A mover-stayer mixture of Markov chain models for the assessment of dedifferentiation and tumour progression in breast cancer

SUMMARY Malignancy grade is a histological measure of attributes related to a breast tumour's aggressive potential. It is not established whether the grade is an inate characteristic which remains unchanged throughout the tumour's development or whether it evolves as the tumour grows. It is likely that a proportion of tumours have the potential to evolve, and so a statistical method was required to assess this hypothesis and, if possible, to estimate the proportion with the potential for evolution. Therefore, a mover-stayer mixture of Markov chain models was developed, with the complication that 'movers' were unobservable because tumours were excised on diagnosis. A quasi-likelihood method was used for estimation. The methods are demonstrated using data from the Swedish twocounty trial of breast-cancer screening.     

Simulated deficiencies of robust estimators of a proportionality constant

In linear regression, robust methods are at the beginning of their use in practice. In the small sample case, such robust methods provide a necessary measure of protection against deviations from the assumed error distribution. This paper studies through simulation the deficiencies of bioptimal estimators and compares them with more common methods like Huber's estimator or Tukey's estimator. Polyoptimal estimators are convex combinations of Pitman estimators and are optimally robust for a confrontation containing several shapes. The word confrontation is due to J.W. Tukey. It expresses the situation when compromising two or several error distributions. The paper uses the confrontation containing the Gaussian distribution along with a symmetric heavy-tailed distribution having a tail of order 0(t^-2) as t→ ±∞.     

The effect of dependence on distribution of the functions of random variables

In this article, we study the effect of dependence on the distributional properties of functions of two random variables. Expressions for the cumulative distribution functions of the linear combinations, products, and ratios of two dependent random variables in terms of their associated copula are derived. We discuss the effect of dependence on quantities such as the variances of linear combinations of functions, the value-at-risk measure, and the stress–strength parameter. Several examples, a simulation study, and a real data analysis are provided to illustrate the result.     

Robustness to non-normality and autocorrelation of individuals control charts

This paper studies the effects of non-normality and autocorrelation on the performances of various individuals control charts for monitoring the process mean and/or variance. The traditional Shewhart X chart and moving range (MR) chart are investigated as well as several types of exponentially weighted moving average (EWMA) charts and combinations of control charts involving these EWMA charts. It is shown that the combination of the X and MR charts will not detect small and moderate parameter shifts as fast as combinations involving the EWMA charts, and that the performana of the X and MR charts is very sensitive to the normality assumption. It is also shown that certain combinations of EWMA charts can be designed to be robust to non-normality and very effective at detecting small and moderate shifts in the process mean and/or variance. Although autocorrelation can have a significant effect on the in-control performances of these combinations of EWMA charts, their relative out-of-control performances under independence are generally maintained for low to moderate levels of autocorrelation.     

A concentration approach to sensitivity studies in statistical estimation problems

It is shown that the concept of concentration is of potential interest in the sensitivity study of some parameters and related estimators. Basic ideas are introduced for a real parameter θ>0 together with graphical representations using Lorenz curves of concentration. Examples based on the mean, standard deviation and variance are provided for some classical distributions. This concentration approach is also discussed in relation with influence functions. Special emphasis is given to the average concentration of an estimator which provides a sensitivity measure allowing one to compare several estimators of the same parameter. Properties of this measure are investigated through simulation studies and its practical interest is illustrated by examples based on the trimmed mean and the Winsorized variance.     

Modelling PK/QT relationships from Phase I dose‐escalation trials for drug combinations and developing quantitative risk assessments of clinically relevant QT prolongations

In current industry practice, it is difficult to assess QT effects at potential therapeutic doses based on Phase I dose‐escalation trials in oncology due to data scarcity, particularly in combinations trials. In this paper, we propose to use dose‐concentration and concentration‐QT models jointly to model the exposures and effects of multiple drugs in combination. The fitted models then can be used to make early predictions for QT prolongation to aid choosing recommended dose combinations for further investigation. The models consider potential correlation between concentrations of test drugs and potential drug–drug interactions at PK and QT levels. In addition, this approach allows for the assessment of the probability of QT prolongation exceeding given thresholds of clinical significance. The performance of this approach was examined via simulation under practical scenarios for dose‐escalation trials for a combination of two drugs. The simulation results show that invaluable information of QT effects at therapeutic dose combinations can be gained by the proposed approaches. Early detection of dose combinations with substantial QT prolongation is evaluated effectively through the CIs of the predicted peak QT prolongation at each dose combination. Furthermore, the probability of QT prolongation exceeding a certain threshold is also computed to support early detection of safety signals while accounting for uncertainty associated with data from Phase I studies. While the prediction of QT effects is sensitive to the dose escalation process, the sensitivity and limited sample size should be considered when providing support to the decision‐making process for further developing certain dose combinations. Copyright © 2016 John Wiley & Sons, Ltd.     

Parametric modelling of prevalent cohort data with uncertainty in the measurement of the initial onset date

In prevalent cohort studies with follow-up, if disease duration is the focus, the date of onset must be obtained retrospectively. For some diseases, such as Alzheimer’s disease, the very notion of a date of onset is unclear, and it can be assumed that the reported date of onset acts only as a proxy for the unknown true date of onset. When adjusting for onset dates reported with error, the features of left-truncation and potential right-censoring of the failure times must be modeled appropriately. Under the assumptions of a classical measurement error model for the onset times and an underlying parametric failure time model, we propose a maximum likelihood estimator for the failure time distribution parameters which requires only the observed backward recurrence times. Costly and time-consuming follow-up may therefore be avoided. We validate the maximum likelihood estimator on simulated datasets under varying parameter combinations and apply the proposed method to the Canadian Study of Health and Aging dataset.

     

Noninformative priors for the nested design

This paper considers noninformative priors for three-stage nested designs. It turns out that the noninformative prior given by Li and Stern (1997) is the one-at-a-time reference prior satisfying a second-order matching criterion when either the variance ratio or linear combinations of the means is of interest. Moreover, it is a joint probability matching prior when both the variance ratio and linear combinations of the means are of interest. These priors are compared with Jeffreys' prior in light of how accurately the coverage probabilities of Bayesian credible intervals match the corresponding frequentist coverage probabilities.     

Analyzing survival data in conjunction with time-dependent surrogate endpoints in clinical trials

Current survival techniques do not provide a good method for handling clinical trials with a large percent of censored observations. This research proposes using time-dependent surrogates of survival as outcome variables, in conjunction with observed survival time, to improve the precision in comparing the relative effects of two treatments on the distribution of survival time. This is in contrast to the standard method used today which uses the marginal density of survival time, T. only, or the marginal density of a surrogate, X, only, therefore, ignoring some available information. The surrogate measure, X, may be a fixed value or a time-dependent variable, X(t). X is a summary measure of some of the covariates measured throughout the trial that provide additional information on a subject's survival time. It is possible to model these time-dependent covariate values and relate the parameters in the model to the parameters in the distribution of T given X. The result is that three new models are available for the analysis of clinical trials. All three models use the joint density of survival time and a surrogate measure. Given one of three different assumed mechanisms of the potential treatment effect, each of the three methods improves the precision of the treatment estimate.     

Model selection for logistic regression via association rules analysis

Interaction is very common in reality, but has received little attention in logistic regression literature. This is especially true for higher-order interactions. In conventional logistic regression, interactions are typically ignored. We propose a model selection procedure by implementing an association rules analysis. We do this by (1) exploring the combinations of input variables which have significant impacts to response (via association rules analysis); (2) selecting the potential (low- and high-order) interactions; (3) converting these potential interactions into new dummy variables; and (4) performing variable selections among all the input variables and the newly created dummy variables (interactions) to build up the optimal logistic regression model. Our model selection procedure establishes the optimal combination of main effects and potential interactions. The comparisons are made through thorough simulations. It is shown that the proposed method outperforms the existing methods in all cases. A real-life example is discussed in detail to demonstrate the proposed method.     

A Method to Generate Multivariate Data with the Desired Moments

We show how it is possible to generate multivariate data which has moments arbitrary close to the desired ones. They are generated as linear combinations of variables with known theoretical moments. It is shown how to derive the weights of the linear combinations in both the univariate and the multivariate setting. The use in bootstrapping is discussed and the method is exemplified with a Monte Carlo simulation where the importance of the ability of generating data with control of higher moments is shown.     

Robust designs for linear mixed effects models

Summary.  In health sciences, medicine and social sciences linear mixed effects models are often used to analyse time-structured data. The search for optimal designs for these models is often hampered by two problems. The first problem is that these designs are only locally optimal. The second problem is that an optimal design for one model may not be optimal for other models. In this paper the maximin principle is adopted to handle both problems, simultaneously. The maximin criterion is formulated by means of a relative efficiency measure, which gives an indication of how much efficiency is lost when the uncertainty about the models over a prior domain of parameters is taken into account. The procedure is illustrated by means of three growth studies. Results are presented for a vocabulary growth study from education, a bone gain study from medical research and an epidemiological decline in height study. It is shown that, for the mixed effects polynomial models that are applied to these studies, the maximin designs remain highly efficient for different sets of models and combinations of parameter values.     

Primal and Dual Capacity Utilization: An Application to Productivity Measurement in the U.S. Automobile Industry

Capacity utilization measures have traditionally been constructed as indexes of actual, as compared to “potential,” output. This potential or capacity output (Y*) can be represented within an economic model of the firm as the tangency between the short- and long-run average cost curves. Economic theoretical measures of capacity utilization (CU) can then be characterized as Y/Y* where Y is the realized level of output. These quantity or primal CU measures allow for economic interpretation; they provide explicit inference as to how changes in exogenous variables affect CU. Additional information for analyzing deviations from capacity production can be obtained by assessing the “dual” cost of the gap.

In this article the definitions and representations of primal-output and dual-cost CU measures are formalized within a dynamic model of a monopolistic firm. As an illustration of this approach to characterizing CU measures, a model is estimated for the U.S. automobile industry, 1959–1980, and primal and dual CU indexes are constructed. Application of these indexes to adjustment-of-productivity measures for “disequilibrium” is then carried out, using the dual-cost measure.     

Risk analysis in the brazilian stock market: copula-APARCH modeling for value-at-risk

Risk management of stock portfolios is a fundamental problem for the financial analysis since it indicates the potential losses of an investment at any given time. The objective of this study is to use bivariate static conditional copulas to quantify the dependence structure and to estimate the risk measure Value-at-Risk (VaR). There were selected stocks that have been performing outstandingly on the Brazilian Stock Exchange to compose pairs trading portfolios (B3, Gerdau, Magazine Luiza, and Petrobras). Due to the flexibility that this methodology offers in the construction of multivariate distributions and risk aggregation in finance, we used the copula-APARCH approach with the Normal, T-student, and Joe-Clayton copula functions. In most scenarios, the results showed a pattern of dependence at the extremes. Moreover, the copula form seems not to be relevant for VaR estimation, since in most portfolios the appropriate copulas lead to significant VaR estimates. It has found that the best models fitted provided conservative risk measures, estimates at 5% and 1%, in a scenario more aggressive.     

How Important Is the Effect of Rounding in Goodness-of-Fit

Abstract

In the area of goodness-of-fit there is a clear distinction between the problem of testing the fit of a continuous distribution and that of testing a discrete distribution. In all continuous problems the data is recorded with a limited number of decimals, so in theory one could say that the problem is always of a discrete nature, but it is a common practice to ignore discretization and proceed as if the data is continuous. It is therefore an interesting question whether in a given problem of test of fit, the “limited resolution” in the observed recorded values may be or may be not of concern, if the analysis done ignores this implied discretization. In this article, we address the problem of testing the fit of a continuous distribution with data recorded with a limited resolution. A measure for the degree of discretization is proposed which involves the size of the rounding interval, the dispersion in the underlying distribution and the sample size. This measure is shown to be a key characteristic which allows comparison, in different problems, of the amount of discretization involved. Some asymptotic results are given for the distribution of the EDF (empirical distribution function) statistics that explicitly depend on the above mentioned measure of degree of discretization. The results obtained are illustrated with some simulations for testing normality when the parameters are known and also when they are unknown. The asymptotic distributions are shown to be an accurate approximation for the true finite n distribution obtained by Monte Carlo. A real example from image analysis is also discussed. The conclusion drawn is that in the cases where the value of the measure for the degree of discretization is not “large”, the practice of ignoring discreteness is of no concern. However, when this value is “large”, the effect of ignoring discreteness leads to an exceded number of rejections of the distribution tested, as compared to what would be the number of rejections if no rounding is taking into account. The error made in the number of rejections might be huge.     

Determining Optimal Number of Samples for Constructing Multivariate Control Charts

Normally, an average run length (ARL) is used as a measure for evaluating the detecting performance of a multivariate control chart. This has a direct impact on the false alarm cost in Phase II. In this article, we first conduct a simulation study to calculate both in-control and out-of-control ARLs under various combinations of process shifts and number of samples. Then, a trade-off analysis between sampling inspection and false alarm costs is performed. Both the simulation results and trade-off analysis suggest that the optimal number of samples for constructing a multivariate control chart in Phase I can be determined.     

Nonparametric estimation of the canonical measure for infinitely divisible distributions

Infinitely divisible distributions (i.d.d.'s) with a finite variance have a characteristic function of a particular form. The exponent is written in terms of the canonical or Kolmogorov measure. This paper considers a nonparametric estimate of the Kolmogorov measure based on the empirical characteristic function (e.c.f.) and a truncation. The weak convergence of this estimator is studied. The raw form of the estimator is a functional of the e.c.f., but to be useful in a finite sample it requires some additional smoothing. Thus smoothed estimators are considered. A dynamic data dependent method of truncation is given. A simulation study is undertaken to show how the Kolmogorov measure can be estimated, as well as giving an illustration of the numerical stability questions. It is also seen that a large sample size is needed.     

Pitman closeness comparison of linear estimators:a canonical form

A general form is presented for the comparison of two linear estimators of a common parameter by means of the Pitman measure of closeness. Several asymptotic results are given. The case in which the estimators are linear combinations of the order statistics is discussed. The asymptotic comparison of the sample mean versus the sample median is derived for the Laplace distribution, and two other examples are given.     

On the distribution of linear combinations of the components of a Dirichlet random vector

On making use of a result of Imhof, an integral representation of the distribution function of linear combinations of the components of a Dirichlet random vector is obtained. In fact, the distributions of several statistics such as Moran and Geary's indices, the Cliff‐Ord statistic for spatial correlation, the sample coefficient of determination, F‐ratios and the sample autocorrelation coefficient can be similarly determined. Linear combinations of the components of Dirichlet random vectors also turn out to be a key component in a decomposition of quadratic forms in spherically symmetric random vectors. An application involving the sample spectrum associated with series generated by ARMA processes is discussed.     

The disagreeable behaviour of the kappa statistic

It is often of interest to measure the agreement between a number of raters when an outcome is nominal or ordinal. The kappa statistic is used as a measure of agreement. The statistic is highly sensitive to the distribution of the marginal totals and can produce unreliable results. Other statistics such as the proportion of concordance, maximum attainable kappa and prevalence and bias adjusted kappa should be considered to indicate how well the kappa statistic represents agreement in the data. Each kappa should be considered and interpreted based on the context of the data being analysed. Copyright © 2014 JohnWiley & Sons, Ltd.