Dependent SiZer: Goodness-of-Fit Tests for Time Series Models

In this paper, we extend SiZer (SIgnificant ZERo crossing of the derivatives) to dependent data for the purpose of goodness-of-fit tests for time series models. Dependent SiZer compares the observed data with a specific null model being tested by adjusting the statistical inference using an assumed autocovariance function. This new approach uses a SiZer type visualization to flag statistically significant differences between the data and a given null model. The power of this approach is demonstrated through some examples of time series of Internet traffic data. It is seen that such time series can have even more burstiness than is predicted by the popular, long- range dependent, Fractional Gaussian Noise model.     

SiZer inference for generalized varying coefficient models

ABSTRACT

SiZer (significant zero crossings of derivatives) is an effective tool for exploring significant features in curves from the viewpoint of the scale space theory. In this paper, a SiZer approach is developed for generalized varying coefficient models (GVCMs) in order to achieve the task of understanding dynamic characteristics of the regression relationship at multiscales. The proposed SiZer method is based on the local-linear maximum likelihood estimation of GVCMs and the one-step estimation procedure is employed to alleviate the computational cost of estimating the coefficients and their derivatives at different scales. Simulation studies are performed to assess the performance of the SiZer inference and two real-world examples are given to demonstrate its applications.     

SiZer Inference for Varying Coefficient Models

Varying coefficient models are a useful statistical tool to explore dynamic patterns of a regression relationship, in which the variation features of the regression coefficients are taken as the main evidence to reflect the dynamic relationship between the response and the explanatory variables. In this study, we propose a SiZer approach as a visually diagnostic device to uncover the statistically significant features of the coefficients. This method can highlight the significant structures of the coefficients under different scales and can therefore extract relatively full information in the data. The simulation studies and real-world data analysis show that the SiZer approach performs satisfactorily in mining the significant features of the coefficients.     

SiZer analysis for the comparison of time series

SiZer (SIgnificant ZERo crossing of the derivatives) is a scale-space visualization tool for statistical inferences. In this paper we introduce a graphical device, which is based on SiZer, for the test of the equality of the mean of two time series. The estimation of the quantile in a confidence interval is theoretically justified by advanced distribution theory. The extension of the proposed method to the comparison of more than two time series is also done using residual analysis. A broad numerical study is conducted to demonstrate the sample performance of the proposed tool. In addition, asymptotic properties of SiZer for the comparison of two time series are investigated.     

A Stochastic Geometry Model for Functional Magnetic Resonance Images

In functional magnetic resonance imaging, spatial activation patterns are commonly estimated using a non-parametric smoothing approach. Significant peaks or clusters in the smoothed image are subsequently identified by testing the null hypothesis of lack of activation in every volume element of the scans. A weakness of this approach is the lack of a model for the activation pattern; this makes it difficult to determine the variance of estimates, to test specific neuroscientific hypotheses or to incorporate prior information about the brain area under study in the analysis. These issues may be addressed by formulating explicit spatial models for the activation and using simulation methods for inference. We present one such approach, based on a marked point process prior. Informally, one may think of the points as centres of activation, and the marks as parameters describing the shape and area of the surrounding cluster. We present an MCMC algorithm for making inference in the model and compare the approach with a traditional non-parametric method, using both simulated and visual stimulation data. Finally we discuss extensions of the model and the inferential framework to account for non-stationary responses and spatio-temporal correlation.     

Nonparametric estimation of a log-variance function in scale-space

In a nonparametric regression setting, we consider the kernel estimation of the logarithm of the error variance function, which might be assumed to be homogeneous or heterogeneous. The objective of the present study is to discover important features in the variation of the data at multiple locations and scales based on a nonparametric kernel smoothing technique. Traditional kernel approaches estimate the function by selecting an optimal bandwidth, but it often turns out to be unsatisfying in practice. In this paper, we develop a SiZer (SIgnificant ZERo crossings of derivatives) tool based on a scale-space approach that provides a more flexible way of finding meaningful features in the variation. The proposed approach utilizes local polynomial estimators of a log-variance function using a wide range of bandwidths. We derive the theoretical quantile of confidence intervals in SiZer inference and also study the asymptotic properties of the proposed approach in scale-space. A numerical study via simulated and real examples demonstrates the usefulness of the proposed SiZer tool.     

Shape-constrained Gaussian process regression for surface reconstruction and multimodal,non-rigid image registration

We present a new statistical framework for landmark ?>curve-based image registration and surface reconstruction. The proposed method first elastically aligns geometric features (continuous, parameterized curves) to compute local deformations, and then uses a Gaussian random field model to estimate the full deformation vector field as a spatial stochastic process on the entire surface or image domain. The statistical estimation is performed using two different methods: maximum likelihood and Bayesian inference via Markov Chain Monte Carlo sampling. The resulting deformations accurately match corresponding curve regions while also being sufficiently smooth over the entire domain. We present several qualitative and quantitative evaluations of the proposed method on both synthetic and real data. We apply our approach to two different tasks on real data: (1) multimodal medical image registration, and (2) anatomical and pottery surface reconstruction.     

SiZer Map for inference with additive models

Sizer Map is proposed as a graphical tool for assistance in nonparametric additive regression testing problems. Four problems have been analyzed by using SiZer Map: testing for additivity, testing the components significance, testing parametric models for the components and testing for interactions. The simplicity and flexibility of SiZer Map for our purposes are highlighted from the performed empirical study with several real datasets. With these data, we compare the conclusions derived from SiZer analysis with the global results derived from standard tests, previously proposed in the literature.     

Generalized Ising models and their applications

The Ising model has become more prominent in spatial statistics since its applications in image analysis, as pioneered by Besag. This paper describes three multilevel generalizations of the Ising model, including the general spin Ising model. We compare and contrast these three generalizations. In all three cases, the normalizing constant is intractable but, using the developments made by physicists, we give adequate approximations for the general spin model, together with complete expressions for the binary Ising model. We show that these approximations allow inference for the general spin model. An application to texture analysis is also given.     

A Spatio-Temporal Model for Functional Magnetic Resonance Imaging Data – with a View to Resting State Networks

Abstract.  Functional magnetic resonance imaging (fMRI) is a technique for studying the active human brain. During the fMRI experiment, a sequence of MR images is obtained, where the brain is represented as a set of voxels. The data obtained are a realization of a complex spatio-temporal process with many sources of variation, both biological and technical. We present a spatio-temporal point process model approach for fMRI data where the temporal and spatial activation are modelled simultaneously. It is possible to analyse other characteristics of the data than just the locations of active brain regions, such as the interaction between the active regions. We discuss both classical statistical inference and Bayesian inference in the model. We analyse simulated data without repeated stimuli both for location of the activated regions and for interactions between the activated regions. An example of analysis of fMRI data, using this approach, is presented.     

Parallel inference for massive distributed spatial data using low-rank models

Due to rapid data growth, statistical analysis of massive datasets often has to be carried out in a distributed fashion, either because several datasets stored in separate physical locations are all relevant to a given problem, or simply to achieve faster (parallel) computation through a divide-and-conquer scheme. In both cases, the challenge is to obtain valid inference that does not require processing all data at a single central computing node. We show that for a very widely used class of spatial low-rank models, which can be written as a linear combination of spatial basis functions plus a fine-scale-variation component, parallel spatial inference and prediction for massive distributed data can be carried out exactly, meaning that the results are the same as for a traditional, non-distributed analysis. The communication cost of our distributed algorithms does not depend on the number of data points. After extending our results to the spatio-temporal case, we illustrate our methodology by carrying out distributed spatio-temporal particle filtering inference on total precipitable water measured by three different satellite sensor systems.     

A Discrete Time Parametric Model for the Analysis of Failure Time Data

This paper introduces a parametric discrete failure time model which allows a variety of smooth hazard function shapes, including shapes which are not readily available with continuous failure time models. The model is easy to fit, and statistical inference is simple. Further, it is readily extended to allow for differences between subjects while retaining the ease of fit and simplicity of statistical inference. The performance of the discrete time analysis is demonstrated by application to several data sets.     

A Monte Carlo approach to quantifying discrepancies between intractable posterior distributions

The computational demand required to perform inference using Markov chain Monte Carlo methods often obstructs a Bayesian analysis. This may be a result of large datasets, complex dependence structures, or expensive computer models. In these instances, the posterior distribution is replaced by a computationally tractable approximation, and inference is based on this working model. However, the error that is introduced by this practice is not well studied. In this paper, we propose a methodology that allows one to examine the impact on statistical inference by quantifying the discrepancy between the intractable and working posterior distributions. This work provides a structure to analyse model approximations with regard to the reliability of inference and computational efficiency. We illustrate our approach through a spatial analysis of yearly total precipitation anomalies where covariance tapering approximations are used to alleviate the computational demand associated with inverting a large, dense covariance matrix.     

Performance of information criteria for spatial models

Model choice is one of the most crucial aspect in any statistical data analysis. It is well known that most models are just an approximation to the true data-generating process but among such model approximations, it is our goal to select the ‘best’ one. Researchers typically consider a finite number of plausible models in statistical applications, and the related statistical inference depends on the chosen model. Hence, model comparison is required to identify the ‘best’ model among several such candidate models. This article considers the problem of model selection for spatial data. The issue of model selection for spatial models has been addressed in the literature by the use of traditional information criteria-based methods, even though such criteria have been developed based on the assumption of independent observations. We evaluate the performance of some of the popular model selection critera via Monte Carlo simulation experiments using small to moderate samples. In particular, we compare the performance of some of the most popular information criteria such as Akaike information criterion (AIC), Bayesian information criterion, and corrected AIC in selecting the true model. The ability of these criteria to select the correct model is evaluated under several scenarios. This comparison is made using various spatial covariance models ranging from stationary isotropic to nonstationary models.     

Inference in generalized additive mixed modelsby using smoothing splines

Generalized additive mixed models are proposed for overdispersed and correlated data, which arise frequently in studies involving clustered, hierarchical and spatial designs. This class of models allows flexible functional dependence of an outcome variable on covariates by using nonparametric regression, while accounting for correlation between observations by using random effects. We estimate nonparametric functions by using smoothing splines and jointly estimate smoothing parameters and variance components by using marginal quasi-likelihood. Because numerical integration is often required by maximizing the objective functions, double penalized quasi-likelihood is proposed to make approximate inference. Frequentist and Bayesian inferences are compared. A key feature of the method proposed is that it allows us to make systematic inference on all model components within a unified parametric mixed model framework and can be easily implemented by fitting a working generalized linear mixed model by using existing statistical software. A bias correction procedure is also proposed to improve the performance of double penalized quasi-likelihood for sparse data. We illustrate the method with an application to infectious disease data and we evaluate its performance through simulation.     

On the foundations: Statistical models and inference

This paper presents an overview of some recent results concerning statistical models and inference. specifically: grounds for statistical models. types of models that simplify by standard probability analysis, the use of categorical information in the reduction of the model with data, and the role of additives in the inference process. The relevant technical material has been developed elsewhere.     

Statistical Inference Enables Bad Science; Statistical Thinking Enables Good Science

ABSTRACT

Scientific research of all kinds should be guided by statistical thinking: in the design and conduct of the study, in the disciplined exploration and enlightened display of the data, and to avoid statistical pitfalls in the interpretation of the results. However, formal, probability-based statistical inference should play no role in most scientific research, which is inherently exploratory, requiring flexible methods of analysis that inherently risk overfitting. The nature of exploratory work is that data are used to help guide model choice, and under these circumstances, uncertainty cannot be precisely quantified, because of the inevitable model selection bias that results. To be valid, statistical inference should be restricted to situations where the study design and analysis plan are specified prior to data collection. Exploratory data analysis provides the flexibility needed for most other situations, including statistical methods that are regularized, robust, or nonparametric. Of course, no individual statistical analysis should be considered sufficient to establish scientific validity: research requires many sets of data along many lines of evidence, with a watchfulness for systematic error. Replicating and predicting findings in new data and new settings is a stronger way of validating claims than blessing results from an isolated study with statistical inferences.     

Local sensitivity approximations for selectivity bias

Observational data analysis is often based on tacit assumptions of ignorability or randomness. The paper develops a general approach to local sensitivity analysis for selectivity bias, which aims to study the sensitivity of inference to small departures from such assumptions. If M is a model assuming ignorability, we surround M by a small neighbourhood N defined in the sense of Kullback–Leibler divergence and then compare the inference for models in N with that for M . Interpretable bounds for such differences are developed. Applications to missing data and to observational comparisons are discussed. Local approximations to sensitivity analysis are model robust and can be applied to a wide range of statistical problems.     

Modeling and prediction for multivariate spatial factor analysis

Factor analysis of multivariate spatial data is considered. A systematic approach for modeling the underlying structure of potentially irregularly spaced, geo-referenced vector observations is proposed. Statistical inference procedures for selecting the number of factors and for model building are discussed. We derive a condition under which a simple and practical inference procedure is valid without specifying the form of distributions and factor covariance functions. The multivariate prediction problem is also discussed, and a procedure combining the latent variable modeling and a measurement-error-free kriging technique is introduced. Simulation results and an example using agricultural data are presented.     

Statistical analysis of an endemic disease from a capture–recapture experiment

There are a number of statistical techniques for analysing epidemic outbreaks. However, many diseases are endemic within populations and the analysis of such diseases is complicated by changing population demography. Motivated by the spread of cowpox amongst rodent populations, a combined mathematical model for population and disease dynamics is introduced. A Markov chain Monte Carlo algorithm is then constructed to make statistical inference for the model based on data being obtained from a capture–recapture experiment. The statistical analysis is used to identify the key elements in the spread of the cowpox virus.