Antony Andrews is an applied economist working at the intersection of public economics, health economics and environmental policy. His research examines how public systems, institutions, and policy shocks shape efficiency, welfare, risk, and economic adjustment. Methodologically, his work uses applied econometrics, including Bayesian methods, panel-data models, efficiency analysis, and latent-variable approaches, to study policy problems in which uncertainty and measurement matter. His main research agenda examines public-sector performance and policy-relevant efficiency, with a particular focus on healthcare systems. A second strand extends this agenda to climate, energy and environmental policy, studying energy inefficiency, growth-carbon lock-in, climate-related welfare losses and macroeconomic downside risk. His recent work further connects this policy-econometrics agenda to expectation formation, examining how central-bank communication and institutional credibility shape household inflation expectations.
Why do some advanced economies remain persistently energy productivity-inefficient despite technological progress? This study argues that the constraint is institutional, not merely technical. Using a dynamic Bayesian stochastic frontier model for 37 OECD countries (2000–2021), this study develops the Energy Waste Severity Index (EWSI), a frontier-based metric that captures both the level and persistence of energy productivity inefficiency. The EWSI reveals a clear divide: countries such as Poland and Ireland face high, entrenched waste consistent with structural and governance frictions, whereas Japan, Switzerland, New Zealand, and the United States pair low inefficiency with weaker persistence. Because persistence signals institutional drag, technical fixes alone are insufficient; coordinated policy and governance reforms are required. By pairing benchmarking with persistence, the EWSI provides policymakers with a practical diagnostic tool to identify bottlenecks, align energy planning with skills, investment, and regulation, and monitor progress toward achieving SDG 7.
This study introduces a hierarchical Bayesian model that decomposes hospital inefficiency into components inherited from higher administrative tiers and those self-generated at the hospital level. This approach extends traditional efficiency analyses (e.g., stochastic frontier models that assume inefficiency occurs only at the provider level) by capturing how inefficiency cascades from provinces and regions down to individual hospitals. The study applies the model to 942 hospital-year observations (2015–2019) from three Canadian provinces (Alberta, Nova Scotia, Ontario). The framework separates persistent technical inefficiency into three latent factors at the province, region, and hospital levels, quantifying inefficiency inherited from upstream governance and inefficiency generated at each level. Results show that inherited inefficiency from higher tiers accounts for roughly 73–76 % of total persistent inefficiency across these provinces. This challenges the policy orthodoxy of targeting individual hospitals in isolation, as even hospitals with low self-generated inefficiency remain far from the efficiency frontier due to systemic constraints imposed by higher levels. This study offers the first empirical decomposition of inefficiency across a national health system's hierarchy. Although demonstrated in Canada, the approach is generalizable to any healthcare system with multilevel governance. It provides policymakers with a diagnostic tool to benchmark efficiency more accurately and to design system-level reforms, such as aligning funding flows, streamlining administration, and removing bottlenecks to achieve meaningful efficiency gains. Keywords
This study explores the complex relationship between firm efficiency and stochastic volatility, focusing on how firms utilise inputs to generate sales and the impact of financial shocks on efficiency levels. Utilising a dataset of 476 U.S. firms across 23 sectors from 2010 to 2022, it integrates stochastic volatility into efficiency analysis, treating volatility as an evolving, unobserved process diverging from traditional methods. The research classifies sectors into various efficiency performance categories based on their response to economic fluctuations. Findings show divergent patterns across sectors, with some exhibiting consistent efficiency and others facing erratic performance due to market and technological changes. This analysis provides valuable insights into sectoral adaptability and resilience in fluctuating economic conditions, offering strategic implications for managers and policymakers.
Using Bayesian Structural Time Series analysis, this study examines the causal impact of loan-to-value (LTV) restrictions imposed by the Reserve Bank of New Zealand in October 2013. By incorporating state-space components, such as local linear trend, seasonality and regression, counterfactual values of house price indices are predicted. Surprisingly, the study reveals that the implementation of LTV restrictions had no significant effect on national house price indices, contradicting prior Central Bank studies that reported a nearly 3 percentage-point decrease in housing cost inflation. This contradictory evidence challenges existing perceptions of the effectiveness of LTV restrictions in curbing house price inflation.
Efficiency analysis is crucial in healthcare to optimise resource allocation and enhance patient outcomes. However, the prompt adaptation of inputs can be hindered by adjustment costs, which impact Long-Run Technical Efficiency (LRTE). To bridge this gap in healthcare literature, this research employs a Bayesian Dynamic Stochastic Frontier Model to estimate parameters and explore healthcare efficiency dynamics over time. The study reveals the LRTE for New Zealand District Health Boards (DHBs) as 0.76, indicating around 32% more input utilisation due to adjustment costs. Most DHBs exhibit consistent short-run operational efficiency, with the national Short-Run Technical Efficiency (SRTE) very close to the LRTE. Among the tertiary providers, Auckland and Capital & Coast DHBs operate below the LRTE level, setting them apart from other tertiary providers. Similarly, Tairawhiti and West Coast DHBs also fall below the LRTE level, as indicated by their SRTE scores, potentially influenced by their unique healthcare settings and resource challenges. This research brings a new perspective to policy discussions by incorporating the temporal dynamics of decision-making and considering adjustment costs. It underscores the need to balance short-term and long-term technical efficiency, underlining their collective significance in fostering a sustainable and efficient healthcare system in New Zealand.
Efficiency and productivity analysis have been critical in healthcare and economics literature. Despite the tremendous innovation in methodology and data availability, a comprehensive literature review on this topic has not been conducted recently. This article provides a three-part literature review of healthcare efficiency and productivity studies. It begins by reviewing the two primary empirical methods used in healthcare efficiency studies, emphasising the treatment of inefficiency persistence. Second, previous contributions to healthcare productivity research are discussed with a focus on methodology and findings. In the third section, various measures of outputs, inputs, and prices in health literature are explored to determine the extent of consensus in the literature. On the methodological front, the literature review shows that while the Data Envelopment Analysis and the Stochastic Frontier Analysis have been used extensively in healthcare productivity and efficiency studies, their application in the context of longitudinal data is limited. Further, no study currently undertakes to measure the TFP changes and its components that use both primal and dual approaches. There is also a considerable variation in the use of inputs, outputs, and price variables, suggesting that the use of variables in healthcare productivity and efficiency literature rests on the balance between data availability and the research scope.
This article introduces the Bayesian structural time series (BSTS) as a potential tool for forecasting in the tourism literature. Using data on Australian tourist arrivals in New Zealand, the forecasting accuracy of the estimated model is evaluated using a fixed partitioning approach. The MAPE of the fitted model is 3.11 per cent for the validation stage and 2.75 per cent for the test stage. The BSTS outperforms two other competing models both in the validation and test stage. In addition to forecasting, BSTS also estimates the trend, trend slope, and seasonality that change over time.
This study uses quarterly data from 2011 to 2018 to evaluate the technical efficiency of New Zealand District Health Boards (DHBs) in providing hospital services. It examines how efficiency is affected by various patient structures and contextual factors. An intertemporal data envelopment analysis and bootstrap approach are used to compute the bias-corrected technical efficiency scores, followed by highly flexible beta regression to assess the relationship between technical efficiency and related factors. The results indicate that the technical efficiency levels of New Zealand DHBs have not improved since 2011, and on average DHBs could increase their provision of hospital services by approximately 12%. Furthermore, most of the poor performing DHBs operate in the area of high socio-economic deprivation. The results from beta regression show that DHBs providing hospital services in highly deprived areas are associated with a decreasing level of technical efficiency as the proportion of surgical, acute, Māori and Pacific inpatient increases. However, an increase in capital to labour ratio improves the technical efficiency of these DHBs. Therefore, policymakers need to formulate comprehensive strategies involving a longer time horizon that facilitates capital investments in critical technology and capacity development to improve the long-run efficiency performance of DHBs operating in the area of high deprivation.
The majority of secondary and tertiary healthcare services in New Zealand are provided through public hospitals managed by 20 local District Health Boards. Due to data issues and ill-judged generic public perceptions, efficiency studies are insufficient in spite of the extensive empirical literatures available. This inevitably leads to criticisms about the perverse incentives which might be created by the National Health Targets designed to improve the performance of public health services. Utilizing a multifaceted administrative hospital dataset, this is the first case study to measure both the technical and cost efficiency of New Zealand public hospitals during the period of 2011–2017. More specifically, it deals with the question of how hospital efficiency varies with respect to activities accounted for by the National Health Targets. The empirical results show no evidence that these targets are achieved at the expenses of lowering the overall efficiency of hospital operations. The national technical efficiency is averaged at 86 percent over the period and cost efficiency is 85 percent. The results are derived by stochastic input distance function and cost frontier in order to accommodate multiple outputs and limited number of census observations. Efficiency ranking is sensitive to specifications of the inefficiency error term, but reasonably robust to the choice of functional form and different proxies for capital input.