Comparisons of predictive values of binary medical diagnostic tests for paired designs

Positive and negative predictive values of a diagnostic test are key clinically relevant measures of test accuracy. Surprisingly, statistical methods for comparing tests with regard to these parameters have not been available for the most common study design in which each test is applied to each study individual. In this paper, we propose a statistic for comparing the predictive values of two diagnostic tests using this paired study design. The proposed statistic is a score statistic derived from a marginal regression model and bears some relation to McNemar's statistic. As McNemar's statistic can be used to compare sensitivities and specificities of diagnostic tests, parameters that condition on disease status, our statistic can be considered as an analog of McNemar's test for the problem of comparing predictive values, parameters that condition on test outcome. We report on the results of a simulation study designed to examine the properties of this test under a variety of conditions. The method is illustrated with data from a study of methods for diagnosis of coronary artery disease.     

Automatic analysis of gas exchange in microbial systems

An automatically working test arrangement for the permanent analysis of O₂ and CO₂ in microbiological cultures is described. The measuring principle is based on the paramagnetic properties of oxygen and on the absorption of infrared by carbon dioxide. The preparation of the gas for measuring and the correction of the recording are indicated. The formula of correction was programmed and the values were calculated for a range of 3%. The routine correction of analysis values is done with a nomogram established on the basis of these individual values. The advantages of the described test arrangement are illustrated by two examples of growth experiments on Saccharomyces cerevisiae.     

Detecting Heterogeneity of Substitution along DNA and Protein Sequences

Regions of differing constraint, mutation rate or recombination along a sequence of DNA or amino acids lead to a nonuniform distribution of polymorphism within species or fixed differences between species. The power of five tests to reject the null hypothesis of a uniform distribution is studied for four classes of alternate hypothesis. The tests explored are the variance of interval lengths; a modified variance test, which includes covariance between neighboring intervals; the length of the longest interval; the length of the shortest third-order interval; and a composite test. Although there is no uniformly most powerful test over the range of alternate hypotheses tested, the variance and modified variance tests usually have the highest power. Therefore, we recommend that one of these two tests be used to test departure from uniformity in all circumstances. Tables of critical values for the variance and modified variance tests are given. The critical values depend both on the number of events and the number of positions in the sequence. A computer program is available on request that calculates both the critical values for a specified number of events and number of positions as well as the significance level of a given data set.     

Evaluating sprinting ability, density of acceleration, and speed dribbling ability of professional soccer players with respect to their positions

The aim of this study is to evaluate sprinting ability, density of acceleration, and speed dribbling ability of professional soccer players with respect to their positions.A total of 243 professional soccer players were examined. These soccer players are playing in different leagues of Turkey. The F-MARC test battery, which was designed by FIFA, was used for soccer players. We did not find any statistical differences for 30-m sprint test and four-line sprint test values with respect to positions of soccer players (p > 0.05). On the other hand, there was a statistical difference for speed dribbling test values in terms of positions of soccer players (p < 0.05). It was found that the test values of defense players, midfielders, and forwards were better than the test values of goalkeepers (p < 0.05). In conclusion, this study, which was done during the training season, shows that there is a similarity between the abilities of professional soccer players for 30-m sprint and four-line sprint tests. Therefore, it is believed that there must be fast players in all positions in terms of sprint ability. There is a similarity among defenders, midfielders, and forwards in terms of speed dribbling ability; in contrast, the speed dribbling ability of goal keepers is different from the players in those three positions. Although there are many more speed dribbling exercises within the training programs of defenders, midfielders, and forwards, the speed dribbling ability test is not used much for goal keepers. Correspondingly, speed dribbling ability is not a specific indicator for goal keepers, and this test should not be used for the choice of goalkeepers.     

Reconsideration of the derivation of Most Probable Numbers,their standard deviations,confidence bounds and rarity values

Aims: The purpose of this work was to derive a simple Excel spreadsheet and a set of standard tables of most probable number (MPN) values that can be applied by users of International Standard Methods to obtain the same output values for MPN, SD of the MPN, 95% confidence limits and test validity. With respect to the latter, it is considered that the Blodgett concept of ‘rarity’ is more valuable than the frequently used approach of improbability (vide de Man). Methods and Results: The paper describes the statistical procedures used in the work and the reasons for introducing a new set of conceptual and practical approaches to the determination of MPNs and their parameters. Examples of MPNs derived using these procedures are provided. The Excel spreadsheet can be downloaded from http://www.wiwiss.fu‐berlin.de/institute/iso/mitarbeiter/wilrich/index.html . Conclusions: The application of the revised approach to the determination of MPN parameters permits those who wish to use tabulated values, and those who require access to a simple spreadsheet to determine values for nonstandard test protocols, to obtain the same output values for any specific set of multiple test results. The concept of ‘rarity’ is a more easily understood parameter to describe test result combinations that are not statistically valid. Provision of the SD of the log MPN value permits derivation of uncertainty parameters that have not previously been possible. Significance and Impact of the Study: A consistent approach for the derivation of MPNs and their parameters is essential for coherence between International Standard Methods. It is intended that future microbiology standard methods will be based on the procedures described in this paper.     

On the Asymptotic Relative Efficiency of the Mantel-Haenszel Test

The Mantel-Haenszel test is optimal when the odds ratio is constant. This paper investigates the effects of departures from the assumption of a constant odds ratio on the behavior of the Mantel-Haenzel test. A simple approximation is proposed for the non-null distribution of the test statistic. Based on this approximation, the asymptotic relative efficiency of the Mantel-Haenszel test, compared to the overall χ² test for no partial association, is calculated. For the case of 2 strata, it is shown that the Mantel-Haenszel test is efficient as long as the logarithms of the odds ratios are of the same sign and their absolute values exceed 1.     

Comparison of the Wingate and Bosco anaerobic tests

The purpose of this study was to compare the Wingate cycling and Bosco repeated jumps anaerobic tests. Eleven men (21.36 +/- 1.6 years; 179.1 +/- 9.3 cm; 78.7 +/- 11.0 kg) and 9 women (21.89 +/- 3.66 years; 171.8 +/- 10.0 cm; 75.9 +/- 21.4 kg), all university athletes, volunteered to participate. Subjects performed each test in random order. The tests consisted of a 30-second Wingate test and a 60-second Bosco test. The Wingate test was conducted using a Monark cycle ergometer and the Bosco test was conducted on a force platform. Following the performance of each test, peak lactate concentrations were determined. Average and peak power values were statistically greater in men and on the Bosco test. Peak lactate values were statistically greater in men but did not differ based on test. Correlations between peak lactate concentrations between tests and lactate values with peak or average power were not statistically significant. The relationship between peak power between tests was statistically significant among men, but not women. The results of the study indicated that the Bosco and Wingate tests, which both measure anaerobic characteristics, appear to measure different aspects of anaerobic power and capacity. The Bosco test also may be inappropriate for athletes who are not well trained in jumping.     

Evaluation of an indirect serum ELISA and a bacteriological faecal culture test for diagnosis of Salmonella serotype Dublin in cattle using latent class models

AIMS: To evaluate a conventional bacteriological test based on faecal culture and an indirect serum ELISA for detection of S. Dublin infected cattle. To compare the predictive values of the two tests in relation to the prevalence. METHODS AND RESULTS: A total of 4531 paired samples from cattle in 29 dairy herds were analysed for presence of S. Dublin bacteria in faeces and immunoglobulins directed against S. Dublin lipopolysaccharide in an indirect serum ELISA. Sensitivity and specificity were estimated at two ELISA cut-off values using a validation method based on latent class models, which presumably provides less biased results than traditional validation methods. Stratification of data into three age groups gave significantly better estimates of test performance of the ELISA. Receiver operating characteristic (ROC) curves were constructed for comparison of overall performance of the ELISA between the three age groups. The sensitivity of the faecal culture test was low (6-14%). ELISA appeared to have a higher validity for animals aged 100-299 days of age than older or younger animals. Overall, the negative predictive value of the ELISA was 2-10 times higher than for the faecal culture test at realistic prevalence of infection in the test population. CONCLUSIONS: The diagnostic sensitivity of the faecal culture test for detection of S. Dublin is poor, the specificity is 1. The superior sensitivity and negative predictive value of the serum ELISA makes this test preferable to faecal culture as an initial screening test and for certification of herds not infected with S. Dublin. SIGNIFICANCE AND IMPACT OF THE STUDY: A quantitative estimate of the sensitivity of a faecal culture test for S. Dublin in a general population was provided. ELISA was shown to be an appropriate alternative diagnostic test. Preferably, samples from animals aged 100-299 days of age should be used as these give the best overall performance of the ELISA. Plots of ROC curves and predictive values in relation to prevalence facilitates optimisation of the ELISA cut-off value.     

Comparing parasite numbers between samples of hosts

The comparison of parasite numbers or intensities between different samples of hosts is a common and important question in most parasitological studies. The main question is whether the values in one sample tend to be higher (or lower) than the values of the other sample. We argue that it is more appropriate to test a null hypothesis about the probability that an individual host from one sample has a higher value than individual hosts from a second sample rather than testing hypotheses about means or medians. We present a recently proposed statistical test especially designed to test hypotheses about that probability. This novel test is more appropriate than other statistical tests, such as Student's t-test, the Mann-Whitney U-test, or a bootstrap test based on Welch's t-statistic, regularly used by parasitologists.     

Determination of Drug Resistance of Mycobacterium tuberculosis Cultures

A total of 3,303 strains of Mycobacterium tuberculosis were tested for sensitivity to streptomycin (SM), isoniazid (INH), and p-aminosalicylic acid (PAS) by the Steenken modified minimal inhibitory concentration (MIC) test. A simultaneous double blind comparison was carried out on 277 selected strains by the Steenken MIC test and the Canetti proportion method. Agreement between the results for the two tests was 82% for SM, 95% for INH, and 89% for PAS. A small number of strains appeared to be sensitive when tested by one method but resistant by the other. MIC determinations were carried out on 83 strains by using Steenken-Smith, Lowenstein-Jensen, and Middlebrook 7H10 media containing a more extended range of concentrations of the test drugs. The MIC values for both SM and dihydrostreptomycin increased on Steenken-Smith medium compared with the other two. INH did not show any medium effect, whereas PAS showed increased MIC values in 7H10 agar. The significance of the comparisons of the MIC values on the various media is discussed in terms of possible changes in the drug sensitivity testing methods used at present in this laboratory.     

Rapid simulation of P values for product methods and multiple-testing adjustment in association studies

A major aim of association studies is the identification of polymorphisms (usually SNPs) associated with a trait. Tests of association may be based on individual SNPs or on sets of neighboring SNPs, by use of (for example) a product P value method or Hotelling's T test. Linkage disequilibrium, the nonindependence of SNPs in physical proximity, causes problems for all these tests. First, multiple-testing correction for individual-SNP tests or for multilocus tests either leads to conservative P values (if Bonferroni correction is used) or is computationally expensive (if permutation is used). Second, calculation of product P values usually requires permutation. Here, we present the direct simulation approach (DSA), a method that accurately approximates P values obtained by permutation but is much faster. It may be used whenever tests are based on score statistics--for example, with Armitage's trend test or its multivariate analogue. The DSA can be used with binary, continuous, or count traits and allows adjustment for covariates. We demonstrate the accuracy of the DSA on real and simulated data and illustrate how it might be used in the analysis of a whole-genome association study.     

Nonparametric evaluation of quantitative traits in population-based association studies when the genetic model is unknown

Statistical association between a single nucleotide polymorphism (SNP) genotype and a quantitative trait in genome-wide association studies is usually assessed using a linear regression model, or, in the case of non-normally distributed trait values, using the Kruskal-Wallis test. While linear regression models assume an additive mode of inheritance via equi-distant genotype scores, Kruskal-Wallis test merely tests global differences in trait values associated with the three genotype groups. Both approaches thus exhibit suboptimal power when the underlying inheritance mode is dominant or recessive. Furthermore, these tests do not perform well in the common situations when only a few trait values are available in a rare genotype category (disbalance), or when the values associated with the three genotype categories exhibit unequal variance (variance heterogeneity). We propose a maximum test based on Marcus-type multiple contrast test for relative effect sizes. This test allows model-specific testing of either dominant, additive or recessive mode of inheritance, and it is robust against variance heterogeneity. We show how to obtain mode-specific simultaneous confidence intervals for the relative effect sizes to aid in interpreting the biological relevance of the results. Further, we discuss the use of a related all-pairwise comparisons contrast test with range preserving confidence intervals as an alternative to Kruskal-Wallis heterogeneity test. We applied the proposed maximum test to the Bogalusa Heart Study dataset, and gained a remarkable increase in the power to detect association, particularly for rare genotypes. Our simulation study also demonstrated that the proposed non-parametric tests control family-wise error rate in the presence of non-normality and variance heterogeneity contrary to the standard parametric approaches. We provide a publicly available R library nparcomp that can be used to estimate simultaneous confidence intervals or compatible multiplicity-adjusted p-values associated with the proposed maximum test.     

Very fast empirical prediction and rationalization of protein pKa values

A very fast empirical method is presented for structure-based protein pKa prediction and rationalization. The desolvation effects and intra-protein interactions, which cause variations in pKa values of protein ionizable groups, are empirically related to the positions and chemical nature of the groups proximate to the pKa sites. A computer program is written to automatically predict pKa values based on these empirical relationships within a couple of seconds. Unusual pKa values at buried active sites, which are among the most interesting protein pKa values, are predicted very well with the empirical method. A test on 233 carboxyl, 12 cysteine, 45 histidine, and 24 lysine pKa values in various proteins shows a root-mean-square deviation (RMSD) of 0.89 from experimental values. Removal of the 29 pKa values that are upper or lower limits results in an RMSD = 0.79 for the remaining 285 pKa values.     

Critical Values of ‘Maximum Studentized Residual’ Statistics in Multiple Linear Regression

In multiple linear regression, test for the discordancy of a single outlier in the response variable is usually based on the ‘maximum studentized residual’ statistic. Exact critical values for the test statistic t are not available. Upper bounds for the critical values have been found by SRIKANTAN (1961), PRESCOTT (1975) and LUND (1975). In this note we show that all these upper bounds are algebraically equivalent.     

农作物种子检验中发芽试验的容许误差的统计模型与计算

当代计算手段远远优于计算种子检验规程发芽试验现行标准中容许误差数值的20 世纪60年代,鉴于此,本文在提出发芽试验统计检验模型的基础上,利用MATLAB编程重新计算了容许误差值．过去计算的三种容许误差有较大的正偏差,另一种有很小的负偏差．建议对现行的种子检验规程有关计数型的容许误差数值进行修订．     

Influence of physical exercise on human preferences for various taste solutions

The effects of physical exercise on preference for various sapid solutions was studied in 58 healthy university students. After 30 min of exercise using a bicycle ergometer at 50% VO2max (maximal oxygen uptake) intensity, a rating scale test on taste hedonic tone and the triangle test for taste absolute threshold were done. The test solutions were sucrose, NaCl, citric acid, caffeine and monosodium glutamate (MSG). Preference scale values for sucrose and citric acid increased after exercise, whereas the values for NaCl, caffeine and MSG were not changed. The absolute thresholds for all the sapid solutions did not differ for pre- and post-exercise. These findings indicate that in humans preference for sucrose and citric acid increase after physical exercise.      

Measurement of narcotic potency using houseflies

A method is described for the measurement of narcotic potencies of chemical compounds, using houseflies. Narcotic potency measurements give rise to statistical problems which differ from those encountered in toxicity determinations in so far as the narcotic process is reversible, and successive values of the number of affected insects in a group subjected to the test do not normally increase monotonically and in some case considerable oscillation occurs. An earlier method (Bradbury & Armstrong, 1954) used probit analysis, but it is now shown that this treatment and also regression analysis both fail to provide a valid method of dealing with variability in this type of test. A test based on the response of two flies, one male and one female per flask, is now described. The test, based on sixteen flies per compound, gave figures for: α₀, the partial saturation of the test compound giving the same average knock-down time as chloroform at a partial saturation of 0.005; α₁, the partial saturation of the test compound giving knock-down in I hr.; b, the slope of the straight line relating log. knock-down time to log. partial saturation; s, the residual standard deviation of log. knock-down time about its regression line on log. partial saturation. From these values the 95% confidence limits for the slope and for the values of α₀ were calculated. The test also provided information on the convulsive action of compounds and a modification of it was used to determine knock-down times of very potent narcotics at high dosages. Results are presented for fifty-seven halogenated hydrocarbons and the hypothesis that variations in potency between narcotics are determined mainly by rates of diffusion is examined. The results do not support this hypothesis. Narcotic and convulsant potencies measured by the method described are a useful guide to the behaviour of compounds in mouse tests.     

Sulfonylurea-induced factitious hypoglycemia in a nondiabetic nurse.

A case of sulfonylureainduced factitious hypoglycemia occurring in a nondiabetic medical nurse is reported. The patient presented with symptoms of hypoglycemia, consistently low fasting plasma glucose values and a reversal of symptoms with glucose administration. An intravenous tolbutamide provocative test on two occasions showed little increase in plasma glucose values. The case is presented to illustrate that sulfonylureainduced hypoglycemia should be considered in the differential diagnosis of fasting adult hypoglycemia, especially in paramedical personnel, and particularly in those with a poor response to the intravenous tolbutamide test.     

Hochberg's Step-Up Method: Cutting Corners Off Holm's Step-Down Method

Holm's method and Hochberg's method for multiple testing canbe viewed as step-down and step-up versions of the Bonferronitest. We show that both are special cases of partition testing.The difference is that, while Holm's method tests each partitionhypothesis using the largest order statistic, setting a criticalvalue based on the Bonferroni inequality, Hochberg's methodtests each partition hypothesis using all the order statistics,setting a series of critical values based on Simes' inequality.Geometrically, Hochberg's step-up method ‘cuts corners’off the acceptance regions of Holm's step-down method by makingassumptions on the joint distribution of the test statistics.As can be expected, partition testing making use of the jointdistribution of the test statistics is more powerful than partitiontesting using probabilistic inequalities. Thus, if the jointdistribution of the test statistics is available, through modellingfor example, we recommend partition step-down testing, settingexact critical values based on the joint distribution.     

Antibiotic Susceptibility Testing of Anaerobes: Comparison of Three Methods, Including an Automated Micro-method, and Evaluation of the Effect of Different Media

Disc-diffusion, agar-dilution and microdilution methods were compared for testing the antibiotic sensitivity of anaerobic bacteria. Eight antibiotics and 31 test organisms were used. There was a poor correlation between MIC values obtained by the agar-dilution and microdilution procedures. The test organisms showed an apparently increased sensitivity to the antibiotics when tested by the agar-dilution, as compared with the microdilution, procedures. Columbia Blood Agar and Thioglycollate Haemin agar, were evaluated for the disc-diffusion and agardilution procedures. There was a poor correlation between the MIC values and inhibition zone diameters for the two media, with lower MIC values and larger zones on Thioglycollate Haemin agar.