This paper presents a general statistical methodology for the analysis of multivariate categorical data arising from observer reliability studies. The procedure essentially involves the construction of functions of the observed proportions which are directed at the extent to which the observers agree among themselves and the construction of test statistics for hypotheses involving these functions. Tests for interobserver bias are presented in terms of first-order marginal homogeneity and measures of interobserver agreement are developed as generalized kappa-type statistics. These procedures are illustrated with a clinical diagnosis example from the epidemiological literature.

https://www.jstor.org/stable/pdfplus/2529310.pdf

The measurement of observer agreement for categorical data

The Mahalanobis distance

A model is developed to predict potential net energy gain for salmonids in streams from characteristics of water velocity and invertebrate drift. Potential net energy gain, or potential profit, is ...

Profitable stream positions for salmonids: relating specific growth rate to net energy gain

Cross-sectional studies have demonstrated a decline in testosterone and free and bioavailable testosterone with age. This occurs in a majority of older persons without an increase in luteinizing hormone (LH), suggesting that a component of the testosterone decrease is due to secondary hypogonadism. To determine whether these findings could be duplicated in a longitudinal study, we measured testosterone, LH, follicle-stimulating hormone (FSH), and sex hormone-binding globulin (SHBG) levels in 77 men participating in the New Mexico Aging Process Study who had sera available in 1980 or 1981 and two or more serial samples in 1982, 1984, 1989, and/or 1994. Thirty-nine subjects had samples available from both 1980 and 1994. The age at entry into the study ranged from 61 to 87 years. Testosterone levels decreased over the 15 years of the study. In persons who were alive for the duration of the study, testosterone levels were significantly lower 5 years before termination of the study (P < .05). Testosterone levels did not differ at entry into the study among those who died and those who were alive at the end of the study period. Eight of 77 subjects (10%) had LH levels above the normal range at some time during the study. In contrast, 43% of subjects had elevated FSH levels. Both LH and FSH increased significantly with age. SHBG levels were measured in 1980 and 1994 and increased significantly with age (P < .0001). LH and FSH were highly correlated with one another, but neither correlated with testosterone. This study demonstrated a longitudinal decline in testosterone and an increase in LH and FSH in older men. The average rate of decrement in testosterone concentration was 110 ng/dL every decade.

Longitudinal changes in testosterone, luteinizing hormone, and follicle-stimulating hormone in healthy older men

The study of biofilm structure and function mandates the use of model systems for which a host of environmental variables can be rigorously controlled. We describe a model of supragingival plaque containing Actinomyces naeslundii, Veillonella dispar, Fusobacterium nucleatum, Streptococcus sobrinus, and Streptococcus oralis wherein cells are cultivated anaerobically in a saliva-based medium on hydroxyapatite discs coated with a salivary pellicle, with material and pieces of apparatus common to all microbiology laboratories. After 0.5 hr, 16.5 hrs, 40.5 hrs, and 64.5 hrs, the composition of adherent biofilms was analyzed by culture techniques, live/dead fluorescence staining, and confocal laser scanning microscopy. Repeated independent trials demonstrated the repeatability of biofilm formation after 40.5 hrs and 64.5 hrs. Brief exposures of biofilms to chlorhexidine or Triclosan produced losses in viability similar to those observed in vivo. This biofilm model should prove very useful for pre-clinical testing of prospective anti-plaque agents at clinically relevant concentrations.

Validation of an in vitro Biofilm Model of Supragingival Plaque

Tables of percentage points for significance tests conrerning the highest or the lowest observation in normal samples, or the two highest or the two lowest observations in normal samples, were recently extended to larger sample sizes than heretofore published and to probability levels of .005 and .001. These tables are being pltblished to satisfy a long existing demand for such extensions.

Extension of Sample Sizes and Percentage Points for Significance Tests of Outlying Observations

A very important and yet widely misunderstood concept or problem in science and technology is that of precision and accuracy of measurement. It is therefore necessary to define the terms precision and accuracy (or imprecision and inaccuracy) clearly and analytically if possible. Also, we need to establish and develop appropriate statistical tests of significance for these measures, since generally a relatively small number of measurements will be made or taken in most investigations. In this paper a discussion is given of some of the pertinent literature for estimating variances in errors of measurement, or the “imprecisions” of measurement, when two or three instruments are used to take the same observations on a series of items or characteristics. Also, present techniques for comparing the imprecision of measurement of one instrument with that of a second instrument through the use of statistical tests of significance are reviewed, as well as procedures for detecting the significance of the difference i...

https://www.jstor.org/stable/pdfplus/1266824.pdf

Errors of Measurement, Precision, Accuracy and the Statistical Comparison of Measuring Instruments

We suggest herein a procedure for finding approximate fiducial bounds on the true reliability for the two parameter negative exponential distribution, which may be used as approximate “confidence” limits on reliability. These limits are simple and easy to compute. Also, they reduce to the exact confidence limits for the case of the single parameter negative exponential distribution.

https://www.jstor.org/stable/pdfplus/1266963.pdf

Approximate Fiducial Bounds on Reliability for the Two Parameter Negative Exponential Distribution

This letter indicates the restrictions on the Beta Distribution that are required to validate the use of PERT means and variances. The conditions appear to be rather restrictive, thereby limiting the generality of application in computing PERT probabilities. The subjective nature of the PERT estimation problem is also discussed.

Frank E. Grubbs

Papers

Extension of Sample Sizes and Percentage Points for Significance Tests of Outlying Observations

Errors of Measurement, Precision, Accuracy and the Statistical Comparison of Measuring Instruments

Approximate Fiducial Bounds on Reliability for the Two Parameter Negative Exponential Distribution

Letter to the Editor—Attempts to Validate Certain PERT Statistics or “Picking on PERT”

An Optimum Procedure for Setting Machines or Adjusting Processes