Consolidated Health Economic Evaluation Reporting Standards 2022 (CHEERS 2022) statement: updated reporting guidance for health economic evaluations.

Health economic evaluations are comparative analyses of alternative courses of action in terms of their costs and consequences. The Consolidated Health Economic Evaluation Reporting Standards (CHEERS) statement, published in 2013, was created to ensure health economic evaluations are identifiable, interpretable, and useful for decision making. It was intended as guidance to help authors report accurately which health interventions were being compared and in what context, how the evaluation was undertaken, what the findings were, and other details that may aid readers and reviewers in interpretation and use of the study. The new CHEERS 2022 statement replaces previous CHEERS reporting guidance. It reflects the need for guidance that can be more easily applied to all types of health economic evaluation, new methods and developments in the field, as well as the increased role of stakeholder involvement including patients and the public. It is also broadly applicable to any form of intervention intended to improve the health of individuals or the population, whether simple or complex, and without regard to context (such as health care, public health, education, social care, etc). This summary article presents the new CHEERS 2022 28-item checklist and recommendations for each item. The CHEERS 2022 statement is primarily intended for researchers reporting economic evaluations for peer reviewed journals as well as the peer reviewers and editors assessing them for publication. However, we anticipate familiarity with reporting requirements will be useful for analysts when planning studies. It may also be useful for health technology assessment bodies seeking guidance on reporting, as there is an increasing emphasis on transparency in decision making.

A cardiovascular disease policy model: part 2-preparing for economic evaluation and to assess health inequalities.

OBJECTIVES: This is the second of the two papers introducing a cardiovascular disease (CVD) policy model. The first paper described the structure and statistical underpinning of the state-transition model, demonstrating how life expectancy estimates are generated for individuals defined by ASSIGN risk factors. This second paper describes how the model is prepared to undertake economic evaluation. DESIGN: To generate quality-adjusted life expectancy (QALE), the Scottish Health Survey was used to estimate background morbidity (health utilities) and the impact of CVD events (utility decrements). The SF-6D algorithm generated utilities and decrements were modelled using ordinary least squares (OLS). To generate lifetime hospital costs, the Scottish Heart Health Extended Cohort (SHHEC) was linked to the Scottish morbidity and death records (SMR) to cost each continuous inpatient stay (CIS). OLS and restricted cubic splines estimated annual costs before and after each of the first four events. A Kaplan-Meier sample average (KMSA) estimator was then used to weight expected health-related quality of life and costs by the probability of survival. RESULTS: The policy model predicts the change in QALE and lifetime hospital costs as a result of an intervention(s) modifying risk factors. Cost-effectiveness analysis and a full uncertainty analysis can be undertaken, including probabilistic sensitivity analysis. Notably, the impacts according to socioeconomic deprivation status can be made. CONCLUSIONS: The policy model can conduct cost-effectiveness analysis and decision analysis to inform approaches to primary prevention, including individually targeted and population interventions, and to assess impacts on health inequalities.

A cardiovascular disease policy model that predicts life expectancy taking into account socioeconomic deprivation.

OBJECTIVES: A policy model is a model that can evaluate the effectiveness and cost-effectiveness of interventions and inform policy decisions. In this study, we introduce a cardiovascular disease (CVD) policy model which can be used to model remaining life expectancy including a measure of socioeconomic deprivation as an independent risk factor for CVD. DESIGN: A state transition model was developed using the Scottish Heart Health Extended Cohort (SHHEC) linked to Scottish morbidity and death records. Individuals start in a CVD-free state and can transit to three CVD event states plus a non-CVD death state. Individuals who have a non-fatal first event are then followed up until death. Taking a competing risk approach, the cause-specific hazards of a first event are modelled using parametric survival analysis. Survival following a first non-fatal event is also modelled parametrically. We assessed discrimination, validation and calibration of our model. RESULTS: Our model achieved a good level of discrimination in each component (c-statistics for men (women)-non-fatal coronary heart disease (CHD): 0.70 (0.74), non-fatal cerebrovascular disease (CBVD): 0.73 (0.76), fatal CVD: 0.77 (0.80), fatal non-CVD: 0.74 (0.72), survival after non-fatal CHD: 0.68 (0.67) and survival after non-fatal CBVD: 0.65 (0.66)). In general, our model predictions were comparable with observed event rates for a Scottish randomised statin trial population which has an overlapping follow-up period with SHHEC. After applying a calibration factor, our predictions of life expectancy closely match those published in recent national life tables. CONCLUSIONS: Our model can be used to estimate the impact of primary prevention interventions on life expectancy and can assess the impact of interventions on inequalities.

Consolidated Health Economic Evaluation Reporting Standards (CHEERS) statement.

Economic evaluations of health interventions pose a particular challenge for reporting. There is also a need to consolidate and update existing guidelines and promote their use in a user friendly manner. The Consolidated Health Economic Evaluation Reporting Standards (CHEERS) statement is an attempt to consolidate and update previous health economic evaluation guidelines efforts into one current, useful reporting guidance.The primary audiences for the CHEERS statement are researchers reporting economic evaluations and the editors and peer reviewers assessing them for publication. The need for new reporting guidance was identified by a survey of medical editors. A list of possible items based on a systematic review was created. A two round, modified Delphi panel consisting of representatives from academia, clinical practice, industry, government, and the editorial community was conducted. Out of 44 candidate items, 24 items and accompanying recommendations were developed. The recommendations are contained in a user friendly, 24 item checklist. A copy of the statement, accompanying checklist, and this report can be found on the ISPOR Health Economic Evaluations Publication Guidelines Task Force website (www.ispor.org/TaskForces/EconomicPubGuidelines.asp). We hope CHEERS will lead to better reporting, and ultimately, better health decisions. To facilitate dissemination and uptake, the CHEERS statement is being co-published across 10 health economics and medical journals. We encourage other journals and groups, to endorse CHEERS. The author team plans to review the checklist for an update in 5 years.

A patient-centred approach to estimate total annual healthcare cost by body mass index in the UK Counterweight programme.

BACKGROUND: Previous studies, based on relative risks for certain secondary diseases, have shown greater healthcare costs in higher body mass index (BMI) categories. The present study quantifies the relationship between BMI and total healthcare expenditure, with the patient as the unit of analysis. METHODS: Analyses of cross-sectional data, collected over 18-months in 2002-2003, from 3324 randomly selected patients, in 65 general practices across UK. Healthcare costs estimated from primary care, outpatient, accident/emergency and hospitalisation attendances, weighted by unit costs taken from standard sources. RESULTS: In univariate analyses, significant associations (P<0.05) were found between total healthcare expenditure and all dependent variables (women>men, drinkernon-smokers, and increasing with greater physical activity, age and BMI. In multivariate analysis, age, sex, BMI, smoking and alcohol consumption remained significantly associated with healthcare cost, and together explained just 9% of the variance in healthcare expenditure. Adjusted total annual healthcare cost was £16 (95% CI £11-£21) higher per unit BMI. All cost categories were significantly (P<0.003) higher for those with BMI >40 compared with BMI <20 kg m(-2): prescription drugs (men: £390 versus £16; women: £211 versus £73), hospitalisation (men: £72 versus £0; women: £243 versus £107), primary care (men: £191 versus £69; women: £268 versus £153) and outpatient care (£234 versus £107 women only). CONCLUSIONS: Annual healthcare expenditure rose a mean of £16 per unit greater BMI, doubling between BMI 20-40 kg m(-2). This gradient may be an underestimate if the lower-BMI patients with heights and weights recorded had other costly diseases.

How to design and evaluate randomized controlled trials in immunotherapy for allergic rhinitis: an ARIA-GA(2) LEN statement.

Specific immunotherapy (SIT) is one of the treatments for allergic rhinitis. However, for allergists, nonspecialists, regulators, payers, and patients, there remain gaps in understanding the evaluation of randomized controlled trials (RCTs). Although treating the same diseases, RCTs in SIT and pharmacotherapy should be considered separately for several reasons, as developed in this study. These include the severity and persistence of allergic rhinitis in the patients enrolled in the study, the problem of the placebo, allergen exposure (in particular pollen and mite), the analysis and reporting of the study, the level of symptoms of placebo-treated patients, the clinical relevance of the efficacy of SIT, the need for a validated combined symptom-medication score, the differences between children and adults and pharmacoeconomic analyses. This statement reviews issues raised by the interpretation of RCTs in sublingual immunotherapy. It is not possible to directly extrapolate the rules or parameters used in medication RCTs to SIT. It also provides some suggestions for the research that will be needed. Interestingly, some of the research questions can be approached with the available data obtained from large RCTs.

Estimation and external validation of a new prognostic model for predicting recurrence-free survival for early breast cancer patients in the UK.

BACKGROUND: We aimed to estimate and externally validate a new UK-specific prognostic model for predicting the long-term risk of a first recurrent event (local recurrence, metastatic recurrence, or second primary breast cancer) in women diagnosed with early breast cancer. METHODS: Using data on the prognostic characteristics and outcomes of 1844 women treated for early breast cancer at the Churchill Hospital in Oxford, parametric regression-based survival analysis was used to estimate a prognostic model for recurrence-free survival. The model, which incorporated established prognostic factors, was externally validated using independent data. Its performance was compared with that of the Nottingham Prognostic Index (NPI) and Adjuvant! Online. RESULTS: The number of positive axillary lymph nodes, tumour grade, tumour size and patient age were strong predictors of recurrence. Oestrogen receptor (ER) positivity was shown to afford a moderate protective effect. The model was able to separate patients into distinct prognostic groups, and predicted well at the patient level, mean Brier Accuracy Score=0.17 (s.e.=0.004) and overall C=0.745 (95% CI, 0.717-0.773). Its performance diminished only slightly when applied to a second independent data set. When compared with the NPI, the model was able to better discriminate between women with excellent and good prognoses, and it did not overestimate 10-year recurrence-free survival to the extent observed for Adjuvant! Online. CONCLUSION: The model estimated here predicts well at both the individual patient and group levels, and appears transportable to patients treated at other UK hospitals. Its parametric form permits long-term extrapolation giving it an advantage over other prognostic tools currently in use. A simple point scoring system and reference table allow 5-, 10-, and 15-year predictions from the model to be quickly and easily estimated. The model is also available to download as an interactive computer program.

Is treatment with ICS and LABA cost-effective for COPD? Multinational economic analysis of the TORCH study.

The TOwards a Revolution in COPD Health (TORCH) study was a 3-yr multicentre trial of 6,112 patients randomised to salmeterol (Salm), fluticasone propionate (FP), a Salm/FP combination (SFC) or placebo (P). Here the cost-effectiveness of treatments evaluated in the TORCH study is assessed. For four regions, 3-yr all-cause hospitalisation, medication and outpatient care costs were calculated. The sample was restricted to the 21 countries (n = 4,237) in which European quality of life five-dimension (EQ-5D) data were collected in order to estimate the number of quality-adjusted life years (QALYs). Regression models were fitted to survival, study medication cost, other medication cost and EQ-5D data in order to estimate total cost, number of QALYs and cost per QALY, adjusted for missing data and region. SFC had a trial-wide estimate of cost per QALY of 43,600 US dollars (USD) compared with P (95% confidence interval 21,400-123,500 USD). Estimates for Salm versus P (197,000 USD) and FP versus P (78,000 USD) were less favourable. The US estimates were greater than those from other regions; for SFC versus P, the cost per QALY was 77,100 (46,200-241,700) USD compared to 24,200 (15,200-56,100) USD in Western Europe. Compared with P, SFC has a lower incremental cost-effectiveness ratio than either FP or Salm used alone, and is, therefore, preferred to these monotherapies on the grounds of cost-effectiveness.

How cost-effective is screening for abdominal aortic aneurysms?

OBJECTIVE: To provide reliable estimates of the long-term cost-effectiveness of abdominal aortic aneurysm screening in men. METHODS: A Markov health economic decision model for screening is described and extrapolated to 30 years. The strategy modelled involves a one-off scan at age 65 years, with annual and three-monthly follow-up scans for small and medium aneurysms, respectively. Referral for elective surgery occurs at an aortic diameter of 5.5 cm. Model parameters are estimated from patient-level data from the UK Multi-centre Aneurysm Screening Study. Model structure is validated on this trial's data, and input parameter uncertainty is addressed by probabilistic sensitivity analysis. Costs and life-years gained are obtained for both screening and no systematic screening strategies. RESULTS: Cost-effectiveness improves dramatically when considered over longer timescales. Taking a 30-year perspective, screening for abdominal aortic aneurysms in men is highly cost-effective at 2320 pounds per life-year gained (95% uncertainty interval: 1600 pounds to 4240 pounds). Adjusting life-years for the age-specific health-related quality of life experienced in this population gave a figure of 2970 pounds (95% uncertainty interval: 2030 pounds to 5430 pounds) per quality-adjusted life-year gained. The additional cost of screening the UK male population is estimated to be 19 m pounds per year. CONCLUSIONS: The long-term cost-effectiveness of screening for abdominal aortic aneurysms in men is highly attractive and this evidence provides further support for a national screening programme in the UK.

Meta-analysis of mixed treatment comparisons at multiple follow-up times.

Mixed treatment comparisons (MTC) meta-analysis is a methodology for making inferences on relative treatment effects based on a synthesis of both direct and indirect evidence on multiple treatment contrasts. This is particularly useful in the context of cost-effectiveness analysis and medical decision making. Here, we extend these methods to a more complex situation where trials report results at one or more, different yet fixed, follow-up times. These methods are applied to an illustrative data set combining evidence on healing rates under six different treatments for gastro-esophageal reflux disease (GERD). A series of Bayesian hierarchical models based on piece-wise exponential hazards is developed that borrow strength across the MTC networks and also across time points. These include models for absolute and relative treatment effects, models with fixed or random effects over time, random walk models, and models with homogeneous or heterogeneous between-trials variation. The deviance information criterion (DIC) is used to guide model development and selection. Models for absolute treatment effects generate materially different rankings of the treatments than models that separate the trial-specific baselines from the relative treatment effects. The extent of between-trials heterogeneity in treatment effects depends on treatment contrast. In discussion we note that models of this type have a very wide potential application.

Cost-effectiveness of asthma control: an economic appraisal of the GOAL study.

BACKGROUND: The Gaining Optimal Asthma ControL (GOAL) study has shown the superiority of a combination of salmeterol/fluticasone propionate (SFC) compared with fluticasone propionate alone (FP) in terms of improving guideline defined asthma control. METHODS: Clinical and economic data were taken from the GOAL study, supplemented with data on health related quality of life, in order to estimate the cost per quality adjusted life year (QALY) results for each of three strata (previously corticosteroid-free, low- and moderate-dose corticosteroid users). A series of statistical models of trial outcomes was used to construct cost effectiveness estimates across the strata of the multinational GOAL study including adjustment to the UK experience. Uncertainty was handled using the non-parametric bootstrap. Cost-effectiveness was compared with other treatments for chronic conditions. RESULT: Salmeterol/fluticasone propionate improved the proportion of patients achieving totally and well-controlled weeks resulting in a similar QALY gain across the three strata of GOAL. Additional costs of treatment were greatest in stratum 1 and least in stratum 3, with some of the costs offset by reduced health care resource use. Cost-effectiveness by stratum was 7600 pound (95% CI: 4800-10,700 pound) per QALY gained for stratum 3; 11,000 pound (8600-14,600 pound) per QALY gained for stratum 2; and 13,700 pound (11,000-18,300 pound) per QALY gained for stratum 1. CONCLUSION: The GOAL study previously demonstrated the improvement in total control associated with the use of SFC compared with FP alone. This study suggests that this improvement in control is associated with cost-per-QALY figures that compare favourably with other uses of scarce health care resources.

Analysis of uncertainty in health care cost-effectiveness studies: an introduction to statistical issues and methods.

Cost-effectiveness analysis is now an integral part of health technology assessment and addresses the question of whether a new treatment or other health care program offers good value for money. In this paper we introduce the basic framework for decision making with cost-effectiveness data and then review recent developments in statistical methods for analysis of uncertainty when cost-effectiveness estimates are based on observed data from a clinical trial. Although much research has focused on methods for calculating confidence intervals for cost-effectiveness ratios using bootstrapping or Fieller's method, these calculations can be problematic with a ratio-based statistic where numerator and/or denominator can be zero. We advocate plotting the joint density of cost and effect differences, together with cumulative density plots known as cost-effectiveness acceptability curves (CEACs) to summarize the overall value-for-money of interventions. We also outline the net-benefit formulation of the cost-effectiveness problem and show that it has particular advantages over the standard incremental cost-effectiveness ratio formulation.

Affordability and cost-effectiveness: decision-making on the cost-effectiveness plane.

Much recent research interest has focused on handling uncertainty in cost-effectiveness analysis and in particular the calculation of confidence intervals for incremental cost-effectiveness ratios (ICERs). Problems of interpretation when ICERs are negative have led to two important and related developments: the use of the net-benefit statistic and the presentation of uncertainty in cost-effectiveness analysis using acceptability curves. However, neither of these developments directly addresses the problem that decision-makers are constrained by a fixed-budget and may not be able to fund new, more expensive interventions, even if they have been shown to represent good value for money. In response to this limitation, the authors introduce the 'affordability curve' which reflects the probability that a programme is affordable for a wide range of threshold budgets. The authors argue that the joint probability an intervention is affordable and cost-effective is more useful for decision-making since it captures both dimensions of the decision problem faced by those responsible for health service budgets.

Cost-effectiveness of beta-blocker therapy with metoprolol or with carvedilol for treatment of heart failure in Canada.

OBJECTIVE: The purpose of this study was to estimate the cost-effectiveness of beta-blocker therapy with either metoprolol or carvedilol in addition to conventional therapy for patients with heart failure (HF) in Canada. DESIGN: A Markov simulation was used to estimate the costs and life expectancy for treating patients with conventional therapy alone and with the addition of metoprolol or carvedilol. Although carvedilol has been marketed in Canada since 1999, metoprolol succinate has yet to be marketed there, so the price is unknown. Therefore we input a Canadian price based on the price ratio of the 2 drugs in the United States. RESULTS: For subjects aged 60 years at HF onset, the expected years of life are 4.53 years for those treated with conventional therapy alone, 5.70 years for those who receive conventional therapy plus metoprolol, and 6.21 years for those who receive conventional therapy plus carvedilol. The expected costs (in 1999 Canadian dollars) are $8,989, $13,833, and $18,114, respectively. This yields incremental cost-effectiveness ratios (ICERs) for metoprolol relative to conventional therapy alone of $4,140 per life-year gained, and for carvedilol relative to metoprolol, the ICER is $8,394 per life-year gained. CONCLUSIONS: In addition to conventional therapy with furosemide and angiotensin converting enzyme inhibitors, treatment with either metoprolol or carvedilol confers a survival benefit that is attractive from a cost-effectiveness point of view. Until better information becomes available, it is not possible to distinguish between the two beta-blockers on the basis of cost-effectiveness. This means that the choice of beta-blockers for HF should be based largely on clinical considerations because both beta-blockers prolong life at relatively low cost.

A Bayesian approach to stochastic cost-effectiveness analysis. An illustration and application to blood pressure control in type 2 diabetes.

The aim of this paper is to discuss the use of Bayesian methods in cost-effectiveness analysis (CEA) and the common ground between Bayesian and traditional frequentist approaches. A further aim is to explore the use of the net benefit statistic and its advantages over the incremental cost-effectiveness ratio (ICER) statistic. In particular, the use of cost-effectiveness acceptability curves is examined as a device for presenting the implications of uncertainty in a CEA to decision makers. Although it is argued that the interpretation of such curves as the probability that an intervention is cost-effective given the data requires a Bayesian approach, this should generate no misgivings for the frequentist. Furthermore, cost-effectiveness acceptability curves estimated using the net benefit statistic are exactly equivalent to those estimated from an appropriate analysis of ICERs on the cost-effectiveness plane. The principles examined in this paper are illustrated by application to the cost-effectiveness of blood pressure control in the U.K. Prospective Diabetes Study (UKPDS 40). Due to a lack of good-quality prior information on the cost and effectiveness of blood pressure control in diabetes, a Bayesian analysis assuming an uninformative prior is argued to be most appropriate. This generates exactly the same cost-effectiveness results as a standard frequentist analysis.

The death of cost-minimization analysis?

Four different types of evaluation methods, cost-benefit analysis (CBA), cost-utility analysis (CUA), cost-effectiveness analysis (CEA) and cost-minimization analysis (CMA), are usually distinguished. In this note, we pronounce the (near) death of CMA by showing the rare circumstances under which CMA is an appropriate method of analysis. We argue that it is inappropriate for separate and sequential hypothesis tests on differences in effects and costs to determine whether incremental cost-effectiveness (or cost-utility) should be estimated. We further argue that the analytic focus should be on the estimation of the joint density of cost and effect differences, the quantification of uncertainty surrounding the incremental cost-effectiveness ratio and the presentation of such data as cost-effectiveness acceptability curves. Two examples from recently published CEA are employed to illustrate the issues. The first shows a situation where analysts might be tempted (inappropriately) to employ CMA rather than CEA. The second illustrates one of the rare circumstances in which CMA may be justified as a legitimate form of analysis.

Quantifying stochastic uncertainty and presenting results of cost-effectiveness analyses.

In the last decade, major advances have been made in the statistical methods for quantifying uncertainty in stochastic cost-effectiveness studies. In this paper, we provide a guide to the literature in which we highlight the preferred methods for confidence interval estimation, new developments in the formulation of the cost-effectiveness problem, suggested ways for presenting results and the areas in which future research may develop. The overall approach taken is nontechnical, with an emphasis on graphical rather than algebraic presentation of methods.

Management of urinary tract infection in general practice: a cost-effectiveness analysis.

BACKGROUND: Symptoms associated with urinary tract infection (UTI) are common in women in general practice and represent a significant burden for the National Health Service. There is considerable variation among general practitioners in the management of patients presenting with these symptoms. AIM: To identify the most appropriate patient management strategy given current information for non-pregnant, adult women presenting in general practice with symptoms of uncomplicated UTI. METHOD: A decision analytic model incorporating a variety of patient management strategies was constructed using available published information and expert opinion. This model was able to provide guidance on current best practice based upon cost-effectiveness (cost per symptom-free day). RESULTS: Empiric treatment was found to be the least costly strategy available. It saved two days of symptoms per episode of UTI at a cost of 14 Pounds. The empiric-and-laboratory strategy involves an incremental cost-effectiveness ratio of 215 Pounds per symptom day averted per episode of UTI. The remaining patient management strategies are never optimal. CONCLUSION: Empiric treatment of patients presenting with symptoms of UTI was found to be cost-effective under a range of assumptions for this patient group. However, recognition of the impact of this strategy upon antibiotic resistance may lead to the dipstick strategy being considered a superior strategy overall.

Handling uncertainty in cost-effectiveness models.

The use of modelling in economic evaluation is widespread, and it most often involves synthesising data from a number of sources. However, even when economic evaluations are conducted alongside clinical trials, some form of modelling is usually essential. The aim of this article is to review the handling of uncertainty in the cost-effectiveness results that are generated by the use of decision-analytic-type modelling. The modelling process is split into a number of stages: (i) a set of methods to be employed in a study are defined, which should include a 'reference case' of agreed methods to enhance the comparability of results; (ii) the clinical and demographic characteristics of the patients the model relates to should be specified as carefully as in any experimental study; and (iii) the data requirements of the model should be estimated using the principles of Bayesian statistics, such that prior distributions are specified for unknown model parameters. Monte Carlo simulation can then be employed to sample from these prior distributions to obtain a distribution of the cost effectiveness of the intervention. Such probabilistic analyses are related to parameter uncertainty. In addition, modelling uncertainty is likely to add a further layer of uncertainty to the results of particular analyses.

Constructing confidence intervals for cost-effectiveness ratios: an evaluation of parametric and non-parametric techniques using Monte Carlo simulation.

The statistic of interest in most health economic evaluations is the incremental cost-effectiveness ratio. Since the variance of a ratio estimator is intractable, the health economics literature has suggested a number of alternative approaches to estimating confidence intervals for the cost-effectiveness ratio. In this paper, Monte Carlo simulation techniques are employed to address the question of which of the proposed methods is most appropriate. By repeatedly sampling from a known distribution and applying the different methods of confidence interval estimation, it is possible to calculate the coverage properties of each method to see if these correspond to the chosen confidence level. As the results of a single Monte Carlo experiment would be valid only for that particular set of circumstances, a series of experiments was conducted in order to examine the performance of the different methods under a variety of conditions relating to the sample size, the coefficient of variation of the numerator and denominator of the ratio, and the covariance between costs and effects in the underlying data. Response surface analysis was used to analyse the results and substantial differences between the different methods of confidence interval estimation were identified. The methods, both parametric and non-parametric, which assume a normal sampling distribution performed poorly, as did the approach based on simply combining the separate intervals on costs and effects. The choice of method for confidence interval estimation can lead to large differences in the estimated confidence limits for cost-effectiveness ratios. The importance of such differences is an empirical question and will depend to a large extent on the role of hypothesis testing in economic appraisal. However, where it is suspected that the sampling distribution is skewed, normal approximation methods produce particularly poor results and should be avoided.