Working papers

This paper studies the first nationwide introduction of automatic enrolment, in which employers in the United Kingdom are obliged to enrol employees into a workplace pension scheme, which employees can then choose to leave if they wish.

This paper considers the micro-econometric analysis of patients' hospital choice for elective medical procedures when their choice set is pre-selected by a general practitioner (GP).

We investigate the impact on social welfare of the United Kingdom (UK) policy introduced in 1980 by which public housing tenants (council housing in UK parlance) had the right to purchase their houses at heavily discounted prices.

We propose a Kronecker product structure for large covariance or correlation matrices.

Recent developments in nonlinear panel data analysis allow identifying and estimating general dynamic systems. In this review we describe some results and techniques for nonparametric identification and flexible estimation in the presence of time-invariant and time-varying latent variables.

Community-based interventions, particularly group-based ones, are considered to be a cost-effective way of delivering interventions in low-income settings. However, design features of these programs could also influence dimensions of household and community behaviour beyond those targeted by the intervention. This paper studies spillover effects of a participatory community health intervention in rural Malawi, implemented through a cluster randomised control trial, on an outcome not directly targeted by the intervention: household consumption smoothing after crop losses.

This paper models the use of statistical hypothesis testing in regulatory approval.

In this paper, we derive a rate of convergence of the Lasso estimator when the penalty parameter  for the estimator is chosen using K-fold cross-validation

Most modern supervised statistical/machine learning (ML) methods are explicitly designed to solve prediction problems very well.

The ill-posedness of the inverse problem of recovering a regression function in a nonparametric instrumental variable (NPIV) model leads to estimators that may suffer from poor statistical performance. In this paper, we explore the possibility of imposing shape restrictions to improve the performance of the NPIV estimators.

The distributional impact of proposed reforms plays a central role in public debates around tax and transfer policy. We show that accounting for realistic patterns of mobility in employment, earnings and household circumstances over the life-cycle greatly affects our assessment of the distributional effects of tax and transfer reforms.

In this paper we document significantly steeper declines in nondurable expenditures in the UK compared to the US, in spite of income paths being similar. We explore several possible causes, including different employment paths, housing ownership and expenses, levels and paths of health status, number of household members, and out-of -pocket medical expenditures. Among all the potential explanations considered, we find that those to do with healthcare—differences in levels and age paths in medical expenses—can fully account for the steeper declines in nondurable consumption in the UK compared to the US.

Quantile regression (QR) is a principal regression method for analyzing the impact of covariates on outcomes. The impact is described by the conditional quantile function and its functionals. In this paper we develop the nonparametric QR-series framework, covering many regressors as a special case, for performing inference on the entire conditional quantile function and its linear functionals.

Modern construction of uniform confidence bands for nonpara-metric densities (and other functions) often relies on the classical Smirnov-Bickel-Rosenblatt (SBR) condition; see, for example, Giné and Nickl (2010). This condition requires the existence of a limit distribution of an extreme value type for the supremum of a studentized empirical process (equivalently, for the supremum of a Gaussian process with the same covariance function as that of the studentized empirical process). The principal contribution of this paper is to remove the need for this classical condition.

This paper considers the problem of testing many moment inequalities where the number of moment inequalities, denoted by p, is possibly much larger than the sample size n.

In this paper, we derive central limit and bootstrap theorems for probabilities that centered high-dimensional vector sums hit rectangles and sparsely convex sets.

Reforms to public services have extended consumer choice by allowing for the entry of private providers. The aim is to generate competitive pressure to improve quality when consumers choose between providers. However, for many services new entrants could also affect whether a consumer demands the service at all. We explore this issue by considering how demand for elective surgery responds following the entry of private providers into the market for publicly funded health care in England.

This paper develops characterizations of identifi…ed sets of structures and structural features for complete and incomplete models involving continuous or discrete variables.

Advances in the study of partial identification allow applied researchers to learn about parameters of interest without making assumptions needed to guarantee point identification. We discuss the roles that assumptions and data play in partial identification analysis, with the goal of providing information to applied researchers that can help them employ these methods in practice.

This paper develops a new direct approach to approximating suprema of general empirical processes by a sequence of suprema of Gaussian processes, without taking the route of approximating whole empirical processes in the sup-norm.