Natalia Bochkina

Dr. Natalia Bochkina

orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2014 in The Annals of Statistics
Verified
Journal Article
Open access
PDF file
NBNatalia Bochkina
Natalia Bochkina
PGPeter J. Green
Peter J. Green
We study the asymptotic behaviour of the posterior distribution in a broad class of statistical models where the “true” solution occurs on the boundary of the parameter space. We show that in this case Bayesian inference is consistent, and that the posterior distribution has not only Gaussian components as in the case of regular models (the Bernstein–von Mises theorem) but also has Gamma distribution components whose form depends on the behaviour of the prior distribution near the boundary and have a faster rate of convergence. We also demonstrate a remarkable property of Bayesian inference, that for some models, there appears to be no bound on efficiency of estimating the unknown parameter if it is on the boundary of the parameter space. We illustrate the results on a problem from emission tomography.

15 August 2013 in Inverse Problems
Verified
Journal Article
Closed access
PDF file
NBNatalia Bochkina
Natalia Bochkina
For ill-posed inverse problems, a regularized solution can be interpreted as a mode of the posterior distribution in a Bayesian framework. This framework enriches the set of possible solutions, as other posterior estimates can be used as a solution to the inverse problem, such as the posterior mean which can be easier to compute in practice. In this paper we prove consistency of Bayesian solutions of an ill-posed linear inverse problem in the Ky Fan metric for a general class of likelihoods and prior distributions in a finite-dimensional setting. This result can be applied to study infinite dimensional problems by letting the dimension of the unknown parameter grow to infinity which can be viewed as discretization on a grid or spectral approximation of an infinite dimensional problem. The likelihood and the prior distribution are assumed to be in an exponential form that includes distributions from the exponential family, and to be differentiable. The prior distribution can be non-conjugate or improper. The observations can be dependent, and no assumption of finite moments of observations, such as expected value or the variance, is necessary thus allowing for possibly non-regular likelihoods. If the variance exists, it may be heteroscedastic, namely, it may depend on the unknown function. We observe quite a surprising phenomenon when applying our result to the spectral approximation framework where it is possible to achieve the parametric rate of convergence, i.e. the problem becomes self-regularized. We also consider a particular case of the unknown parameter being on the boundary of the parameter set, and show that the rate of convergence in this case is faster than for an interior point parameter.

12 November 2007 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
ETErnest Turro
Ernest Turro
NBNatalia Bochkina
Natalia Bochkina
AHAnne-Mette K Hein
Anne-Mette K Hein
SRSylvia Richardson
Sylvia Richardson
Affymetrix 3' GeneChip microarrays are widely used to profile the expression of thousands of genes simultaneously. They differ from many other microarray types in that GeneChips are hybridised using a single labelled extract and because they contain multiple 'match' and 'mismatch' sequences for each transcript. Most algorithms extract the signal from GeneChip experiments in a sequence of separate steps, including background correction and normalisation, which inhibits the simultaneous use of all available information. They principally provide a point estimate of gene expression and, in contrast to BGX, do not fully integrate the uncertainty arising from potentially heterogeneous responses of the probes.

11 October 2007 in Statistical Applications in Genetics and Molecular Biology
Verified
Journal Article
Closed access
ALAlex Lewin
Alex Lewin
NBNatalia Bochkina
Natalia Bochkina
SRSylvia Richardson
Sylvia Richardson
We present a Bayesian hierarchical model for detecting differentially expressed genes using a mixture prior on the parameters representing differential effects. We formulate an easily interpretable 3-component mixture to classify genes as over-expressed, under-expressed and non-differentially expressed, and model gene variances as exchangeable to allow for variability between genes. We show how the proportion of differentially expressed genes, and the mixture parameters, can be estimated in a fully Bayesian way, extending previous approaches where this proportion was fixed and empirically estimated. Good estimates of the false discovery rates are also obtained.Different parametric families for the mixture components can lead to quite different classifications of genes for a given data set. Using Affymetrix data from a knock out and wildtype mice experiment, we show how predictive model checks can be used to guide the choice between possible mixture priors. These checks show that extending the mixture model to allow extra variability around zero instead of the usual point mass null fits the data better.A software package for R is available.

3 April 2018 in Journal of Computational and Graphical Statistics
Verified
Journal Article
Closed access
AMAdria Caballe Mestres
Adria Caballe Mestres
NBNatalia Bochkina
Natalia Bochkina
CMClaus Mayer
Claus Mayer
Gaussian graphical models represent the underlying graph structure of conditional dependence between random variables, which can be determined using their partial correlation or precision matrix. In a high-dimensional setting, the precision matrix is estimated using penalized likelihood by adding a penalization term, which controls the amount of sparsity in the precision matrix and totally characterizes the complexity and structure of the graph. The most commonly used penalization term is the L1 norm of the precision matrix scaled by the regularization parameter, which determines the trade-off between sparsity of the graph and fit to the data. In this article, we propose several procedures to select the regularization parameter in the estimation of graphical models that focus on recovering reliably the appropriate network structure of the graph. We conduct an extensive simulation study to show that the proposed methods produce useful results for different network topologies. The approaches are also applied in a high-dimensional case study of gene expression data with the aim to discover the genes relevant to colon cancer. Using these data, we find graph structures, which are verified to display significant biological gene associations. Supplementary material is available online.

10 January 2006 in Biochimica et Biophysica Acta (BBA) - General Subjects
Verified
Journal Article
Closed access
SPSimon Parry
Simon Parry
DHDirk Hadaschik
Dirk Hadaschik
CBChristine Blancher
Christine Blancher
MKMande K. Kumaran
Mande K. Kumaran
NBNatalia Bochkina
Natalia Bochkina
ADAnne Dell
Anne Dell