Canadian Journal of Statistics-Revue Canadienne De Statistique最新文献

In countries where population census data are limited, generating accurate subnational estimates of health and demographic indicators is challenging. Existing model-based geostatistical methods leverage covariate information and spatial smoothing to reduce the variability of estimates but often ignore the survey design, while traditional small area estimation approaches may not incorporate both unit-level covariate information and spatial smoothing in a design consistent way. We propose a smoothed model-assisted estimator that accounts for survey design and leverages both unit-level covariates and spatial smoothing. Under certain regularity assumptions, this estimator is both design consistent and model consistent. We compare it with existing design-based and model-based estimators using real and simulated data.

The augmented inverse weighting (AIW) estimator is commonly used to estimate the marginal mean of an outcome because of its doubly robust property. However, the AIW estimator can be severely biased if both the propensity score (PS) and the outcome regression (OR) models are misspecified. One possible reason is that misspecification of the PS or OR model yields extreme values in these models, which can have a great influence on the marginal mean estimate. In this article, we propose a calibrated AIW estimator for the marginal mean, which can control the influence of these extreme values and provide a stable marginal mean estimator. The proposed estimator also enjoys the doubly robust property. We also extend this method to handle high-dimensional covariates in PS and OR models. Asymptotic results are also developed. Extensive simulation studies show that the proposed method performs better in most cases than existing approaches by providing a more stable estimate. We apply this method to an AIDS clinical trial study.

Multiple oscillating time series are typically analyzed in the frequency domain, where coherence is usually said to represent the magnitude of the correlation between two signals at a particular frequency. The correlation being referenced is complex-valued and is similar to the real-valued Pearson correlation in some ways but not others. We discuss the dependence among oscillating series in the context of the multivariate complex normal distribution, which plays a role for vectors of complex random variables analogous to the usual multivariate normal distribution for vectors of real-valued random variables. We emphasize special cases that are valuable for the neural data we are interested in and provide new variations on existing results. We then introduce a complex latent variable model for narrowly band-pass-filtered signals at some frequency, and show that the resulting maximum likelihood estimate produces a latent coherence that is equivalent to the magnitude of the complex canonical correlation at the given frequency. We also derive an equivalence between partial coherence and the magnitude of complex partial correlation, at a given frequency. Our theoretical framework leads to interpretable results for an interesting multivariate dataset from the Allen Institute for Brain Science.

The purpose of this article is to study serial correlations, allowing for unconditional heteroscedasticity and time-varying probabilities of zero financial returns. Depending on the set-up, we investigate how the standard autocorrelations can be accommodated to deliver an accurate representation of the serial correlations of stock price changes. We shed light on the properties of the different serial correlations measures by means of Monte Carlo experiments. Theoretical results are also illustrated on shares from the Chilean stock market and Facebook stock intraday data.

Existing methods for fitting spatial autoregressive models have various strengths and weaknesses. For example, the maximum likelihood estimation (MLE) approach yields efficient estimates but is computationally burdensome. Computationally efficient methods, such as generalized method of moments (GMMs) and spatial two-stage least squares (2SLS), typically require exogenous covariates to be significant, a restrictive assumption that may fail in practice. We propose a new estimating equation approach, termed combined moment equation (COME), which combines the first moment with covariance conditions on the residual terms. The proposed estimator is less computationally demanding than MLE and does not need the restrictive exogenous conditions as required by GMM and 2SLS. We show that the proposed estimator is consistent and establish its asymptotic distribution. Extensive simulations demonstrate that the proposed method outperforms the competitors in terms of bias, efficiency, and computation. We apply the proposed method to analyze an air pollution study, and obtain some interesting results about the spatial distribution of PM2.5 concentrations in Beijing.

Modelling multivariate survival data is complicated by the complex association structure among the responses. To balance model flexibility and interpretability, we propose a semiparametric copula model to modulate multivariate survival data, with the marginal distributions of the response components described by semiparametric linear transformation models. To conduct inference about the model parameters, we develop a two-stage maximum likelihood method and a three-stage pseudo-likelihood estimation procedure. We investigate the impact of model misspecification on the estimation of covariate effects and identify a scenario in which consistent estimation of the marginal parameters is retained even when the copula model is misspecified. The proposed methods are justified both theoretically and empirically. An application to a real dataset is provided to demonstrate the utility of the proposed method.

On average, randomization achieves balance in covariate distributions between treatment groups; yet in practice, chance imbalance exists post randomization, which increases the error in estimating treatment effects. This is an important issue, especially in cluster randomized trials, where the experimental units (the clusters) are highly heterogeneous and relatively few in number. To address this, several restricted randomization designs have been proposed to balance on a few covariates of particular interest. More recently, approaches involving rerandomization have been proposed that aim to achieve simultaneous balance on several important prognostic factors. In this article, we comment on some properties of rerandomized designs and propose a new design for comparing two or more treatments. This design combines optimal nonbipartite matching of the subjects together with rerandomization, both aimed at minimizing a measure of distance between elements in blocks to achieve reductions in the mean squared error of estimated treatment effects. Compared with the existing alternatives, the proposed design can substantially reduce the mean squared error of the estimated treatment effect. This enhanced efficiency is evaluated both theoretically and empirically, and robustness properties are also noted. The design is generalized to three or more treatment arms.

The presence of measurement error is a widespread issue, which, when ignored, can render the results of an analysis unreliable. Numerous corrections for the effects of measurement error have been proposed and studied, often under the assumption of a normally distributed, additive measurement-error model. In many situations, observed data are nonsymmetric, heavy-tailed, or otherwise highly non-normal. In these settings, correction techniques relying on the assumption of normality are undesirable. We propose an extension of simulation extrapolation that is nonparametric in the sense that no specific distributional assumptions are required on the error terms. The technique can be implemented when either validation data or replicate measurements are available, and is designed to be immediately accessible to those familiar with simulation extrapolation.

In supervised learning, feature selection methods identify the most relevant predictors to include in a model. For linear models, the inclusion or exclusion of each variable may be represented as a vector of bits playing the role of the genetic material that defines the model. Genetic algorithms reproduce the strategies of natural selection on a population of models to identify the best. We derive the distribution of the importance scores for parallel genetic algorithms under the null hypothesis that none of the features has predictive power. They, hence, provide an objective threshold for feature selection that does not require the visual inspection of a bubble plot. We also introduce the eradication strategy, akin to forward stepwise selection, where the genes of useful variables are sequentially forced into the models. The method is illustrated on real data, and simulation studies are run to describe its performance.

The existence of immune or cured individuals in a population and whether there is sufficient follow-up in a sample of censored observations on their lifetimes to be confident of their presence are questions of major importance in medical survival analysis. Here we give a detailed analysis of a statistic designed to test for sufficient follow-up in a sample. Assuming an i.i.d. censoring model, we obtain exact finite-sample and asymptotic distributions for the statistic, and use these to calculate the power of a test based on it. A particularly useful finding is that the asymptotic distribution of the test statistic is parameter-free in the null case when follow-up is insufficient. The methods are illustrated with application to a glioma cancer dataset.