be easily understood by bridge inspectors and engineers were used as predictor variables. Nonlinear and log-linear models were evaluated for developing cost prediction models. A residual analysis of these models showed that log-linear models were preferred to nonlinear models. Costs of bridges that had been replaced between 1980 and 1985 by the Indiana Department of Transportation (INDOT) were used as a data base. Replacement costs were converted to 1985 price using construction price indices. The final cost prediction models were validated using the costs of selected bridges which were replaced between January and June 1986, by the INDOT. Bridge replacement costs estimated by these models showed a fairly good correlation with the actual contract costs. To estimate current or future costs at a place other than in Indiana, one need to multiply appropriate cost indices.

Continental land cover assessment using landsat MSS data

Abstract A statistical procedure to assess level II continental resources using Landsat MSS digital data is presented. The statistical procedure involves a two-stage cluster sample within a stratified random sample. The utility of this procedure is assessed by using it to estimate the areal extent of the conifer and hardwood resources of the continental United States. National estimates of conifer and hardwood derived using this sampling procedure were within 3% of U.S. Forest Service figures. According to the Landsat-based study, 11% of the country is conifer forest, and 12% is hardwood. The corresponding U.S.F.S. figures are 13 and 15%, respectively. Comparison of the MSS classification products and airphotos showed that the conifer cover class was correctly identified 74% of the time and hardwood 80% of the time. The average classification accuracy countrywide for the four cover types considered (conifer, hardwood, water, and “other”) is 74%, the overall accuracy is 85%. The statistical procedure provides a method of incorporating Landsat MSS digital data as a second stage for level II continental resource assessment. Alternate data sources, e.g., satellite and aircraft photographic imagery, may also be used in conjunction with this statistical model.

A Statistical Model of Book Use and its Application to the Book Storage Problem

Abstract A statistical model is presented for describing the distribution of book uses in a research library. This model is used to attack the problem of book storage in a research library. A rule which says that a book goes to the storage collection if it is not used for k consecutive years after its acquisition in the library is studied. A similar rule for transferring active books from the storage to the active collection is also examined. Examples are provided to illustrate some of the results.

Performance Effects of Variables in Dynamic Visual Inspection

Abstract Three task variables of dynamic visual inspection were examined in laboratory experiments: (V) conveyor-belt velocities, (T) target exposure time and (P) the viewing position of the inspector. Measurements were obtained on both error types in inspection of equally-spaced targets for 36 experimental condition. Task variables V and T provided significant main effects on inspection accuracy and variables T and P had an interacting effect. The probability of correctly identifying a target was found to be describable as l-2.58e−a where a = 10.587T- 0.0.75/V-0.012/[T+ P2] and the coefficient of determination, R2 = 0.88. Inspectors eye motions were recorded and gross eye-motion patterns were identified but none appeared to be directly associated with inspection accuracy. Shifts in the inspection error criterion were observed and described for changes in these task variables. Both inspection speed and accuracy are combined in a cost model. This study shows that different conveyor speeds have better econ...

Trace Metal Discharges of the Grand Calumet River

Abstract Trace metal contamination of water and sediment of the polluted Grand Calumet River system was assessed for one year. Levels of cadmium, lead, zinc and iron in sediment generally exceeded literature values, while total levels in the water were less markedly elevated. Total discharge of metal from the river showed the following descending order of discharge: Fe > Zn > Pb > Cd. Significant amounts of the filterable fraction of lead, about 10 tons/year, are discharged through the Indiana Harbor Canal into Lake Michigan.

EVALUATION OF WILDLIFE REFLECTORS IN REDUCING VEHICLE-DEER COLLISIONS ON INDIANA INTERSTATE 80/90

The Indiana Department of Transportation is committed to reducing vehicle-deer collision incidents on the Indiana Interstate I-80/90 as well as on the other roads. Very few of the studies to reduce vehicle-deer collisions incorporated any sound and complete statistical design. Some states (California, Colorado, Maine, Ontario-Canada, Washington State and Wyoming) have found that the use of wildlife reflectors did not reduce vehicle-deer collisions. However, some other states (British Columbia-Canada, Iowa, Minnesota, Oregon, Washington State and Wisconsin) found that the use of wildlife reflectors did reduce vehicle-deer collisions. The main objective of this experimental study is to evaluate the effectiveness of the Reflectors in reducing vehicle-deer collisions. The experimental design uses one-mile long road sections for each combination of reflector colors (red and blue/green), reflector spacing (30 m and 45 m), reflector design (single and dual reflectors), and median (one with and one without reflectors). In this design there are sixteen treatment combinations. A complete set of treatment combinations is called a replicate and the design had two replicates. Two one-mile control sections were placed at each end of each replicate. Data for the peak months of April, May, October and November was used in the data analyses. Poisson Regression models were used to analyze the data. No statistically significant differences among reflectors combinations or between reflectors and controls were found. When comparing all combined reflector sites with all combined control sites, the Poisson Regression Analyses indicate that the difference between the Poisson Mean (μ) of the all reflectors sections and all the control sections is statistically significant. The use of reflectors provides an expected reduction in deer-vehicle collisions of 19% with 95% confidence limits of 5% to 30%. Maximum reduction is associated with 100 ft spacing regardless of the reflector color, median with or without reflectors, single or double reflectors. The cost effectiveness of this reduction will be behind any decision to use reflectors to reduce vehicle-deer collisions.