Time series analysis of categorical data using auto-odds ratio function

In this paper, we consider the auto-odds ratio function (AORF) as a measure of serial association for a stationary time series process of categorical data at two different time points. Numerical measures such as the autocorrelation function (ACF) have no meaningful interpretation, unless the time series data are numerical. Instead, we use the AORF as a measure of association to study the serial dependency of the categorical time series for both ordinal and nominal categories. Biswas and Song [Discrete-valued ARMA processes. Stat Probab Lett. 2009;79(17):1884–1889] provided some results on this measure for Pegram's operator-based AR(1) process with binary responses. Here, we extend this measure to more general set-ups, i.e. for AR(p) and MA(q) processes and for a general number of categories. We discuss how this method can effectively be used in parameter estimation and model selection. Following Weiß [Empirical measures of signed serial dependence in categorical time series. J Stat Comput Simul. 2011;81(4):411–429], we derive the large sample distribution of the estimator of the AORF under independent and identically distributed (iid) set-up. Some simulation results and two categorical data examples (one is ordinal and other nominal) are presented to illustrate the proposed method.     

Testing spatial randomness based on empirical distribution function: A study on lattice data

In this article, we extended the empirical distribution function based test statistic _Ik$I_k$ of Skaug and Tjostheim [1993. Nonparametric test of serial independence based on the empirical distribution function. Biometrika 80, 591–602] in the time series setting to _Dn$D_n$ for spatial lattice data and derived the asymptotic distribution of the proposed test statistic _Dn$D_n$ under the null hypothesis of spatial independence. The size and power of the proposed test statistic under conditional autoregressive model (CAR) were simulated. We applied _Dn$D_n$, Moran's I and Geary's c   to the transformed and well-studied sudden infant death syndrome data from North Carolina and found that _Dn$D_n$ produced a much smaller p$p$-value in testing spatial independence.     

Equivalence theorem for Schur optimality of experimental designs

An experimental design is said to be Schur optimal, if it is optimal with respect to the class of all Schur isotonic criteria, which includes Kiefer's criteria of _Φp${\Phi }_p$-optimality, distance optimality criteria and many others. In the paper we formulate an easily verifiable necessary and sufficient condition for Schur optimality in the set of all approximate designs of a linear regression experiment with uncorrelated errors. We also show that several common models admit a Schur optimal design, for example the trigonometric model, the first-degree model on the Euclidean ball, and the Berman's model.     

Truncated linear estimation of a bounded multivariate normal mean

We consider the problem of estimating the mean θ$\theta$ of an _Np(θ,_Ip)${\mathrm{N}}_{\mathrm{p}}(\theta ,I_p)$ distribution with squared error loss ∥δ−θ∥²$\parallel \delta -\theta {\parallel }^2$ and under the constraint ∥θ∥≤m$\parallel \theta \parallel \le m$, for some constant m>0$m>0$. Using Stein's identity to obtain unbiased estimates of risk, Karlin's sign change arguments, and conditional risk analysis, we compare the risk performance of truncated linear estimators with that of the maximum likelihood estimator _δmle${\delta }_{\mathrm{mle}}$. We obtain for fixed (m,p)$(m,p)$ sufficient conditions for dominance. An asymptotic framework is developed, where we demonstrate that the truncated linear minimax estimator dominates _δmle${\delta }_{\mathrm{mle}}$, and where we obtain simple and accurate measures of relative improvement in risk. Numerical evaluations illustrate the effectiveness of the asymptotic framework for approximating the risks for moderate or large values of p.     

Classification rules for triply multivariate data with an AR(1) correlation structure on the repeated measures over time

In this article we study the problem of classification of three-level multivariate data, where multiple q$q$-variate observations are measured on u$u$-sites and over p$p$-time points, under the assumption of multivariate normality. The new classification rules with certain structured and unstructured mean vectors and covariance structures are very efficient in small sample scenario, when the number of observations is not adequate to estimate the unknown variance–covariance matrix. These classification rules successfully model the correlation structure on successive repeated measurements over time. Computation algorithms for maximum likelihood estimates of the unknown population parameters are presented. Simulation results show that the introduction of sites in the classification rules improves their performance over the existing classification rules without the sites.     

Detecting multiple confounders

This paper proposes an approach for detecting multiple confounders which combines the advantages of two causal models, the potential outcome model and the causal diagram. The approach need not use a complete causal diagram as long as it is known that a known covariate set Z$Z$ contains the parent set of the exposure E  . On the other hand, whether a covariate is or not a confounder may depend on its categorization. We introduce uniform non-confounding which implies non-confounding in any subpopulation defined by the interval of a covariate (or any pooled level for a discrete covariate). We show that the conditions in Miettinen and Cook's criteria for non-confounding also imply uniform non-confounding. Further we present an algorithm for deleting non-confounders from the potential confounder set Z$Z$, which extends Greenland et al.'s [1999a. Causal diagrams for epidemiologic research. Epidemiology 10, 37–48] approach by splitting Z$Z$ into a series of potential confounder subsets. We also discuss conditions for non-confounding bias in the subpopulations in which we are interested, where the subpopulations may be defined by non-confounders.     

On the stability of the risk hull method for projection estimators

We consider in this paper the regularization by projection of a linear inverse problem Y=Af+εξ$Y=\mathit{Af}+\epsilon \xi$ where ξ$\xi$ denotes a Gaussian white noise, A   a compact operator and ε>0$\epsilon >0$ a noise level. Compared to the standard unbiased risk estimation (URE) method, the risk hull minimization (RHM) procedure presents a very interesting numerical behavior. However, the regularization in the singular value decomposition setting requires the knowledge of the eigenvalues of A$A$. Here, we deal with noisy eigenvalues: only observations on this sequence are available. We study the efficiency of the RHM method in this situation. More generally, we shed light on some properties usually related to the regularization with a noisy operator.     

Robust modified profile estimating function with application to the generalized estimating equation

We consider methods for reducing the effect of fitting nuisance parameters on a general estimating function, when the estimating function depends on not only a vector of parameters of interest, θ$\theta$, but also on a vector of nuisance parameters, λ$\lambda$. We propose a class of modified profile estimating functions with plug-in bias reduced by two orders. A robust version of the adjustment term does not require any information about the probability mechanism beyond that required by the original estimating function. An important application of this method is bias correction for the generalized estimating equation in analyzing stratified longitudinal data, where the stratum-specific intercepts are considered as fixed nuisance parameters, the dependence of the expected outcome on the covariates is of interest, and the intracluster correlation structure is unknown. Furthermore, when the quasi-scores for θ$\theta$ and λ$\lambda$ are available, we propose an additional multiplicative adjustment term such that the modified profile estimating function is approximately information unbiased. This multiplicative adjustment term can serve as an optimal weight in the analysis of stratified studies. A brief simulation study shows that the proposed method considerably reduces the impact of the nuisance parameters.     

Asymptotic properties of the EPMC for modified linear discriminant analysis when sample size and dimension are both large

We deal with the problem of classifying a new observation vector into one of two known multivariate normal distributions when the dimension p and training sample size N   are both large with p<N$p<N$. Modified linear discriminant analysis (MLDA) was suggested by Xu et al. [10]. Error rate of MLDA is smaller than the one of LDA. However, if p and N   are moderately large, error rate of MLDA is close to the one of LDA. These results are conditional ones, so we should investigate whether they hold unconditionally. In this paper, we give two types of asymptotic approximations of expected probability of misclassification (EPMC) for MLDA as n→∞$n\to \infty$ with p=O(n^δ)$p=O(n^{\delta })$, 0<δ<1$0<\delta <1$. The one of two is the same as the asymptotic approximation of LDA, and the other is corrected version of the approximation. Simulation reveals that the modified version of approximation has good accuracy for the case in which p and N are moderately large.     

Confidence intervals in regression utilizing prior information

We consider a linear regression model with regression parameter β=(_β1,…,_βp)$\beta =({\beta }_1,\dots ,{\beta }_p)$ and independent and identically N(0,σ²)$N(0,{\sigma }^2)$ distributed errors. Suppose that the parameter of interest is θ=a^Tβ$\theta =a^T\beta$ where a$a$ is a specified vector. Define the parameter τ=c^Tβ-t$\tau =c^T\beta -t$ where the vector c$c$ and the number t$t$ are specified and a$a$ and c$c$ are linearly independent. Also suppose that we have uncertain prior information that τ=0$\tau =0$. We present a new frequentist 1-α$1-\alpha$ confidence interval for θ$\theta$ that utilizes this prior information. We require this confidence interval to (a) have endpoints that are continuous functions of the data and (b) coincide with the standard 1-α$1-\alpha$ confidence interval when the data strongly contradict this prior information. This interval is optimal in the sense that it has minimum weighted average expected length where the largest weight is given to this expected length when τ=0$\tau =0$. This minimization leads to an interval that has the following desirable properties. This interval has expected length that (a) is relatively small when the prior information about τ$\tau$ is correct and (b) has a maximum value that is not too large. The following problem will be used to illustrate the application of this new confidence interval. Consider a 2×2$2\times 2$ factorial experiment with 20 replicates. Suppose that the parameter of interest θ$\theta$ is a specified simple   effect and that we have uncertain prior information that the two-factor interaction is zero. Our aim is to find a frequentist 0.95 confidence interval for θ$\theta$ that utilizes this prior information.     

An identity for the Fisher information and Mahalanobis distance

Consider a mixture problem consisting of k classes. Suppose we observe an s-dimensional random vector X   whose distribution is specified by the relations P(X∈A|Y=i)=_Pi(A)$P(X\in A|Y=i)=P_i(A)$, where Y   is an unobserved class identifier defined on {1,…,k}$\{1,\dots ,k\}$, having distribution P(Y=i)=_pi$P(Y=i)=p_i$. Assuming the distributions _Pi$P_i$ having a common covariance matrix, elegant identities are presented that connect the matrix of Fisher information in Y   on the parameters _p1,…,_pk$p_1,\dots ,p_k$, the matrix of linear information in X, and the Mahalanobis distances between the pairs of P  's. Since the parameters are not free, the information matrices are singular and the technique of generalized inverses is used. A matrix extension of the Mahalanobis distance and its invariant forms are introduced that are of interest in their own right. In terms of parameter estimation, the results provide an independent of the parameter upper bound for the loss of accuracy by esimating _p1,…,_pk$p_1,\dots ,p_k$ from a sample of X^′$X^{\prime }$s, as compared with the ideal estimator based on a random sample of Y^′$Y^{\prime }$s.     

A unified framework for analysis and comparison of randomized response surveys of binary characteristics

The randomized response (RR) procedures for estimating the proportion (π)$(\pi )$ of a population belonging to a sensitive or stigmatized group ask each respondent to report a response by randomly transforming his/her true attribute into one of several response categories. In this paper, we present a common framework for discussing various RR surveys of dichotomous populations with polychotomous responses. The unified approach is focused on the substantive issues relating to respondents’ privacy and statistical efficiency and is helpful for fair comparison of various procedures. We describe a general technique for constructing unbiased estimators of π$\pi$ based on arbitrary RR procedures, from unbiased estimators based on an open survey with the same sampling design. The technique works well for any sampling design p(s)$p(s)$ and also for variance estimation. We develop an approach for comparing RR procedures, taking both respondents’ protection and statistical efficiency into account. For any given RR procedure with three or more response categories, we present a method for designing an RR procedure with a binary response variable which provides the same respondents’ protection and at least as much statistical information. This result suggests that RR surveys of dichotomous populations should use only binary response variables.     

Two sets of isotones for comparing tests of exponentiality

Isotones   are a deterministic graphical device introduced by Mudholkar et al. [1991. A graphical procedure for comparing goodness-of-fit tests. J. Roy. Statist. Soc. B 53, 221–232], in the context of comparing some tests of normality. An isotone of a test is a contour of p$p$ values of the test applied to “ideal samples”, called profiles, from a two-shape-parameter family representing the null and the alternative distributions of the parameter space. The isotone is an adaptation of Tukey's sensitivity curves, a generalization of Prescott's stylized sensitivity contours, and an alternative to the isodynes   of Stephens. The purpose of this paper is two fold. One is to show that the isotones can provide useful qualitative information regarding the behavior of the tests of distributional assumptions other than normality. The other is to show that the qualitative conclusions remain the same from one two-parameter family of alternatives to another. Towards this end we construct and interpret the isotones of some tests of the composite hypothesis of exponentiality, using the profiles of two Weibull extensions, the generalized Weibull and the exponentiated Weibull families, which allow IFR, DFR, as well as unimodal and bathtub failure rate alternatives. Thus, as a by-product of the study, it is seen that a test due to Csörg? et al. [1975. Application of characterizations in the area of goodness-of-fit. In: Patil, G.P., Kotz, S., Ord, J.K. (Eds.), Statistical Distributions in Scientific Work, vol. 2. Reidel, Boston, pp. 79–90], and Gnedenko's Q(r)$Q(r)$ test [1969. Mathematical Methods of Reliability Theory. Academic Press, New York], are appropriate for detecting monotone failure rate alternatives, whereas a bivariate F$F$ test due to Lin and Mudholkar [1980. A test of exponentiality based on the bivariate F$F$ distribution. Technometrics 22, 79–82] and their entropy test [1984. On two applications of characterization theorems to goodness-of-fit. Colloq. Math. Soc. Janos Bolyai 45, 395–414] can detect all alternatives, but are especially suitable for nonmonotone failure rate alternatives.     

On the detection of changes in autoregressive time series,II. Resampling procedures

We study an autoregressive time series model with a possible change in the regression parameters. Approximations to the critical values for change-point tests are obtained through various bootstrapping methods. Theoretical results show that the bootstrapping procedures have the same limiting behavior as their asymptotic counterparts discussed in Hušková et al. [2007. On the detection of changes in autoregressive time series, I. Asymptotics. J. Statist. Plann. Inference 137, 1243–1259]. In fact, a small simulation study illustrates that the bootstrap tests behave better than the original asymptotic tests if performance is measured by the α$\alpha$- and β$\beta$-errors, respectively.     

CARMA(p,q) generalized random processes

There is now a vast literature on the theory and applications of generalized random processes, pioneered by Itô (1953), Gel’fand (1955) and Yaglom (1957). In this note we make use of the theory of generalized random processes as defined in the book of Gel’fand and Vilenkin (1964) to extend the definition of continuous-time ARMA(p,q  ) processes to allow q≥p$q\ge p$, in which case the processes do not exist in the classical sense. The resulting CARMA generalized random processes provide a framework within which it is possible to study derivatives of CARMA processes of arbitrarily high order.     

Improving the estimators of the parameters of a probit regression model: A ridge regression approach

This paper considered the estimation of the regression parameters of a general probit regression model. Accordingly, we proposed five ridge regression (RR) estimators for the probit regression models for estimating the parameters (β)$(\beta )$ when the weighted design matrix is ill-conditioned and it is suspected that the parameter β$\beta$ may belong to a linear subspace defined by Hβ=h$H\beta =h$. Asymptotic properties of the estimators are studied with respect to quadratic biases, MSE matrices and quadratic risks. The regions of optimality of the proposed estimators are determined based on the quadratic risks. Some relative efficiency tables and risk graphs are provided to illustrate the numerical comparison of the estimators. We conclude that when q≥3$q\ge 3$, one would uses PRRRE; otherwise one uses PTRRE with some optimum size α$\alpha$. We also discuss the performance of the proposed estimators compare to the alternative ridge regression method due to Liu (1993).     

Regularization and variable selection for infinite variance autoregressive models

Autoregressive models with infinite variance are of great importance in modeling heavy-tailed time series and have been well studied. In this paper, we propose a penalized method to conduct model selection for autoregressive models with innovations having Pareto-like distributions with index α∈(0,2)$\alpha \in (\mathrm{0,2})$. By combining the least absolute deviation loss function and the adaptive lasso penalty, the proposed method is able to consistently identify the true model and at the same time produce efficient estimators with a convergence rate of n^−1/α$n^{-1/\alpha }$. In addition, our approach provides a unified way to conduct variable selection for autoregressive models with finite or infinite variance. A simulation study and a real data analysis are conducted to illustrate the effectiveness of our method.     

Regression with fractional polynomials when interactions are erroneously omitted

We propose a new summary tool, so-called average predictive comparison (APC), which summarizes the effect of a particular predictor in a context of regression. Different from the definition in our earlier work (Liu and Gustafson, 2008), the new definition allows a pointwise evaluation of a predictor's effect for any given value of this predictor. We employ this summary tool to examine the consequence of erroneously omitting interactions in regression models. To be able to involve curved relationships between a response variable and predictors, we consider fractional polynomial regression models (Royston and Altman, 1994). We derive the asymptotic properties of the APC estimates under a general setting with p(≥2)$p(\ge 2)$ predictors involved. In particular, when there are only two predictors of interest, we find out that the APC estimator is robust to the model misspecification under some certain conditions. We illustrate the application of the proposed summary tool via a real data example. We also conduct simulation experiments to further check the performance of the APC estimates.     

A note on goodness-of-fit test of continuation ratio logistic regression models under case–control data

We extend the discussion of Qin and Zhang's [1997. A goodness of fit test for logistic regression models base on case–control data. Biometrika 84, 609–618] goodness-of-fit test of logistic regression under case–control data to continuation ratio logistic regression (CRLR) models. We first showed that the retrospective CRLR model, which is valid for case–control data (the null hypothesis _H0)${\mathrm{H}}_0)$, is equivalent to an I  -sample semiparametric model. Then under _H0${\mathrm{H}}_0$, we find the semiparametric profile empirical likelihood estimators of distributions of the covariate conditioning on each response category and use them to define a Kolmogorov–Smirnov type test for assessing the global fit of CRLR models under case–control data. Unlike prospective CRLR models, retrospective CRLR models cannot be partitioned to a series of retrospective binary logistic regression models studied by Qin and Zhang [1997. A goodness of fit test for logistic regression models base on case–control data. Biometrika 84, 609–618].