Searcharxiv⌕ Search

arXiv subjects

Robert A. Stine

Publications and source records attributed to Robert A. Stine.

8 recordsLinked to original sources
arXiv2022

Impartial Predictive Modeling and the Use of Proxy Variables

Fairness aware data mining (FADM) aims to prevent algorithms from discriminating against protected groups. The literature has come to an impasse as to what constitutes explainable variability as opposed to discrimination. This distinction hinges on a rigorous understanding of the role of proxy variables; i.e., those variables which are associated both the protected feature and the outcome of interest. We demonstrate that fairness is achieved by ensuring impartiality with respect to sensitive characteristics and provide a framework for impartiality by accounting for different perspectives on the data generating process. In particular, fairness can only be precisely defined in a full-data scenario in which all covariates are observed. We then analyze how these models may be conservatively estimated via regression in partial-data settings. Decomposing the regression estimates provides insights into previously unexplored distinctions between explainable variability and discrimination that illuminate the use of proxy variables in fairness aware data mining.

stat.ME↗
arXiv2021

Threshold Martingales and the Evolution of Forecasts

This paper introduces a martingale that characterizes two properties of evolving forecast distributions. Ideal forecasts of a future event behave as martingales, sequen- tially updating the forecast to leverage the available information as the future event approaches. The threshold martingale introduced here measures the proportion of the forecast distribution lying below a threshold. In addition to being calibrated, a threshold martingale has quadratic variation that accumulates to a total determined by a quantile of the initial forecast distribution. Deviations from calibration or to- tal volatility signal problems in the underlying model. Calibration adjustments are well-known, and we augment these by introducing a martingale filter that improves volatility while guaranteeing smaller mean squared error. Thus, post-processing can rectify problems with calibration and volatility without revisiting the original forecast- ing model. We apply threshold martingales first to forecasts from simulated models and then to models that predict the winner in professional basketball games.

cs.LG↗
arXiv2020

Fitting High-Dimensional Interaction Models with Error Control

There is a renewed interest in polynomial regression in the form of identifying influential interactions between features. In many settings, this takes place in a high-dimensional model, making the number of interactions unwieldy or computationally infeasible. Furthermore, it is difficult to analyze such spaces directly as they are often highly correlated. Standard feature selection issues remain such as how to determine a final model which generalizes well. This paper solves these problems with a sequential algorithm called Revisiting Alpha-Investing (RAI). RAI is motivated by the principle of marginality and searches the feature-space of higher-order interactions by greedily building upon lower-order terms. RAI controls a notion of false rejections and comes with a performance guarantee relative to the best-subset model. This ensures that signal is identified while providing a valid stopping criterion to prevent over-selection. We apply RAI in a novel setting over a family of regressions in order to select gene-specific interaction models for differential expression profiling.

stat.ME↗
arXiv2016

Submodularity in Statistics: Comparing the Success of Model Selection Methods

We demonstrate the usefulness of submodularity in statistics as a characterization of the difficulty of the \emph{search} problem of feature selection. The search problem is the ability of a procedure to identify an informative set of features as opposed to the performance of the optimal set of features. Submodularity arises naturally in this setting due to its connection to combinatorial optimization. In statistics, submodularity isolates cases in which collinearity makes the choice of model features difficult from those in which this task is routine. Researchers often report the signal-to-noise ratio to measure the difficulty of simulated data examples. A measure of submodularity should also be provided as it characterizes an independent component difficulty. Furthermore, it is closely related to other statistical assumptions used in the development of the Lasso, Dantzig selector, and sure information screening.

math.ST↗
arXiv2015

A Risk Ratio Comparison of $l_0$ and $l_1$ Penalized Regression

There has been an explosion of interest in using $l_1$-regularization in place of $l_0$-regularization for feature selection. We present theoretical results showing that while $l_1$-penalized linear regression never outperforms $l_0$-regularization by more than a constant factor, in some cases using an $l_1$ penalty is infinitely worse than using an $l_0$ penalty. We also show that the "optimal" $l_1$ solutions are often inferior to $l_0$ solutions found using stepwise regression. We also compare algorithms for solving these two problems and show that although solutions can be found efficiently for the $l_1$ problem, the "optimal" $l_1$ solutions are often inferior to $l_0$ solutions found using greedy classic stepwise regression. Furthermore, we show that solutions obtained by solving the convex $l_1$ problem can be improved by selecting the best of the $l_1$ models (for different regularization penalties) by using an $l_0$ criterion. In other words, an approximate solution to the right problem can be better than the exact solution to the wrong problem.

math.ST↗
arXiv2013

Spatio-Temporal Low Count Processes with Application to Violent Crime Events

There is significant interest in being able to predict where crimes will happen, for example to aid in the efficient tasking of police and other protective measures. We aim to model both the temporal and spatial dependencies often exhibited by violent crimes in order to make such predictions. The temporal variation of crimes typically follows patterns familiar in time series analysis, but the spatial patterns are irregular and do not vary smoothly across the area. Instead we find that spatially disjoint regions exhibit correlated crime patterns. It is this indeterminate inter-region correlation structure along with the low-count, discrete nature of counts of serious crimes that motivates our proposed forecasting tool. In particular, we propose to model the crime counts in each region using an integer-valued first order autoregressive process. We take a Bayesian nonparametric approach to flexibly discover a clustering of these region-specific time series. We then describe how to account for covariates within this framework. Both approaches adjust for seasonality. We demonstrate our approach through an analysis of weekly reported violent crimes in Washington, D.C. between 2001-2008. Our forecasts outperform standard methods while additionally providing useful tools such as prediction intervals.

stat.AP↗
arXiv2004

Least Angle Regression

The purpose of model selection algorithms such as All Subsets, Forward Selection and Backward Elimination is to choose a linear model on the basis of the same set of data to which the model will be applied. Typically we have available a large collection of possible covariates from which we hope to select a parsimonious set for the efficient prediction of a response variable. Least Angle Regression (LARS), a new model selection algorithm, is a useful and less greedy version of traditional forward selection methods. Three main properties are derived: (1) A simple modification of the LARS algorithm implements the Lasso, an attractive version of ordinary least squares that constrains the sum of the absolute regression coefficients; the LARS modification calculates all possible Lasso estimates for a given problem, using an order of magnitude less computer time than previous methods. (2) A different LARS modification efficiently implements Forward Stagewise linear regression, another promising new model selection method;

math.ST↗