arXiv subjects

Art B. Owen

Publications and source records attributed to Art B. Owen.

87 records · Page 5Linked to original sources

arXiv2014

Low discrepancy constructions in the triangle

Most quasi-Monte Carlo research focuses on sampling from the unit cube. Many problems, especially in computer graphics, are defined via quadrature over the unit triangle. Quasi-Monte Carlo methods for the triangle have been developed by Pillands and Cools (2005) and by Brandolini et al. (2013). This paper presents two QMC constructions in the triangle with a vanishing discrepancy. The first is a version of the van der Corput sequence customized to the unit triangle. It is an extensible digital construction that attains a discrepancy below 12/sqrt(N). The second construction rotates an integer lattice through an angle whose tangent is a quadratic irrational number. It attains a discrepancy of O(log(N)/N) which is the best possible rate. Previous work strongly indicated that such a discrepancy was possible, but no constructions were available. Scrambling the digits of the first construction improves its accuracy for integration of smooth functions. Both constructions also yield convergent estimates for integrands that are Riemann integrable on the triangle without requiring bounded variation.

math.NA↗

arXiv2014

The sign of the logistic regression coefficient

Let Y be a binary random variable and X a scalar. Let $\hatβ$ be the maximum likelihood estimate of the slope in a logistic regression of Y on X with intercept. Further let $\bar x_0$ and $\bar x_1$ be the average of sample x values for cases with y=0 and y=1, respectively. Then under a condition that rules out separable predictors, we show that sign($\hatβ$) = sign($\bar x_1-\bar x_0$). More generally, if $x_i$ are vector valued then we show that $\hatβ=0$ if and only if $\bar x_1=\bar x_0$. This holds for logistic regression and also for more general binary regressions with inverse link functions satisfying a log-concavity condition. Finally, when $\bar x_1\ne \bar x_0$ then the angle between $\hatβ$ and $\bar x_1-\bar x_0$ is less than ninety degrees in binary regressions satisfying the log-concavity condition and the separation condition, when the design matrix has full rank.

math.ST↗

arXiv2013

Multiple hypothesis testing adjusted for latent variables, with an application to the AGEMAP gene expression data

In high throughput settings we inspect a great many candidate variables (e.g., genes) searching for associations with a primary variable (e.g., a phenotype). High throughput hypothesis testing can be made difficult by the presence of systemic effects and other latent variables. It is well known that those variables alter the level of tests and induce correlations between tests. They also change the relative ordering of significance levels among hypotheses. Poor rankings lead to wasteful and ineffective follow-up studies. The problem becomes acute for latent variables that are correlated with the primary variable. We propose a two-stage analysis to counter the effects of latent variables on the ranking of hypotheses. Our method, called LEAPP, statistically isolates the latent variables from the primary one. In simulations, it gives better ordering of hypotheses than competing methods such as SVA and EIGENSTRAT. For an illustration, we turn to data from the AGEMAP study relating gene expression to age for 16 tissues in the mouse. LEAPP generates rankings with greater consistency across tissues than the rankings attained by the other methods.

stat.AP↗

arXiv2012

Bootstrapping data arrays of arbitrary order

In this paper we study a bootstrap strategy for estimating the variance of a mean taken over large multifactor crossed random effects data sets. We apply bootstrap reweighting independently to the levels of each factor, giving each observation the product of independently sampled factor weights. No exact bootstrap exists for this problem [McCullagh (2000) Bernoulli 6 285-301]. We show that the proposed bootstrap is mildly conservative, meaning biased toward overestimating the variance, under sufficient conditions that allow very unbalanced and heteroscedastic inputs. Earlier results for a resampling bootstrap only apply to two factors and use multinomial weights that are poorly suited to online computation. The proposed reweighting approach can be implemented in parallel and online settings. The results for this method apply to any number of factors. The method is illustrated using a 3 factor data set of comment lengths from Facebook.

stat.ME↗

arXiv2012

Variance components and generalized Sobol' indices

This paper introduces generalized Sobol' indices, compares strategies for their estimation, and makes a systematic search for efficient estimators. Of particular interest are contrasts, sums of squares and indices of bilinear form which allow a reduced number of function evaluations compared to alternatives. The bilinear framework includes some efficient estimators from Saltelli (2002) and Mauntz (2002) as well as some new estimators for specific variance components and mean dimensions. This paper also provides a bias corrected version of the estimator of Janon et al.\,(2012) and extends the bias correction to generalized Sobol' indices. Some numerical comparisons are given.

math.NA↗

arXiv2012

Better estimation of small Sobol' sensitivity indices

A new method for estimating Sobol' indices is proposed. The new method makes use of 3 independent input vectors rather than the usual 2. It attains much greater accuracy on problems where the target Sobol' index is small, even outperforming some oracles which adjust using the true but unknown mean of the function. When the target Sobol' index is quite large, the oracles do better than the new method.

stat.ME↗

arXiv2011

Outlier Detection Using Nonconvex Penalized Regression

This paper studies the outlier detection problem from the point of view of penalized regressions. Our regression model adds one mean shift parameter for each of the $n$ data points. We then apply a regularization favoring a sparse vector of mean shift parameters. The usual $L_1$ penalty yields a convex criterion, but we find that it fails to deliver a robust estimator. The $L_1$ penalty corresponds to soft thresholding. We introduce a thresholding (denoted by $Θ$) based iterative procedure for outlier detection ($Θ$-IPOD). A version based on hard thresholding correctly identifies outliers on some hard test problems. We find that $Θ$-IPOD is much faster than iteratively reweighted least squares for large data because each iteration costs at most $O(np)$ (and sometimes much less) avoiding an $O(np^2)$ least squares estimate. We describe the connection between $Θ$-IPOD and $M$-estimators. Our proposed method has one tuning parameter with which to both identify outliers and estimate regression coefficients. A data-dependent choice can be made based on BIC. The tuned $Θ$-IPOD shows outstanding performance in identifying outliers in various situations in comparison to other existing approaches. This methodology extends to high-dimensional modeling with $p\gg n$, if both the coefficient vector and the outlier pattern are sparse.

stat.ME↗

arXiv2011

Moment based estimation of stochastic Kronecker graph parameters

Stochastic Kronecker graphs supply a parsimonious model for large sparse real world graphs. They can specify the distribution of a large random graph using only three or four parameters. Those parameters have however proved difficult to choose in specific applications. This article looks at method of moments estimators that are computationally much simpler than maximum likelihood. The estimators are fast and in our examples, they typically yield Kronecker parameters with expected feature counts closer to a given graph than we get from KronFit. The improvement was especially prominent for the number of triangles in the graph.

stat.ML↗

arXiv2011

Correct ordering in the Zipf-Poisson ensemble

We consider a Zipf--Poisson ensemble in which $X_i\sim\poi(Ni^{-α})$ for $α>1$ and $N>0$ and integers $i\ge 1$. As $N\to\infty$ the first $n'(N)$ random variables have their proper order $X_1>X_2>...>X_{n'}$ relative to each other, with probability tending to 1 for $n'$ up to $(AN/\log(N))^{1/(α+2)}$ for an explicit constant $A(α)\ge 3/4$. The rate $N^{1/(α+2)}$ cannot be achieved. The ordering of the first $n'(N)$ entities does not preclude $X_m>X_{n'}$ for some interloping $m>n'$. The first $n"$ random variables are correctly ordered exclusive of any interlopers, with probability tending to 1 if $n"\le (BN/\log(N))^{1/(α+2)}$ for $B<A$. For a Zipf--Poisson model of the British National Corpus, which has a total word count of $100{,}000{,}000$, our result estimates that the 72 words with the highest counts are properly ordered.

stat.ME↗

arXiv2010

Empirical stationary correlations for semi-supervised learning on graphs

In semi-supervised learning on graphs, response variables observed at one node are used to estimate missing values at other nodes. The methods exploit correlations between nearby nodes in the graph. In this paper we prove that many such proposals are equivalent to kriging predictors based on a fixed covariance matrix driven by the link structure of the graph. We then propose a data-driven estimator of the correlation structure that exploits patterns among the observed response values. By incorporating even a small fraction of observed covariation into the predictions, we are able to obtain much improved prediction on two graph data sets.

stat.AP↗

arXiv2009

Karl Pearson's meta-analysis revisited

This paper revisits a meta-analysis method proposed by Pearson [Biometrika 26 (1934) 425--442] and first used by David [Biometrika 26 (1934) 1--11]. It was thought to be inadmissible for over fifty years, dating back to a paper of Birnbaum [J. Amer. Statist. Assoc. 49 (1954) 559--574]. It turns out that the method Birnbaum analyzed is not the one that Pearson proposed. We show that Pearson's proposal is admissible. Because it is admissible, it has better power than the standard test of Fisher [Statistical Methods for Research Workers (1932) Oliver and Boyd] at some alternatives, and worse power at others. Pearson's method has the advantage when all or most of the nonzero parameters share the same sign. Pearson's test has proved useful in a genomic setting, screening for age-related genes. This paper also presents an FFT-based method for getting hard upper and lower bounds on the CDF of a sum of nonnegative random variables.

math.ST↗

arXiv2009

Bi-cross-validation of the SVD and the nonnegative matrix factorization

This article presents a form of bi-cross-validation (BCV) for choosing the rank in outer product models, especially the singular value decomposition (SVD) and the nonnegative matrix factorization (NMF). Instead of leaving out a set of rows of the data matrix, we leave out a set of rows and a set of columns, and then predict the left out entries by low rank operations on the retained data. We prove a self-consistency result expressing the prediction error as a residual from a low rank approximation. Random matrix theory and some empirical results suggest that smaller hold-out sets lead to more over-fitting, while larger ones are more prone to under-fitting. In simulated examples we find that a method leaving out half the rows and half the columns performs well.

stat.AP↗

arXiv2008

Local antithetic sampling with scrambled nets

We consider the problem of computing an approximation to the integral $I=\int_{[0,1]^d}f(x) dx$. Monte Carlo (MC) sampling typically attains a root mean squared error (RMSE) of $O(n^{-1/2})$ from $n$ independent random function evaluations. By contrast, quasi-Monte Carlo (QMC) sampling using carefully equispaced evaluation points can attain the rate $O(n^{-1+\varepsilon})$ for any $\varepsilon>0$ and randomized QMC (RQMC) can attain the RMSE $O(n^{-3/2+\varepsilon})$, both under mild conditions on $f$. Classical variance reduction methods for MC can be adapted to QMC. Published results combining QMC with importance sampling and with control variates have found worthwhile improvements, but no change in the error rate. This paper extends the classical variance reduction method of antithetic sampling and combines it with RQMC. One such method is shown to bring a modest improvement in the RMSE rate, attaining $O(n^{-3/2-1/d+\varepsilon})$ for any $\varepsilon>0$, for smooth enough $f$.

stat.CO↗

arXiv2008

Construction of weakly CUD sequences for MCMC sampling

In Markov chain Monte Carlo (MCMC) sampling considerable thought goes into constructing random transitions. But those transitions are almost always driven by a simulated IID sequence. Recently it has been shown that replacing an IID sequence by a weakly completely uniformly distributed (WCUD) sequence leads to consistent estimation in finite state spaces. Unfortunately, few WCUD sequences are known. This paper gives general methods for proving that a sequence is WCUD, shows that some specific sequences are WCUD, and shows that certain operations on WCUD sequences yield new WCUD sequences. A numerical example on a 42 dimensional continuous Gibbs sampler found that some WCUD inputs sequences produced variance reductions ranging from tens to hundreds for posterior means of the parameters, compared to IID inputs.

stat.CO↗

arXiv2007

The pigeonhole bootstrap

Recently there has been much interest in data that, in statistical language, may be described as having a large crossed and severely unbalanced random effects structure. Such data sets arise for recommender engines and information retrieval problems. Many large bipartite weighted graphs have this structure too. We would like to assess the stability of algorithms fit to such data. Even for linear statistics, a naive form of bootstrap sampling can be seriously misleading and McCullagh [Bernoulli 6 (2000) 285--301] has shown that no bootstrap method is exact. We show that an alternative bootstrap separately resampling rows and columns of the data matrix satisfies a mean consistency property even in heteroscedastic crossed unbalanced random effects models. This alternative does not require the user to fit a crossed random effects model to the data.

stat.AP↗