Assessing the concept of controlled experiments in science teachers

Biology teachers, attending a post-graduate training course, were given a written test in which they had to identify the controlled set-up in two different experiments. A teaching strategy was designed to help the subjects to construct and consolidate an understanding of controlled experiments, in line with scientific inquiry methods, by following the process of hypothesis, formulation and testing.     

Tutorial: using confidence curves in medical research

Confidence intervals represent a routinely used standard method to document the uncertainty of estimated effects. In most cases, for the calculation of confidence intervals the conventional fixed 95% confidence level is used. Confidence curves represent a graphical illustration of confidence intervals for confidence levels varying between 0 and 100%. Although such graphs have been repeatedly proposed under different names during the last 40 years, confidence curves are rarely used in medical research. In this paper, we introduce confidence curves and present a short historical review. We draw attention to the different interpretation of one- and two-sided statistical inference. It is shown that these two options also have influence on the plotting of appropriate confidence curves. We illustrate the use of one- and two-sided confidence curves and explain their correct interpretation. In medical research more emphasis on the choice between the one- and two-sided approaches should be given. One- and two-sided confidence curves are useful complements to the conventional methods of presenting study results.     

Use of binomial group testing in tests of hypotheses for classification or quantitative covariables

In group testing, the test unit consists of a group of individuals. If the group test is positive, then one or more individuals in the group are assumed to be positive. A group observation in binomial group testing can be, say, the test result (positive or negative) for a pool of blood samples that come from several different individuals. It has been shown that, when the proportion (p) of infected individuals is low, group testing is often preferable to individual testing for identifying infected individuals and for estimating proportions of those infected. We extend the potential applications of group testing to hypothesis-testing problems wherein one wants to test for a relationship between p and a classification or quantitative covariable. Asymptotic relative efficiencies (AREs) of tests based on group testing versus the usual individual testing are obtained. The Pitman ARE strongly favors group testing in many cases. Small-sample results from simulation studies are given and are consistent with the large-sample (asymptotic) findings. We illustrate the potential advantages of group testing in hypothesis testing using HIV-1 seroprevalence data.     

Generalized inferences on the overall treatment effect in meta-analysis with normally distributed outcomes

This paper focuses on inferences about the overall treatment effect in meta-analysis with normally distributed responses based on the concepts of generalized inference. A refined generalized pivotal quantity based on t distribution is presented and simulation study shows that it can provide confidence intervals with satisfactory coverage probabilities and perform hypothesis testing with satisfactory type-I error control at very small sample sizes.     

A Further Problem of Interval Estimation of an Unknown Regressor in Model I of Linear Regression

For the model y = α + βx + ? (model I) of linear regression we dealt with in KUHNERT and HORN (1980) the determination of a confidence interval for that x₀ where the expectation Ey reaches a given value y₀. Here we start with realizations of random variables y (i = 1,…, m) being independent of x which are given in addition to the realizations of-y. Now y₀ denotes the unknown value of \documentclass{article}\pagestyle{empty}\begin{document}$ \mathop \sum \limits_{i = 1}^m $\end{document} ciEy and x₀ the x-value where the expectation Ey reaches that value y₀. For this x₀ we give a confidence interval. Applications stem from dose response assays.     

Assessing the implications of publication bias for two popular estimates of between-study variance in meta-analysis

Perhaps the greatest threat to the validity of a meta-analysis is the possibility of publication bias, where studies with interesting or statistically significant results are more likely to be published. This obviously impacts on inference concerning the treatment effect but also has implications for estimates of between-study variance. Two popular and established estimation methods are considered and formulae for assessing the implications of the bias are provided in terms of a general process for selecting studies. Meta-analysts, concerned that publication bias may be present, can use these as part of a sensitivity analysis to assess the robustness of their estimates of between-study variance using any selection process that is likely to be used in practice. The procedure is illustrated using a meta-analysis of clinical trials concerning the effectiveness of endoscopic sclerotherapy for preventing death in patients with cirrhosis and oesophagogastric varices.     

The Binary Regression Quantile Plot: Assessing the Importance of Predictors in Binary Regression Visually

We present a graphical measure of assessing the explanatory power of regression models with a binary response. The binary regression quantile plot and an area defined by it are used for the visual comparison and ordering of nested binary response regression models. The plot shows how well various models explain the data. Two data sets are analyzed and the area representing the fit of a model is shown to agree with the usual likelihood ratio test.     

Confidence Interval of a Proportion with Over‐dispersion

A new approach that extends the classical Clopper‐Pearson procedure is proposed for the estimation of the (1–α)% confidence interval of a proportion with over‐dispersion. Over‐dispersion occurs when a proportion of interest shows more variation (variance inflation) than predicted by the binomial distribution. There are two steps in the approach. The first step consists of the estimation of the variance inflation factor. In the second step, an extended Clopper‐Pearson procedure is applied to calculate the confidence interval after the effective sample size is obtained by adjusting with the estimated variance inflation factor. The performance of the extended Clopper‐Pearson procedure is evaluated via a Monte Carlo study under the setup motivated from head lice studies. It is demonstrated that the 95% confidence intervals constructed from the new approach generally have the closest coverage rate to target (95%) when compared with those constructed from competing procedures.     

Interval Estimation of the Effective Population Size from Heterozygote‐Excess in SNP Markers

The effective population size N_e is an important parameter in population genetics and conservation biology. In recent years, there has been great interest in the use of molecular markers to estimate N_e. Although the point estimates from molecular markers in general suffer from a low reliability, the use of single nucleotide polymorphism (SNP) markers over a wide range of genome is expected to remarkably improve the reliability. In this study, expressions were derived for interval estimates of N_e from one published method, the heterozygote‐excess method, when it is applied to SNP markers. The conditional variance theory is applied to the derivation of a confidence interval for N_e under random union of gametes, monogamy and polygyny. Stochastic simulation shows that the obtained confidence interval is slightly conservative, but fairly useful for practical applications. The result is illustrated with real data on SNP markers in a pig strain.     

Sample Size Calculation for Clinical Studies on the Efficacy of a New Contraceptive Method

The current guideline of the European Agency for the Evaluation of Medicinal Products (EMEA) on the clinical investigation of steroid contraceptives in women, which was prepared by the Committee for Proprietary Medicinal Products (CPMP), calls for the calculation of a confidence interval for the Pearl Index, a widely used measure to describe the reliability of a contraceptive method. The key studies should be large enough to give a Pearl Index with a 95% confidence interval such that the difference between the upper limit of the confidence interval and the corresponding point estimate does not exceed a given margin. As a consequence of this guidance, the success probability of a Pearl Index study is given by its capability, i.e. probability to fulfil this criterion. The resulting power function based on the necessary exposure time does not increase strictly. The minimum exposure time T_min should be calculated such that this function exceeds a given probability for all T ≥ T_min. In this paper, the underlying model is discussed, and definitions and formulae are given for the assumption of a Poisson model. The necessary total exposure time is calculated as a function of a given true pregnancy rate. In addition, some simulations were conducted for the model where a drop‐out mechanism is incorporated into the process. Assuming an exponential distribution for the time to drop‐out the phenomenon that the power does not increase strictly with exposure time is less pronounced. (© 2004 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

自花授粉作物杂交育种组合潜势的预测和比较

在黄花烟草Nicotiana russica中,开花期这一性状用V_5作亲本可能产生较大变异,无论是选择早开花的还是选择迟开花的,都有较大机会得到理想目标株系;对于株高这一性状,含有V(?)的组合可望有较大机会产生高于标准品种的株系。通过组合间育种潜势的比较,能了解各亲本中基因分布的基本情况,进而进行客观评价并对杂交组合做出取舍。试验证明,用一个组合的早期世代的参数m和D来预测高世代或纯系的育种潜势是可行的。     

Elimination of a genetic correlation between the sexes via artificial correlational selection

Genetic correlations between the sexes can constrain the evolution of sexual dimorphism and be difficult to alter, because traits common to both sexes share the same genetic underpinnings. We tested whether artificial correlational selection favoring specific combinations of male and female traits within families could change the strength of a very high between-sex genetic correlation for flower size in the dioecious plant Silene latifolia. This novel selection dramatically reduced the correlation in two of three selection lines in fewer than five generations. Subsequent selection only on females in a line characterized by a lower between-sex genetic correlation led to a significantly lower correlated response in males, confirming the potential evolutionary impact of the reduced correlation. Although between-sex genetic correlations can potentially constrain the evolution of sexual dimorphism, our findings reveal that these constraints come not from a simple conflict between an inflexible genetic architecture and a pattern of selection working in opposition to it, but rather a complex relationship between a changeable correlation and a form of selection that promotes it. In other words, the form of selection on males and females that leads to sexual dimorphism may also promote the genetic phenomenon that limits sexual dimorphism.     

Testing and estimation of time-varying cause-specific hazard ratios with covariate adjustment

SUMMARY: In the evaluation of efficacy of a vaccine to protect against disease caused by a genetically diverse infectious pathogen, it is often important to assess whether vaccine protection depends on variations of the exposing pathogen. This problem can be viewed within the framework of a K-competing risks model where the endpoint event is pathogen-specific infection and the cause of failure is the strain type determined after the infection is diagnosed. The Cox model with time-dependent coefficients is used to relate the cause-specific outcomes to explanatory variables to allow for time-varying treatment effects. The strain-specific vaccine efficacy can be defined in terms of one minus the cause-specific hazard ratios. We develop inferential methods for testing whether the vaccine affords some protection against at least one pathogen strain, and for testing equal vaccine protection against the strains, adjusting for covariate effects. We also consider estimation of covariate-adjusted time-varying strain-specific vaccine efficacy. The methods are applied to a dataset from an oral cholera vaccine trial and the performances of the proposed tests are studied through simulations. These techniques apply more generally for testing and estimation of time-varying cause-specific hazard ratios.     

A Monte Carlo evaluation of five interval estimators for the relative risk in sparse data

The relative risk (RR) is one of the most frequently used indices to measure the strength of association between a disease and a risk factor in etiological studies or the efficacy of an experimental treatment in clinical trials. In this paper, we concentrate attention on interval estimation of RR for sparse data, in which we have only a few patients per stratum, but a moderate or large number of strata. We consider five asymptotic interval estimators for RR, including a weighted least-squares (WLS) interval estimator with an ad hoc adjustment procedure for sparse data, an interval estimator proposed elsewhere for rare events, an interval estimator based on the Mantel-Haenszel (MH) estimator with a logarithmic transformation, an interval estimator calculated from a quadratic equation, and an interval estimator derived from the ratio estimator with a logarithmic transformation. On the basis of Monte Carlo simulations, we evaluate and compare the performance of these five interval estimators in a variety of situations. We note that, except for the cases in which the underlying common RR across strata is around 1, using the WLS interval estimator with the adjustment procedure for sparse data can be misleading. We note further that using the interval estimator suggested elsewhere for rare events tends to be conservative and hence leads to loss of efficiency. We find that the other three interval estimators can consistently perform well even when the mean number of patients for a given treatment is approximately 3 patients per stratum and the number of strata is as small as 20. Finally, we use a mortality data set comparing two chemotherapy treatments in patients with multiple myeloma to illustrate the use of the estimators discussed in this paper.