Abstract
There is increasing interest in the use of instrumental variable analysis to overcome unmeasured confounding in observational pharmacoepidemiological studies. This is partly because instrumental variable analyses are potentially less biased than conventional regression analyses. However, instrumental variable analyses are less precise, and regulators and clinicians find it difficult to interpret conflicting evidence from instrumental variable compared with conventional regression analyses. In this paper, we describe three techniques to assess which approach (instrumental variable versus conventional regression analyses) is least biased. These techniques are negative control outcomes, negative control populations and tests of covariate balance. We illustrate these methods using an analysis of the effects of smoking cessation therapies (varenicline) prescribed in primary care.
Original language | English |
---|---|
Pages (from-to) | 2067-2077 |
Number of pages | 11 |
Journal | International Journal of Epidemiology |
Volume | 46 |
Issue number | 6 |
Early online date | 7 Apr 2017 |
DOIs | |
Publication status | Published - 1 Dec 2017 |
Funding
*Corresponding author. Medical Research Council Integrative Epidemiology Unit at the University of Bristol, Oakfield Grove, Bristol BS8 2BN, UK. E-mail: [email protected] This work was supported by the Medical Research Council [MR/ N01006X/1], the National Institute for Health Research (NIHR) Health Technology Assessment (HTA) programme [project number 14/49/94]. The Integrative Epidemiology Unit is supported by the Medical Research Council and the University of Bristol [MC_UU_12013/6, MC_UU_12013/9]. A.E.T., M.R.M. and G.T. are members of the UK Centre for Tobacco and Alcohol Studies, a UKCRC Public Health Research: Centre of Excellence. Funding from the British Heart Foundation, Cancer Research UK, Economic and Social Research Council, Medical Research Council and the National Institute for Health Research, under the auspices of the UK Clinical Research Collaboration, is gratefully acknowledged. K.H.T. is funded by a Clinical Lectureship from the National Institute for Health Research. R.M.M. is supported by Cancer Research UK programme grant [C18281/A19169] (the Integrative Cancer Epidemiology Programme). No funding body has influenced data collection, analysis or its interpretations. The views and opinions expressed therein are those of the authors and do not necessarily reflect those of the HTA programme, NIHR, NHS or the Department of Health. Conflict of interest: M.R.M. reports grants from Pfizer and Rusan, and non-financial support from GlaxoSmithKline, outside the submitted work; A.E.T. reports a grant from the Global Research Awards for Nicotine Dependence which is an Independent Competitive Grants Program supported by Pfizer. R.M.M. was a member of the Independent Scientific Advisory Committee of the Medicines and Healthcare products Regulatory Agency which approves applications for CPRD studies. All other authors report no other relationships or activities that could appear to have influenced the submitted work.
Keywords
- Causal inference
- Instrumental variables
- Negative controls
- Pharmacoepidemiology
ASJC Scopus subject areas
- Epidemiology