Publications
26 results found
Yang X, Orjuela JP, McCoy E, et al., 2022, The impact of black carbon (BC) on mode-specific galvanic skin response (GSR) as a measure of stress in urban environments, Environmental Research, Vol: 214, ISSN: 0013-9351
Previous research has shown that walking and cycling could help alleviate stress in cities, however there is poor knowledge on how specific microenvironmental conditions encountered during daily journeys may lead to varying degrees of stress experienced at that moment. We use objectively measured data and a robust causal inference framework to address this gap. Using a Bayesian Doubly Robust (BDR) approach, we find that black carbon exposure statistically significantly increases stress, as measured by Galvanic Skin Response (GSR), while cycling and while walking. Augmented Outcome Regression (AOR) models indicate that greenspace exposure and the presence of walking or cycling infrastructure could reduce stress. None of these effects are statistically significant for people in motorized transport. These findings add to a growing evidence-base on health benefits of policies aimed at decreasing air pollution, improving active travel infrastructure and increasing greenspace in cities.
Bhuyan P, McCoy EJ, Li H, et al., 2021, Analysing the causal effect of London cycle superhighways on traffic congestion, Annals of Applied Statistics, Vol: 15, Pages: 1999-2022, ISSN: 1932-6157
Transport operators have a range of intervention options available to improve or enhance their networks. Such interventions are often made in the absence of sound evidence on resulting outcomes. Cycling superhighways were promoted as a sustainable and healthy travel mode, one of the aims of which was to reduce traffic congestion. Estimating the impacts that cycle superhighways have on congestion is complicated due to the nonrandom assignment of such intervention over the transport network. In this paper we analyse the causal effect of cycle superhighways utilising preintervention and postintervention information on traffic and road characteristics along with socioeconomic factors. We propose a modeling framework based on the propensity score and outcome regression model. The method is also extended to the doubly robust set-up. Simulation results show the superiority of the performance of the proposed method over existing competitors. The method is applied to analyse a real dataset on the London transport network. The methodology proposed can assist in effective decision making to improve network performance.
Yang X, McCoy E, Anaya-Boig E, et al., 2021, The effects of traveling in different transport modes on Galvanic Skin Response (GSR) as a measure of stress: an observational study, Environment International, Vol: 156, Pages: 1-10, ISSN: 0160-4120
BackgroundStress is one of many ailments associated with urban living, with daily travel a potential major source. Active travel, nevertheless, has been associated with lower levels of stress compared to other modes. Earlier work has relied on self-reported measures of stress, and on study designs that limit our ability to establish causation.ObjectivesTo evaluate effects of daily travel in different modes on an objective proxy measure of stress, the galvanic skin response (GSR).MethodsWe collected data from 122 participants across 3 European cities as part of the Physical Activity through Sustainable Transport Approaches (PASTA) study, including: GSR measured every minute alongside confounders (physical activity, near-body temperature) during three separate weeks covering 3 seasons; sociodemographic and travel information through questionnaires. Causal relationships between travel in different modes (the “treatment”) and stress were established by using a propensity score matching (PSM) approach to adjust for potential confounding and estimating linear mixed models (LMM) with individuals as random effects to account for repeated measurements. In three separate analyses, we compared GSR while cycling to not cycling, then walking to not walking then motorized (public or private) travel to any activity other than motorized travel.ResultsDepending on LMM formulations used, cycling reduces 1-minute GSR by 5.7% [95% CI: 2.0–16.9%] to 11.1% [95% CI: 5.0–24.4%] compared to any other activity. Repeating the analysis for other modes we find that: walking is also beneficial, reducing GSR by 3.9% [95% CI: 1.4–10.7%] to 5.7% [95% CI: 2.6–12.3%] compared to any other activity; motorized mode (private or public) in reverse increases GSR by up to 1.1% [95% CI: 0.5–2.9%].DiscussionActive travel offers a welcome way to reduce stress in urban dwellers’ daily lives. Stress can be added to the growing number of evidence-based reasons for
Liu B, Cardoso A, Couturier P, et al., 2021, Datasets for online controlled experiments, NeurIPS Datasets and Benchmarks 2021
Online Controlled Experiments (OCE) are the gold standard to measure impact and guide decisions for digital products and services. Despite many methodological advances in this area, the scarcity of public datasets and the lack of a systematic review and categorization hinder its development. We present the first survey and taxonomy for OCE datasets, which highlight the lack of a public dataset to support the design and running of experiments with adaptive stopping, an increasingly popular approach to enable quickly deploying improvements or rolling back degrading changes. We release the first such dataset, containing daily checkpoints of decision metrics from multiple, real experiments run on a global e-commerce platform. The dataset design is guided by a broader discussion on data requirements for common statistical tests used in digital experimentation. We demonstrate how to use the dataset in the adaptive stopping scenario using sequential and Bayesian hypothesis tests and learn the relevant parameters for each approach.
Liu CHB, Chamberlain BP, McCoy EJ, 2020, What is the value of experimentation and measurement?, Data Science and Engineering, Vol: 5, Pages: 152-167, ISSN: 2364-1185
Experimentation and Measurement (E&M) capabilities allow organizations to accurately assess the impact of new propositions and to experiment with many variants of existing products. However, until now, the question of measuring the measurer, or valuing the contribution of an E&M capability to organizational success has not been addressed. We tackle this problem by analyzing how, by decreasing estimation uncertainty, E&M platforms allow for better prioritization. We quantify this benefit in terms of expected relative improvement in the performance of all new propositions and provide guidance for how much an E&M capability is worth and when organizations should invest in one.
Graham D, Niak C, McCoy EJ, et al., 2019, Do speed cameras reduce road traffic collisions?, PLoS One, Vol: 14, ISSN: 1932-6203
This paper quantifies the effect of speed cameras on road trafficcollisions using anapproximate Bayesian doubly-robust (DR) causal inference estimation method.Previous empirical work on this topic, which shows a diverse range ofestimatedeffects, is based largely on outcome regression (OR) models using the Empirical Bayesapproach or on simple before and after comparisons. Issues of causality andconfounding have received little formal attention. A causal DR approach combinespropensity score (PS) and OR models to give an average treatmenteffect (ATE)estimator that is consistent and asymptotically normal under correct specification ofeither of the two component models. We develop this approach withina novelapproximate Bayesian framework to derive posterior predictive distributions for theATE of speed cameras on road traffic collisions. Our results for England indicatesignificant reductions in the number of collisions at speed cameras sites (mean ATE =-15%). Our proposed method offers a promising approach for evaluation of transportsafety interventions.
Graham DJ, McCoy EJ, Stephens DA, 2016, Approximate Bayesian inference for doubly robust estimation, Bayesian Analysis, Vol: 11, Pages: 47-69, ISSN: 1931-6690
Doubly robust estimators are typically constructed by combining outcome regression and propensity score models to satisfy moment restrictions that ensure consistent estimation of causal quantities provided at least one of the component models is correctly specified. Standard Bayesian methods are difficult to apply because restricted moment models do not imply fully specified likelihood functions. This paper proposes a Bayesian bootstrap approach to derive approximate posterior predictive distributions that are doubly robust for estimation of causal quantities. Simulations show that the approach performs well under various sources of misspecification of the outcome regression or propensity score models. The estimator is applied in a case study of the effect of area deprivation on the incidence of child pedestrian casualties in British cities.
Tzouras S, Anagnostopoulos C, Mccoy E, 2015, Financial time series modeling using the Hurst exponent, PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, Vol: 425, Pages: 50-68, ISSN: 0378-4371
- Author Web Link
- Cite
- Citations: 22
McCoy EJ, Graham DJ, Stephens DA, 2014, Quantifying causal effects of road network capacity expansions on traffic volume and density via a mixed model propensity score estimator, Journal of the American Statistical Association, Vol: 109, ISSN: 1537-274X
Road network capacity expansions are frequently proposed as solutions to ur-ban traffic congestion but are controversial because it is thought that theycan directly ‘induce’ growth in traffic volumes. This paper quantifies causaleffects of road network capacity expansions on aggregate urban traffic volumeand density in US cities using a mixed model propensity score (PS) estimator.The motivation for this approach is that we seek to estimate a dose-responserelationship between capacity and volume but suspect confounding from bothobserved and unobserved characteristics. Analytical results and simulationsshow that a longitudinal mixed model PS approach can be used to adjust ef-fectively for time-invariant unobserved confounding via random effects. Ourempirical results indicate that network capacity expansions can cause substan-tial increases in aggregate urban traffic volumes such that even major capacityincreases can actually lead to little or no reduction in network traffic densi-ties. This result has important implications for optimal urban transportationstrategies.
Martin JS, Jasra A, Singh SS, et al., 2014, Approximate Bayesian computation for smoothing, Stochastic Analysis and Applications, Vol: 32, Pages: 397-420, ISSN: 0736-2994
We consider a method for approximate inference in hidden Markov models (HMMs). The method circumvents the need to evaluate conditional densities of observations given the hidden states. It may be considered an instance of Approximate Bayesian Computation (ABC) and it involves the introduction of auxiliary variables valued in the same space as the observations. The quality of the approximation may be controlled to arbitrary precision through a parameter ε > 0. We provide theoretical results which quantify, in terms of ε, the ABC error in approximation of expectations of additive functionals with respect to the smoothing distributions. Under regularity assumptions, this error is, where n is the number of time steps over which smoothing is performed. For numerical implementation, we adopt the forward-only sequential Monte Carlo (SMC) scheme of [14] and quantify the combined error from the ABC and SMC approximations. This forms some of the first quantitative results for ABC methods which jointly treat the ABC and simulation errors, with a finite number of data and simulated samples. © Taylor & Francis Group, LLC.
Martin JS, Jasra A, McCoy E, 2013, Inference for a class of partially observed point process models, Annals of the Institute of Statistical Mathematics, Vol: 65, Pages: 413-437, ISSN: 0020-3157
This paper presents a simulation-based framework for sequential inference from partially and discretely observed point process models with static parameters. Taking on a Bayesian perspective for the static parameters, we build upon sequential Monte Carlo methods, investigating the problems of performing sequential filtering and smoothing in complex examples, where current methods often fail. We consider various approaches for approximating posterior distributions using SMC. Our approaches, with some theoretical discussion are illustrated on a doubly stochastic point process applied in the context of finance.
Jasra A, Singh SS, Martin JS, et al., 2012, Filtering via approximate Bayesian computation, STATISTICS AND COMPUTING, Vol: 22, Pages: 1223-1237, ISSN: 0960-3174
- Author Web Link
- Cite
- Citations: 46
Graham DJ, McCoy EJ, Stephens DA, 2012, Quantifying the effect of area deprivation on child pedestrian casualties by using longitudinal mixed models to adjust for confounding, interference and spatial independence, Journal of the Royal Statistical Society Series A-Statistics in Society, Vol: 176, ISSN: 0964-1998
Yang Z, Walden AT, McCoy EJ, 2011, Correntropy: Implications of nonGaussianity for the moment expansion and deconvolution, Signal Processing, Vol: 91, Pages: 864-876
The recently introduced correntropy function is an interesting and useful similarity measure between two random variables which has found myriad applications in signal processing. A series expansion for correntropy in terms of higher-order moments of the difference between the two random variables has been used to try to explain its statistical properties for uses such as deconvolution. We examine the existence and form of this expansion, showing that it may be divergent, e.g., when the difference has the Laplace distribution, and give sufficient conditions for its existence for differently characterized sub-Gaussian distributions. The contribution of the higher-order moments can be quite surprising, depending on the size of the Gaussian kernel in the definition of the correntropy. In the blind deconvolution setting we demonstrate that statistical exchangeability explains the existence of sub-optimal minima in the correntropy cost surface and show how the positions of these minima are controlled by the size of the Gaussian kernel.
Au-Yeung SWM, Harder U, Mccoy EJ, et al., 2009, Predicting patient arrivals to an accident and emergency department, EMERGENCY MEDICINE JOURNAL, Vol: 26, Pages: 241-244, ISSN: 1472-0205
- Author Web Link
- Cite
- Citations: 19
McCoy EJ, Stephens DA, 2004, Bayesian time series analysis of periodic behaviour and spectral structure, INTERNATIONAL JOURNAL OF FORECASTING, Vol: 20, Pages: 713-730, ISSN: 0169-2070
- Author Web Link
- Cite
- Citations: 5
Olhede SC, McCoy EJ, Stephens DA, 2004, Large-sample properties of the periodogram estimator of seasonally persistent processes, Biometrika, Vol: 91, Pages: 613-628, ISSN: 0006-3444
Hodges SD, Roberts G, Papaspiliopoulos O, et al., 2001, Non-Gaussian Ornstein-Uhlenbeck-based models and some of their uses in financial economics -: Discussion, JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, Vol: 63, Pages: 208-241, ISSN: 1369-7412
- Author Web Link
- Cite
- Citations: 4
McCoy EJ, 2001, Wavelet-based modelling of persistent periodicities, 3rd European Congress of Mathematics (3ecm), Publisher: BIRKHAUSER VERLAG AG, Pages: 601-608
McCoy EJ, Walden AT, Percival DB, 1998, Multitaper spectral estimation of power law processes, IEEE Transactions on Signal Processing, Vol: 46, Pages: 655-668, ISSN: 1053-587X
Walden AT, Percival DB, McCoy EJ, 1998, Spectrum estimation by wavelet thresholding of multitaper estimators, IEEE Transactions on Signal Processing, Vol: 46, Pages: 3153-3165, ISSN: 1053-587X
McCoy EJ, Walden AT, Percival DB, 1998, Multitaper spectral estimation of power law processes, IEEE Transactions on Signal Processing, Vol: 46, Pages: 655-668, ISSN: 1053-587X
Walden AT, Percival DB, McCoy EJ, 1998, Spectrum estimation by wavelet thresholding of multitaper estimators, IEEE Transactions on Signal Processing, Vol: 46, Pages: 3153-3165, ISSN: 1053-587X
McCoy EJ, Walden AT, 1996, Wavelet analysis and synthesis of stationary long-memory processes, Journal of Computational and Graphical Statistics, Vol: 5, Pages: 26-56, ISSN: 1061-8600
WALDEN AT, MCCOY EJ, PERCIVAL DB, 1995, THE EFFECTIVE BANDWIDTH OF A MULTITAPER SPECTRAL ESTIMATOR, BIOMETRIKA, Vol: 82, Pages: 201-214, ISSN: 0006-3444
- Author Web Link
- Cite
- Citations: 46
WALDEN AT, MCCOY E, PERCIVAL DB, 1994, THE VARIANCE OF MULTITAPER SPECTRUM ESTIMATES FOR REAL GAUSSIAN-PROCESSES, IEEE TRANSACTIONS ON SIGNAL PROCESSING, Vol: 42, Pages: 479-482, ISSN: 1053-587X
- Author Web Link
- Cite
- Citations: 42
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.