Decision-analytic models (DAMs) used to evaluate the cost effectiveness of interventions are pivotal sources of evidence used in economic evaluations. Parameter estimates used in the DAMs are often based on the results of a regression analysis, but there is little guidance relating to these. This study had two objectives. The first was to identify the frequency of use of regression models in economic evaluations, the parameters they inform, and the amount of information reported to describe and support the analyses. The second objective was to provide guidance to improve practice in this area, based on the review. The review concentrated on a random sample of economic evaluations submitted to the UK National Institute for Health and Clinical Excellence (NICE) as part of its technology appraisal process. Based on these findings, recommendations for good practice were drafted, together with a checklist for critiquing reporting standards in this area. Based on the results of this review, statistical regression models are in widespread use in DAMs used to support economic evaluations, yet reporting of basic information, such as the sample size used and measures of uncertainty, is limited. Recommendations were formed about how reporting standards could be improved to better meet the needs of decision makers. These recommendations are summarised in a checklist, which may be used by both those conducting regression analyses and those critiquing them, to identify what should be reported when using the results of a regression analysis within a DAM.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
National Institute for Health and Clinical Excellence. Published technology appraisals. http://www.nice.org.uk/Guidance/TA/Published. 16 Oct 2012.
Kearns B, Ara R, Waillo A. NICE Decision Support Unit: regression methods. http://www.nicedsu.org.uk/Regression-methods(2391678).htm. 1-8-2013.
Cox DR, Snell EJ. Applied statistics: principles and examples. London: Chapman & Hall; 1981.
Chatfield C. The initial examination of data. J R Stat Soc A. 1985;148(3):214–53.
National Institute for Health and Clinical Excellence. Guide to the methods of technology appraisal (updated June 2008). 2008.
Freeman JV, Walters SJ, Campbell MJ. How to display data. Oxford: BMJ Books; 2008.
Few S. Show me the numbers. California: Analytics Press; 2004.
Altman DG. Statistics and ethics in medical research. VI: presentation of results. Br Med J. 1980;281(6254):1542–4.
Hand DJ. Statistics and data mining: intersecting disciplines. ACM SIGKDD Explor Newslett. 1999;1(1):16–9.
Good P, Hardin J. Common mistakes in statistics (and how to avoid them). New Jersey: Wiley; 2003.
Harrell FE, Lee KL, Mark DB. Tutorial in biostatistics multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat Med. 1996;15:361–87.
Royston P, Suaerbrei W. Multivariable model-building: a pragmatic approach to regression analysis based on fractional polynomials for modelling continuous variables. Chichester: Wiley; 2008.
Little RJA, Rubin DB. Statistical analysis with missing data. 2nd ed. New York: Wiley; 2002.
Briggs A, Clark T, Wolstenholme J, Clarke P. Missing … presumed at random: cost-analysis of incomplete data. Health Econ. 2003;12(5):377–92.
Briggs AH, Weinstein MC, Fenwick EA, Karnon J, Sculpher MJ, Paltiel AD. Model parameter estimation and uncertainty analysis a report of the ISPOR-SMDM modeling good research practices task force working group-6. Med Decision Mak. 2012;32(5):722–32.
Campbell MJ. Statistics at square two: understanding modern statistical applications in medicine. Oxford: BMJ Books; 2006
Cooper NJ, Sutton AJ, Mugford M, Abrams KR. Use of Bayesian Markov Chain Monte Carlo methods to model cost-of-illness data. Med Decision Mak. 2003;23(1):38–53.
Tufte E. Improving data analysis in political science. World Politics. 1969;21(4):641–54.
Machin D, Campbell MJ, Walters SJ. Medical statistics. 4th ed. Chichester: Wiley; 2007.
Ara R, Brazier J. Predicting the short form-6D preference-based index using the eight mean short form-36 health dimension scores: estimating preference-based health-related utilities when patient level data are not available. Value Health. 2009;12(2):346–53.
Sullivan PW, Ghushchyan V. Preference-based EQ-5D index scores for chronic conditions in the United States. Med Decis Making. 2006;26(4):410–20.
Sullivan PW, Slejko JF, Sculpher MJ, Ghushchyan V. Catalogue of EQ-5D scores for the United Kingdom. Med Decis Making. 2011;31(6):800–4.
Dobrez D, Cella D, Pickard AS, Lai JS, Nickolov A. Estimation of patient preference-based utility weights from the functional assessment of cancer therapy-general. Value Health. 2007;10(4):266–72.
Briggs A, Sculpher M, Claxton K. Decision modelling for health economic evaluation. Oxford: Oxford University Press; 2006.
Stevenson M, Tappenden P, Squires H. Methods for handling uncertainty within pharmaceutical funding decisions. Int J Syst Sci 2012. Available from: http://www.tandfonline.com/doi/abs/10.1080/00207721.2012.723056?journalcode=tsys20#.ubqbazqn0cB
Strong M, Oakley JE, Chilcott J. Managing structural uncertainty in health economic decision models: a discrepancy approach. J R Stat Soc Ser C. 2012;61(1):25–45.
Husereau D, Drummond D, Petrou S, Carswell C, Moher D, Greenberg D, et al. Consolidated health economic evaluation reporting standards (CHEERS) statement. Pharmacoeconomics. 2013;31(5):361–7.
This article is based on a report that was funded by NICE through its Decision Support Unit. The views, and any errors or omissions, expressed in this article are of the authors only.
BK drafted the manuscript and takes responsibility as the overall guarantor of the content. BK, RA and AW conceived and planned the work. All authors contributed to drafting the checklist and revising the manuscript for important intellectual content. All authors have given their approval for the final version to be published.
The authors acknowledge Paul Tappenden, who contributed to the work, but did not meet the criteria for authorship.
AM is a member of the technology appraisal committee at NICE. BK, RA, AW, MHA, KA and MC have no other potential conflicts of interest. AM’s contribution was made under the terms of a Career Development research training fellowship issued by the National Institute for Health Research (NIHR; grant CDF-2009-02-21). The views expressed in this publication are those of the authors and not necessarily those of the National Health Service, The NIHR or the Department of Health.
Proposed Checklist for Statistical Regression Analyses
Have the objectives of the analysis been stated?
Has the need for a de novo regression analysis been justified?
Has the source of the data used been stated? This would include synopses of key study features such as socio-demographic/clinical characteristics and the data collection method.
Has the total sample size available been reported?
Are sufficient explanations of all variables used provided?
Are sufficient numerical and/or graphical summaries provided?
Has the quality of data (missing values, outliers, possible bias, etc.) been described?
Has the type/method of regression model(s) considered been stated/justified?
Have any modelling assumptions been stated?
Is a convincing rationale given for the inclusion of explanatory variables?
Arriving at the Final Model
Are sufficient details about the computational methods used provided?
If more than one model was considered, has justification been given for why the preferred model has been selected?
Has the choice of covariates been justified?
Is the sample size reported for every model presented?
Has the handling of missing values (if any) been described?
Presentation of the Final Model
Are the coefficient estimates provided?
Are appropriate measures of uncertainty and significance provided?
Validating the Final Model
Are summary measures of goodness of fit presented?
Are details of the results of a residual analysis provided?
Has the model been validated on external (or quasi-external) data?
Is the plausibility of the modelled predictions and/or coefficients discussed?
Are the results compared to the literature and/or other data?
Acknowledging and Propagating Uncertainty in the Analysis
Has the method for handling parameter uncertainty been reported?
Is sufficient detail given for how parameter uncertainty was handled (e.g. if a variance–covariance matrix is used, is this available in some form?)
Is parameter uncertainty appropriately reflected in the DAM?
Has any structural (model) uncertainty been explored (in the DAM)?
Have the model’s limitations been discussed (and explored if possible)?
About this article
Cite this article
Kearns, B., Ara, R., Wailoo, A. et al. Good Practice Guidelines for the use of Statistical Regression Models in Economic Evaluations. PharmacoEconomics 31, 643–652 (2013). https://doi.org/10.1007/s40273-013-0069-y
- Economic Evaluation
- Technology Appraisal
- Statistical Regression Model
- Single Technology Appraisal
- Final Statistical Model