On using Lehmann alternatives with nonresponders.

The problem of testing for treatment effect when some subjects in the treatment group may be unaffected by the treatment is considered. A form of the Lehmann alternative suggested by Conover and Salsburg is used that assumes that each control score has the same distribution as the minimum of the known number of responses in the treatment group. It is shown that the locally most powerful test leads to a test statistic that, under the hypothesis of no treatment effect, is the sum of independent pareto random variables whereas under the alternative hypothesis it is the sum of independent random variables from a mixture of two pareto distributions. The limiting distribution of the test statistic under both hypotheses is in the domain of attraction of a stable distribution whose indices are derived. The power of the test is given, and its properties are discussed. A set of data from clinical research involving development of a new drug is used to show application of the procedure and demonstrate its usefulness.     

Tests Against Qualitative Interaction: Exact Critical Values and Robust Tests

Consider a study to evaluate treatment A with a placebo in two or more groups of patients. If treatment A is beneficial to one group of patients and harmful to another, then we say that there is qualitative interaction or crossover interaction between patient groups and the treatments. Gail and Simon (1985, Biometrics 41, 361-372) developed a large-sample procedure for this testing problem. Their test has received favorable coverage in the literature. In this article, we obtain corresponding exact finite sample results for normal error distribution and provide a table of critical values. The test statistic is similar to the familiar F-ratio, and its p-value is equal to a weighted sum of tail areas of F-distributions. The computations to implement this are simple. A simulation study shows that the exact critical values provided here for normal error distribution are preferable to the asymptotic critical values for a wide range of error distributions. We also develop tests that are power robust against long-tailed error distributions. Our robust test uses M-estimators instead of the least squares estimators. We show that the efficiency robustness of the M-estimator translates to power robustness of the corresponding test. Therefore, our robust tests are better if outliers are expected. A simulation study illustrates the substantial power advantages of our robust tests.     

A test for linkage and association in general pedigrees: the pedigree disequilibrium test

Family-based tests of linkage disequilibrium typically are based on nuclear-family data including affected individuals and their parents or their unaffected siblings. A limitation of such tests is that they generally are not valid tests of association when data from related nuclear families from larger pedigrees are used. Standard methods require selection of a single nuclear family from any extended pedigrees when testing for linkage disequilibrium. Often data are available for larger pedigrees, and it would be desirable to have a valid test of linkage disequilibrium that can use all potentially informative data. In this study, we present the pedigree disequilibrium test (PDT) for analysis of linkage disequilibrium in general pedigrees. The PDT can use data from related nuclear families from extended pedigrees and is valid even when there is population substructure. Using computer simulations, we demonstrated validity of the test when the asymptotic distribution is used to assess the significance, and examined statistical power. Power simulations demonstrate that, when extended pedigree data are available, substantial gains in power can be attained by use of the PDT rather than existing methods that use only a subset of the data. Furthermore, the PDT remains more powerful even when there is misclassification of unaffected individuals. Our simulations suggest that there may be advantages to using the PDT even if the data consist of independent families without extended family information. Thus, the PDT provides a general test of linkage disequilibrium that can be widely applied to different data structures.     

Impact of genetic testing for breast-ovarian cancer susceptibility

Previously, we have reported a clinical trial in which any woman in a defined geographic region who had a qualifying family history and who was referred by her physician or who was identified through a regional cancer registry was offered free genetic counseling, BRCA testing, and recommendations based on test results. Each family was represented by one affected and one unaffected person. Of the 87 families actually tested, 13 were found to have deleterious mutations. To assess the impact of the counseling and testing process, we contacted the tested individuals 1 month and 1 year after receiving the test result and those with an abnormal test result after 4 years. Index subjects, we found, differed significantly from relatives. Before coming for counseling, index subjects perceived both their general health and emotional health as worse than did their relatives. After counseling and testing, index subjects continue to worry more about breast cancer than do relatives. Affected subjects, we found, differed significantly from unaffected subjects. Before counseling, affected subjects knew more about breast cancer, perceived their general health as poorer, and reported greater adherence to recommended breast cancer surveillance than did unaffected subjects. After counseling and testing, affected subjects were less satisfied than unaffected subjects with having been tested. This study indicates that the group most prone to distress by cancer risk genetic counseling and testing is not the recruited relatives, nor even those affected with cancer, but rather the index patients themselves. The index patients, i.e., the ones who want the risk information most, appear to undergo the most stress in obtaining it.     

The mechanomyography of persons after stroke during isometric voluntary contractions.

This study was to investigate the properties of mechanomyography (MMG), or muscle sound, of the paretic muscle in the affected side of hemiplegic subjects after stroke during isometric voluntary contractions, in comparison with those from the muscle in the unaffected side of the hemiplegic subjects and from the healthy muscle of unimpaired subjects. MMG and electromyography (EMG) signals were recorded simultaneously from the biceps brachii muscles of the dominant arm of unimpaired subjects (n=5) and the unaffected and affected arms of subjects after stroke (n=8), when performing a fatiguing maximal voluntary contraction (MVC) associated with the decrease in elbow flexion torque, and then submaximal elbow flexions at 20%, 40%, 60% and 80% MVCs. The root mean squared (RMS) values, the mean power frequencies (MPF, in the power density spectrum, PDS) of the EMG and MMG, and the high frequency rate (HF-rate, the ratio of the power above 15Hz in the MMG PDS) were used for the analysis. The MMG RMS decreased more slowly during the MVC in the affected muscle compared to the healthy and unaffected muscles. A transient increase could be observed in the MMG MPFs from the unaffected and healthy muscles during the MVC, associated with the decrease in their simultaneous EMG MPFs due to the muscular fatigue. No significant variation could be seen in the EMG and MMG MPFs in the affected muscles during the MVC. The values in the MPF and HF-rate of MMG from the affected muscles were significantly lower than those from the healthy and unaffected muscles (P<0.05) at the high contraction level (80% MVC). Both the MMG and EMG RMS values in the healthy and unaffected groups were found to be significantly higher than the affected group (P<0.05) at 60% and 80% MVCs. These observations were related to an atrophy of the fast-twitch fibers and a reduction of the neural input in the affected muscles of the hemiplegic subjects. The results in this study suggested MMG could be used as a complementary to EMG for the analysis on muscular characteristics in subjects after stroke.     

Bisphenol A induces oxidative stress and mitochondrial dysfunction in lymphoblasts from children with autism and unaffected siblings

Autism is a behaviorally defined neurodevelopmental disorder. Although there is no single identifiable cause for autism, roles for genetic and environmental factors have been implicated in autism. Extensive evidence suggests increased oxidative stress and mitochondrial dysfunction in autism. In this study, we examined whether bisphenol A (BPA) is an environmental risk factor for autism by studying its effects on oxidative stress and mitochondrial function in the lymphoblasts. When lymphoblastoid cells from autistic subjects and age-matched unaffected sibling controls were exposed to BPA, there was an increase in the generation of reactive oxygen species (ROS) and a decrease in mitochondrial membrane potential in both groups. A further subdivision of the control group into two subgroups—unaffected nontwin siblings and twin siblings—showed significantly higher ROS levels without any exposure to BPA in the unaffected twin siblings compared to the unaffected nontwin siblings. ROS levels were also significantly higher in the autism vs the unaffected nontwin siblings group. The effect of BPA on three important mtDNA genes—NADH dehydrogenase 1, NADH dehydrogenase 4, and cytochrome b—was analyzed to observe any changes in the mitochondria after BPA exposure. BPA induced a significant increase in the mtDNA copy number in the lymphoblasts from the unaffected siblings group and in the unaffected twin siblings group vs the unaffected nontwin siblings. In all three genes, the mtDNA increase was seen in 70% of the subjects. These results suggest that BPA exposure results in increased oxidative stress and mitochondrial dysfunction in the autistic subjects as well as the age-matched sibling control subjects, particularly unaffected twin siblings. Therefore, BPA may act as an environmental risk factor for autism in genetically susceptible children by inducing oxidative stress and mitochondrial dysfunction.     

Firing properties of motor units during fatigue in subjects after stroke.

The purpose of this work was to investigate the electromyographic (EMG) fatigue representations in muscles of subjects after stroke at the level of motor unit, based on the analysis of mean power frequency (MPF) in the power density spectrum (PDS) for intramuscular EMG and our previous modeling and experiment studies on the neuromuscular transmission failure (NTF). NTF due to the local muscular fatigue had been captured in motor unit signals from healthy subjects during a submaximal fatigue contraction previously. In this study, the EMG signals for the biceps brachii muscles were collected by needle electrodes from the affected and unaffected arms of six hemiplegic subjects after stroke, and from the dominated arm of six healthy subjects during a full maximum voluntary contraction (MVC) and a subsequent 20% MVC. The MPF of EMG trials detected intramuscularly during the full and 20% MVCs, and the parameters of motor unit action potential trains (MUAPTs) during 20% MVC were analyzed in three groups: the normal (from healthy subjects), unaffected (from subjects after stroke), and affected (from subjects after stroke). It was found that during the full MVC the MPFs of the normal and unaffected groups decreased more than the affected when monitored by a moving time window of 2 s. The comparison on the overall MPF during the full MVC for these three groups over the whole time course of the EMG signal (18 s) were: the affected overall MPF was higher than the unaffected (P < 0.05); and the unaffected overall MPF was larger than the normal (P < 0.05). However, no significant decrease in MPF was found for these three groups during 20% MVC. The NTF was captured in most MUAPTs in the groups of the normal and unaffected rather than in the affected group, symbolized by the lowered rates of change (RCs) of firing rate (FR) (P < 0.05), more MUAPTs with positive RCs of maximum oscillation (MO) in MUAPT power density spectra (P < 0.05), and the significant higher RCs of minimum inter-pulse interval (MINI) (P < 0.05) in the normal and unaffected compared to the affected group. Enhanced neural drives to the motor units of the unaffected and affected groups were observed during 20% MVC, which possibly came from the bilateral neural inputs due to the disinhibition of the ipsilateral projections in subjects after stroke. For identifying the fatigue associated with NTF, the motor unit firing parameters, FR, MINI, and MO, were more sensitive than the MPF. The results obtained in this work provided a further understanding on the EMG of the fatigue processes in paretic and non-paretic muscles during voluntary contractions.     

Nonparametric comparison of two survival-time distributions in the presence of dependent censoring

When testing the null hypothesis that treatment arm-specific survival-time distributions are equal, the log-rank test is asymptotically valid when the distribution of time to censoring is conditionally independent of randomized treatment group given survival time. We introduce a test of the null hypothesis for use when the distribution of time to censoring depends on treatment group and survival time. This test does not make any assumptions regarding independence of censoring time and survival time. Asymptotic validity of this test only requires a consistent estimate of the conditional probability that the survival event is observed given both treatment group and that the survival event occurred before the time of analysis. However, by not making unverifiable assumptions about the data-generating mechanism, there exists a set of possible values of corresponding sample-mean estimates of these probabilities that are consistent with the observed data. Over this subset of the unit square, the proposed test can be calculated and a rejection region identified. A decision on the null that considers uncertainty because of censoring that may depend on treatment group and survival time can then be directly made. We also present a generalized log-rank test that enables us to provide conditions under which the ordinary log-rank test is asymptotically valid. This generalized test can also be used for testing the null hypothesis when the distribution of censoring depends on treatment group and survival time. However, use of this test requires semiparametric modeling assumptions. A simulation study and an example using a recent AIDS clinical trial are provided.     

Power calculations for a general class of tests of linkage and association that use nuclear families with affected and unaffected sibs

Family-based tests of association are now often used when trying to fine-map a disease susceptibility locus. Recently, several tests of linkage and association have been proposed that use nuclear families with multiple affected and unaffected sibs rather than just case-parent triads. In this paper we propose a test that generalizes these previous tests. Formulae are derived to calculate the power of the test for a randomly mating population. These power calculations are used to determine conditions under which it is advantageous to include unaffected sibs in the analysis.     

Nonparametric Methods in Crossover Trials

The crossover design is often used in biomedical trials since it eliminates between subject variability. This paper is concerned with the statistical analysis of data arising from such trials when assumptions like normality do not necessarily apply. Nonparametric analysis of the two-period, two-treatment design was first described by Koch in a paper 1972. The purpose of this paper is to study nonparametric methods in crossover designs with three or more treatments and an equal number of periods. The proposed test for direct treatment effects is based on within subject comparisons after removing a possible period effect. With only two treatments this test reduces to the twosided Wilcoxon signed rank test. By simulation experiments the validity of the significance level of the test when using the asymptotic distribution of the test statistic are manifested and the power against different alternatives illustrated. A test for first order carryover effects can be constructed by a straightforward generalization of the test proposed by Koch in 1972. However, since this test is based on between subject comparisons its power will be low. Our recommendation is to consider the crossover design rather than the parallel group design if the carryover effects are assumed to be neglible or positive and smaller then the direct treatment effects.     

A Maximum Rank-Sum Test for One-Pulse Variation in Monthly Data

A nonparametric test to detect a pulse in monthly data is presented. This test is a maximum rank-sum test. The test statistic can be computed from frequencies or rates. The exact null distribution of the test statistic is tabulated for pulses that last 3, 4, 5, or 6 months. Estimates from a simulation study of the test's type I error rate and power are presented. The statistical modeling of the data is discussed. Several examples are given to illustrate the application of the test and the modeling procedures. Practical matters such as the treatment of tied observations, the effect of unequal lengths in the months, sample-size calculation, and post-test power analysis are discussed and illustrated with examples.     

Some developments on the affected-pedigree-member method of linkage analysis.

Some improvements are presented for the affected-pedigree-member method of linkage analysis, which is a generalization of the sib-pair method. The test statistic is extended to include contrasts between affected and unaffected pedigree members, so that it now utilizes marker information from all typed pedigree members rather than just the typed affected members. Computer simulation using a sample pedigree of 14 individuals shows that this modification can substantially increase statistical power where there is a direct association between marker variation and disease and where disease risk is elevated in carriers of the disease allele. Data on Huntington disease in 16 British families, which were analyzed previously using only the affected individuals, are reanalyzed with the unaffected individuals included. Strong rejection of the null hypothesis of no association between Huntington disease and the HindIII polymorphism is confirmed, but the particular families in which the association is significant differs from that obtained through an analysis based only on affected individuals and reflects more closely the results obtained from a lod-score analysis. The test statistic is also modified here to incorporate contrasts between individuals of zero kinship, if needed. This enables contrasts between individuals from different pedigrees, as well as contrasts involving individuals sampled from the general population, to be incorporated into the test of association. For population data, the methodology reduces to a type of contingency-table analysis, in which the rows of the table correspond to different marker-locus genotypes and in which the two columns categorize subjects into an "affected" group versus an "unaffected," or control, group. This aspect of the methodology is illustrated using two population data sets, the first relating APO-E genotype to the frequency of individuals undergoing maintenance hemodialysis and the second relating APO-B genotype to the frequency of coronary artery disease. The present methodology confirms the lack of association between marker and disease in the former data set and confirms the presence of association in the latter. Finally, the methodology is formulated here in terms of ordinary, multiperson kinship coefficients rather than in terms of the generalized kinship coefficients originally proposed. This greatly reduces the number of coefficients to be calculated, thereby enhancing the computational efficiency of the computer program.     

A modified sign test for comparing paired ROC curves

We develop a permutation test for assessing a difference in the areas under the curve (AUCs) in a paired setting where both modalities are given to each diseased and nondiseased subject. We propose that permutations be made between subjects specifically by shuffling the diseased/nondiseased labels of the subjects within each modality. As these permutations are made within modality, the permutation test is valid even if both modalities are measured on different scales. We show that our permutation test is a sign test for the symmetry of an underlying discrete distribution whose size remains valid under the assumption of equal AUCs. We demonstrate the operating characteristics of our test via simulation and show that our test is equal in power to a permutation test recently proposed by Bandos and others (2005).     

Predictive probability early termination plans for phase II clinical trials

A phase II clinical trial is designed to gather data to help decide whether an experimental treatment has sufficient effectiveness to justify further study. In a one-arm trial with dichotomous outcome, we wish to test a simple null hypothesis on the Bernoulli parameter against a one-sided alternative in a sample of N patients. It is advisable to have a rule to terminate the trial early when evidence accumulates that the treatment is ineffective. Predictive probabilities based on the binomial distribution and beta and uniform prior distributions for the binomial parameter are found to be useful as the basis of group sequential designs. Size, power and average sample size for these designs are discussed. A process for the specification of an early termination plan, advice on the quantification of prior beliefs, and illustrative examples are included.     

Exact tests for the analysis of case-control studies of genetic markers

OBJECTIVES: The association of a candidate gene with disease can be evaluated by a case-control study in which the genotype distribution is compared for diseased cases and unaffected controls. Usually, the data are analyzed with Armitage's test using the asymptotic null distribution of the test statistic. Since this test does not generally guarantee a type I error rate less than or equal to the significance level alpha, tests based on exact null distributions have been investigated. METHODS: An algorithm to generate the exact null distribution for both Armitage's test statistic and a recently proposed modification of the Baumgartner-Weiss-Schindler statistic is presented. I have compared the tests in a simulation study. RESULTS: The asymptotic Armitage test is slightly anticonservative whereas the exact tests control the type I error rate. The exact Armitage test is very conservative, but the exact test based on the modification of the Baumgartner-Weiss-Schindler statistic has a type I error rate close to alpha. The exact Armitage test is the least powerful test; the difference in power between the other two tests is often small and the comparison does not show a clear winner. CONCLUSION: Simulation results indicate that an exact test based on the modification of the Baumgartner-Weiss-Schindler statistic is preferable for the analysis of case-control studies of genetic markers.     

The micronucleus test: statistical design and analysis.

Alternative statistical procedures are discussed which may be employed to compare the incidences among treatment groups of micronucleated polychromatic and normochromatic erythrocytes and their ratios. Comparison of incidences of micronucleated polychromatic erythrocytes using a sequential sampling strategy based on the negative binomial distribution is shown to require fewer animals for the same sensitivity of test than a similar procedure based on the binomial distribution. The sequential test is superior, both in power and number of animals required, to an alternative 1-stage test based on the same distribution. The procedure described permits the investigator to optimize the number of animals in each test group and the number of cells counted per animal to detect a predetermined increase in the incidence of micronucleated cells over that observed in the control population within chosen limits of type I and type II error. An alternative sequential approach based on the binomial distribution is presented, which is applicable when the number of cells analyzed per animal is variable.     

Case-control studies of genetic markers: power and sample size approximations for Armitage's test for trend

The association of a candidate gene with disease can be efficiently evaluated by a case-control study in which allele frequencies are compared for diseased cases and unaffected controls. However, when the distribution of genotypes in the population deviates from Hardy-Weinberg proportions, the frequency of genotypes--rather than alleles--should be compared by the Armitage test for trend. We present formulas for power and sample size for studies that use Armitage's trend test. The formulas make no assumptions about Hardy-Weinberg equilibrium, but do assume random ascertainment of cases and controls, all of whom are independent of one another. We demonstrate the accuracy of the formulas by simulations.     

Analysis of experimental data with repeated measurements

Summary. Experimental data often consist of serial measurements on subjects after a treatment. Typical questions concerning such data are: (A) Do subjects really react to treatment or are the fluctuations just random? (B) What are the numerical characteristics of the response? (C) Is the response identical in all groups? Differences between the individuals in the dynamics of the reaction make it difficult to apply standard statistical procedures. This paper proposes to answer questions (A) and (B) at the individual level, then to give an answer to (C) on the basis of this information. This kind of analysis may be useful since it can separate subjects giving response from those that do not and can identify individual response patterns and compare treatments with respect to each numerical characteristic separately. To answer question (A), a permutation test is proposed and its power is evaluated by simulation.     

Effect of weighted vest suit worn during daily activities on running speed, jumping power, and agility in young men

ABSTRACT: Rantalainen, T, Ruotsalainen, I, and Virmavirta, M. Effect of weighted vest suit worn during daily activities on running speed, jumping power, and agility in young men. J Strength Cond Res 26(11): 3030-3035, 2012-Previous weighted vest interventions using exercise in addition to hypergravity have been successful in improving postural balance and power production capacity. The purpose of this study was to investigate if hypergravity alone in daily activities excluding sporting activities is effective in improving neuromuscular performance in young adults. Eight male subjects (age = 32 [SD: 6] years, height = 178 [5] cm, and body mass = 81 [8] kg) wore weighted vests 3 d·wk for 3 weeks during waking hours, excluding sporting activities. Control group comprised 9 male subjects (age = 32 [6] years, height = 179 [5] cm, and body mass = 83 [9] kg). Performance was assessed with countermovement jump (body mass normalized peak power), figure-of-8 running test (running time), and running velocity test at baseline and at the end of the intervention. At baseline, the groups did not differ from each other (multivariate analysis of variance [MANOVA] p = 0.828). A significant group × time interaction (MANOVA F = 5.1, p = 0.015) was observed for performance variables. Analysis of covariance indicated that the intervention improved the figure-of-8 running time (p = 0.016) (-2.2 vs. 0.5%), whereas normalized peak power (0.0 vs. 1.6%) and running velocity (1.3 vs. 0.1%) were unaffected (p ≥ 0.095). Wearing weighted vests was effective in slightly improving agility-related performance in young men. Because the effect was small, applying hypergravity only during exercise probably suffices. It appears that a proper volume and intensity of hypergravity could be in the order of 5-10% body weight vest worn during up to 50% of the training sessions for a period of 3-4 weeks.     

Poor efficacy of residual chlorine disinfectant in drinking water to inactivate waterborne pathogens in distribution systems.

To evaluate the inactivating power of residual chlorine in a distribution system, test microorganisms (Escherichia coli, Clostridium perfringens, bacteriophage phi-X 170, and poliovirus type 1) were added to drinking water samples obtained from two water treatment plants and their distribution system. Except for Escherichia coli, microorganisms remained relatively unaffected in water from the distribution systems tested. When sewage was added to the water samples, indigenous thermotolerant coliforms were inactivated only when water was obtained from sites very close to the treatment plant and containing a high residual chlorine concentration. Clostridium perfringens was barely inactivated, suggesting that the most resistant pathogens such as Giardia lamblia, Cryptosporidium parvum, and human enteric viruses would not be inactivated. Our results suggest that the maintenance of a free residual concentration in a distribution system does not provide a significant inactivation of pathogens, could even mask events of contamination of the distribution, and thus would provide only a false sense of safety with little active protection of public health. Recent epidemiological studies that have suggested a significant waterborne level of endemic gastrointestinal illness could then be explained by undetected intrusions in the distribution system, intrusions resulting in the infection of a small number of individuals without eliciting an outbreak situation.