arXiv subjects

Moulinath Banerjee

Publications and source records attributed to Moulinath Banerjee.

At least 55 records · Page 3Linked to original sources

arXiv2017

Common change point estimation in panel data from the least squares and maximum likelihood viewpoints

We establish the convergence rates and asymptotic distributions of the common break change-point estimators, obtained by least squares and maximum likelihood in panel data models and compare their asymptotic variances. Our model assumptions accommodate a variety of commonly encountered probability distributions and, in particular, models of particular interest in econometrics beyond the commonly analyzed Gaussian model, including the zero-inflated Poisson model for count data, and the probit and tobit models. We also provide novel results for time dependent data in the signal-plus-noise model, with emphasis on a wide array of noise processes, including Gaussian process, MA$(\infty)$ and $m$-dependent processes. The obtained results show that maximum likelihood estimation requires a stronger signal-to-noise model identifiability condition compared to its least squares counterpart. Finally, since there are three different asymptotic regimes that depend on the behavior of the norm difference of the model parameters before and after the change point, which cannot be realistically assumed to be known, we develop a novel data driven adaptive procedure that provides valid confidence intervals for the common break, without requiring a priori knowledge of the asymptotic regime the problem falls in.

math.ST↗

arXiv2016

Divide and Conquer in Non-standard Problems and the Super-efficiency Phenomenon

We study how the divide and conquer principle --- partition the available data into subsamples, compute an estimate from each subsample and combine these appropriately to form the final estimator --- works in non-standard problems where rates of convergence are typically slower than $\sqrt{n}$ and limit distributions are non-Gaussian, with a special emphasis on the least squares estimator (and its inverse) of a monotone regression function. We find that the pooled estimator, obtained by averaging non-standard estimates across the mutually exclusive subsamples, outperforms the non-standard estimator based on the entire sample in the sense of pointwise inference. We also show that, under appropriate conditions, if the number of subsamples is allowed to increase at appropriate rates, the pooled estimator is asymptotically normally distributed with a variance that is empirically estimable from the subsample-level estimates. Further, in the context of monotone function estimation we show that this gain in pointwise efficiency comes at a price --- the pooled estimator's performance, in a uniform sense (maximal risk) over a class of models worsens as the number of subsamples increases, leading to a version of the super-efficiency phenomenon. In the process, we develop analytical results for the order of the bias in isotonic regression, which are of independent interest.

math.ST↗

arXiv2016

Inference for Monotone Trends Under Dependence

We focus on the problem estimating a monotone trend function under additive and dependent noise. New point-wise confidence interval estimators under both short- and long-range dependent errors are introduced and studied. These intervals are obtained via the method of inversion of certain discrepancy statistics arising in hypothesis testing problems. The advantage of this approach is that it avoids the estimation of nuisance parameters such as the derivative of the unknown function, which existing methods are forced to deal with. While the methodology is motivated by earlier work in the independent context, the dependence of the errors, especially longrange dependence leads to new challenges, such as the study of convex minorants of drifted fractional Brownian motion that may be of independent interest. We also unravel a new family of universal limit distributions (and tabulate selected quantiles) that can henceforth be used for inference in monotone function problems involving dependence.

math.ST↗

arXiv2016

Penalized Maximum Likelihood Estimation of Multi-layered Gaussian Graphical Models

Analyzing multi-layered graphical models provides insight into understanding the conditional relationships among nodes within layers after adjusting for and quantifying the effects of nodes from other layers. We obtain the penalized maximum likelihood estimator for Gaussian multi-layered graphical models, based on a computational approach involving screening of variables, iterative estimation of the directed edges between layers and undirected edges within layers and a final refitting and stability selection step that provides improved performance in finite sample settings. We establish the consistency of the estimator in a high-dimensional setting. To obtain this result, we develop a strategy that leverages the biconvexity of the likelihood function to ensure convergence of the developed iterative algorithm to a stationary point, as well as careful uniform error control of the estimates over iterations. The performance of the maximum likelihood estimator is illustrated on synthetic data.

stat.ME↗

arXiv2015

Asymptotics for change-point models under varying degrees of mis-specification

Change-point models are widely used by statisticians to model drastic changes in the pattern of observed data. Least squares/maximum likelihood based estimation of change-points leads to curious asymptotic phenomena. When the change-point model is correctly specified, such estimates generally converge at a fast rate ($n$) and are asymptotically described by minimizers of jump process. Under complete mis-specification by a smooth curve, i.e. when a change-point model is fitted to data described by a smooth curve, the rate of convergence slows down to $n^{1/3}$ and the limit distribution changes to that of the minimizer of a continuous Gaussian process. In this paper we provide a bridge between these two extreme scenarios by studying the limit behavior of change-point estimates under varying degrees of model mis-specification by smooth curves, which can be viewed as local alternatives. We find that the limiting regime depends on how quickly the alternatives approach a change-point model. We unravel a family of `intermediate' limits that can transition, at least qualitatively, to the limits in the two extreme scenarios.

math.ST↗

arXiv2014

M-estimation in multistage sampling procedures

Multi-stage (designed) procedures, obtained by splitting the sampling budget suitably across stages, and designing the sampling at a particular stage based on information about the parameter obtained from previous stages, are often advantageous from the perspective of precise inference. We develop a generic framework for M-estimation in a multistage setting and apply empirical process techniques to develop limit theorems that describe the large sample behavior of the resulting M-estimates. Applications to change-point estimation, inverse isotonic regression, classification and mode estimation are provided: it is typically seen that the multistage procedure accentuates the efficiency of the M-estimates by accelerating the rate of convergence, relative to one-stage procedures. The step-by-step process induces dependence across stages and complicates the analysis in such problems, which we address through careful conditioning arguments.

stat.ME↗

arXiv2013

Baseline zone estimation in two dimensions

We consider the problem of estimating the region on which a non-parametric regression function is at its baseline level in two dimensions. The baseline level typically corresponds to the minimum/maximum of the function and estimating such regions or their complements is pertinent to several problems arising in edge estimation, environmental statistics, fMRI and related fields. We assume the baseline region to be convex and estimate it via fitting a `stump' function to approximate $p$-values obtained from tests for deviation of the regression function from its baseline level. The estimates, obtained using an algorithm originally developed for constructing convex contours of a density, are studied in two different sampling settings, one where several responses can be obtained at a number of different covariate-levels (dose-response) and the other involving limited number of response values per covariate (standard regression). The shape of the baseline region and the smoothness of the regression function at its boundary play a critical role in determining the rate of convergence of our estimate: for a regression function which is `p-regular' at the boundary of the convex baseline region, our estimate converges at a rate $N^{2/(4p+3)}$ in the dose-response setting, $N$ being the total budget, and its analogue in the standard regression setting converges at a rate of $N^{1/(2p+2)}$. Extensions to non-convex baseline regions are explored as well.

stat.ME↗

arXiv2013

Two-Stage Plans for Estimating a Threshold Value of a Regression Function

This study investigates two-stage plans based on nonparametric procedures for estimating an inverse regression function at a given point. Specifically, isotonic regression is used at stage one to obtain an initial estimate followed by another round of isotonic regression in the vicinity of this estimate at stage two. It is shown that such two stage plans accelerate the convergence rate of one-stage procedures and are superior to existing two-stage procedures that use local parametric approximations at stage two when the available budget is moderate and/or the regression function is 'ill-behaved'. Both Wald and Likelihood Ratio type confidence intervals for the threshold value of interest are investigated and the latter are recommended in applications due to their simplicity and robustness. The developed plans are illustrated through a comprehensive simulation study and an application to car fuel efficiency data.

stat.ME↗

arXiv2012

Likelihood based inference for current status data on a grid: A boundary phenomenon and an adaptive inference procedure

In this paper, we study the nonparametric maximum likelihood estimator for an event time distribution function at a point in the current status model with observation times supported on a grid of potentially unknown sparsity and with multiple subjects sharing the same observation time. This is of interest since observation time ties occur frequently with current status data. The grid resolution is specified as $cn^{-γ}$ with $c>0$ being a scaling constant and $γ>0$ regulating the sparsity of the grid relative to $n$, the number of subjects. The asymptotic behavior falls into three cases depending on $γ$: regular Gaussian-type asymptotics obtain for $γ<1/3$, nonstandard cube-root asymptotics prevail when $γ>1/3$ and $γ=1/3$ serves as a boundary at which the transition happens. The limit distribution at the boundary is different from either of the previous cases and converges weakly to those obtained with $γ\in(0,1/3)$ and $γ\in(1/3,\infty)$ as $c$ goes to $\infty$ and 0, respectively. This weak convergence allows us to develop an adaptive procedure to construct confidence intervals for the value of the event time distribution at a point of interest without needing to know or estimate $γ$, which is of enormous advantage from the perspective of inference. A simulation study of the adaptive procedure is presented.

math.ST↗

arXiv2011

Uncloaking globular clusters in the inner Galaxy

Extensive photometric studies of the globular clusters located towards the center of the Milky Way have been historically neglected. The presence of patchy differential reddening in front of these clusters has proven to be a significant obstacle to their detailed study. We present here a well-defined and reasonably homogeneous photometric database for 25 of the brightest Galactic globular clusters located in the direction of the inner Galaxy. These data were obtained in the B, V, and I bands using the Magellan 6.5m telescope and the Hubble Space Telescope. A new technique is extensively used in this paper to map the differential reddening in the individual cluster fields, and to produce cleaner, dereddened color-magnitude diagrams for all the clusters in the database. Subsequent papers will detail the astrophysical analysis of the cluster populations, and the properties of the obscuring material along the clusters' lines of sight.

astro-ph.GA↗

arXiv2011

Threshold estimation based on a p-value framework in dose-response and regression settings

We use p-values to identify the threshold level at which a regression function takes off from its baseline value, a problem motivated by applications in toxicological and pharmacological dose-response studies and environmental statistics. We study the problem in two sampling settings: one where multiple responses can be obtained at a number of different covariate-levels and the other the standard regression setting involving limited number of response values at each covariate. Our procedure involves testing the hypothesis that the regression function is at its baseline at each covariate value and then computing the potentially approximate p-value of the test. An estimate of the threshold is obtained by fitting a piecewise constant function with a single jump discontinuity, otherwise known as a stump, to these observed p-values, as they behave in markedly different ways on the two sides of the threshold. The estimate is shown to be consistent and its finite sample properties are studied through simulations. Our approach is computationally simple and extends to the estimation of the baseline value of the regression function, heteroscedastic errors and to time-series. It is illustrated on some real data applications.

stat.ME↗

arXiv2011

A two-stage hybrid procedure for estimating an inverse regression function

We consider a two-stage procedure (TSP) for estimating an inverse regression function at a given point, where isotonic regression is used at stage one to obtain an initial estimate and a local linear approximation in the vicinity of this estimate is used at stage two. We establish that the convergence rate of the second-stage estimate can attain the parametric $n^{1/2}$ rate. Furthermore, a bootstrapped variant of TSP (BTSP) is introduced and its consistency properties studied. This variant manages to overcome the slow speed of the convergence in distribution and the estimation of the derivative of the regression function at the unknown target quantity. Finally, the finite sample performance of BTSP is studied through simulations and the method is illustrated on a data set.

math.ST↗

arXiv2011

Mapping differential reddening in the inner Galactic globular cluster system

A serious limitation in the study of many globular clusters -- especially those located near the Galactic Center -- has been the existence of large and differential extinction by foreground dust. In a series of papers we intend to map the differential extinction and remove its effects, using a new dereddening technique, in a sample of clusters in the direction of the inner Galaxy, observed using the Magellan 6.5m telescope and the Hubble Space Telescope. These observations and their analysis will let us produce high quality color-magnitude diagrams of these poorly studied clusters that will allow us to determine these clusters' relative ages, distances and chemistry and to address important questions about the formation and the evolution of the inner Galaxy. We also intend to use the maps of the differential extinction to sample and characterize the interstellar medium along the numerous low latitude lines of sight where the clusters in our sample lie. In this first paper we describe in detail our dereddening method along with the powerful statistics tools that allow us to apply it, and we show the kind of results that we can expect, applying the method to M62, one of the clusters in our sample. The width of the main sequence and lower red giant branch narrows by a factor of 2 after applying our dereddening technique, which will significantly help to constrain the age, distance, and metallicity of the cluster.

astro-ph.GA↗

arXiv2010

Inconsistency of bootstrap: The Grenander estimator

In this paper, we investigate the (in)-consistency of different bootstrap methods for constructing confidence intervals in the class of estimators that converge at rate $n^{1/3}$. The Grenander estimator, the nonparametric maximum likelihood estimator of an unknown nonincreasing density function $f$ on $[0,\infty)$, is a prototypical example. We focus on this example and explore different approaches to constructing bootstrap confidence intervals for $f(t_0)$, where $t_0\in(0,\infty)$ is an interior point. We find that the bootstrap estimate, when generating bootstrap samples from the empirical distribution function $\mathbb{F}_n$ or its least concave majorant $\tilde{F}_n$, does not have any weak limit in probability. We provide a set of sufficient conditions for the consistency of any bootstrap method in this example and show that bootstrapping from a smoothed version of $\tilde{F}_n$ leads to strongly consistent estimators. The $m$ out of $n$ bootstrap method is also shown to be consistent while generating samples from $\mathbb{F}_n$ and $\tilde{F}_n$.

math.ST↗

arXiv2010

Threshold estimation based on a P-value framework

We use p-values as a discrepancy criterion for identifying the threshold value at which a regression function takes off from its baseline value -- a problem that is motivated by applications in omics experiments, systems engineering, pharmacological dose-response studies and astronomy. In this paper, we study the problem in a controlled sampling setting, where multiple responses, discrete or continuous, can be obtained at a number of different covariate-levels. Our procedure involves testing the hypothesis that the regression function is at its baseline at each covariate value using the sampled responses at that value and then computing the p-value of the test. An estimate of the threshold is provided by fitting a stump, i.e., a piecewise constant function with a single jump discontinuity, to the observed p-values, since the corresponding p-values behave in markedly different ways on different sides of the threshold. The estimate is shown to be consistent, as both the number of covariate values and the number of responses sampled at each value become large, and its finite sample properties are studied through an extensive simulation study. Our approach is computationally simple and can also be used to estimate the baseline value of the regression function. The procedure is illustrated on two motivating real data applications. Extensions to multiple thresholds are also briefly investigated.

stat.ME↗

arXiv2009

Change-point estimation under adaptive sampling

We consider the problem of locating a jump discontinuity (change-point) in a smooth parametric regression model with a bounded covariate. It is assumed that one can sample the covariate at different values and measure the corresponding responses. Budget constraints dictate that a total of $n$ such measurements can be obtained. A multistage adaptive procedure is proposed, where at each stage an estimate of the change point is obtained and new points are sampled from its appropriately chosen neighborhood. It is shown that such procedures accelerate the rate of convergence of the least squares estimate of the change-point. Further, the asymptotic distribution of the estimate is derived using empirical processes techniques. The latter result provides guidelines on how to choose the tuning parameters of the multistage procedure in practice. The improved efficiency of the procedure is demonstrated using real and synthetic data. This problem is primarily motivated by applications in engineering systems.

math.ST↗

arXiv2009

Streaming motion in Leo I

Whether a dwarf spheroidal galaxy is in equilibrium or being tidally disrupted by the Milky Way is an important question for the study of its dark matter content and distribution. This question is investigated using 328 recent observations from the dwarf spheroidal Leo I. For Leo I, tidal disruption is detected, at least for stars sufficiently far from the center, but the effect appears to be quite modest. Statistical tools include isotonic and split point estimators, asymptotic theory, and resampling methods.

stat.AP↗

arXiv2007

Likelihood based inference for monotone response models

The behavior of maximum likelihood estimates (MLEs) and the likelihood ratio statistic in a family of problems involving pointwise nonparametric estimation of a monotone function is studied. This class of problems differs radically from the usual parametric or semiparametric situations in that the MLE of the monotone function at a point converges to the truth at rate $n^{1/3}$ (slower than the usual $\sqrt{n}$ rate) with a non-Gaussian limit distribution. A framework for likelihood based estimation of monotone functions is developed and limit theorems describing the behavior of the MLEs and the likelihood ratio statistic are established. In particular, the likelihood ratio statistic is found to be asymptotically pivotal with a limit distribution that is no longer $χ^2$ but can be explicitly characterized in terms of a functional of Brownian motion. Applications of the main results are presented and potential extensions discussed.

math.ST↗