Semiparametric methods for estimation of a nonlinear exposure‐outcome relationship using instrumental variables with application to Mendelian randomization

Abstract

Mendelian randomization, the use of genetic variants as instrumental variables (IV), can test for and estimate the causal effect of an exposure on an outcome. Most IV methods assume that the function relating the exposure to the expected value of the outcome (the exposure‐outcome relationship) is linear. However, in practice, this assumption may not hold. Indeed, often the primary question of interest is to assess the shape of this relationship. We present two novel IV methods for investigating the shape of the exposure‐outcome relationship: a fractional polynomial method and a piecewise linear method. We divide the population into strata using the exposure distribution, and estimate a causal effect, referred to as a localized average causal effect (LACE), in each stratum of population. The fractional polynomial method performs metaregression on these LACE estimates. The piecewise linear method estimates a continuous piecewise linear function, the gradient of which is the LACE estimate in each stratum. Both methods were demonstrated in a simulation study to estimate the true exposure‐outcome relationship well, particularly when the relationship was a fractional polynomial (for the fractional polynomial method) or was piecewise linear (for the piecewise linear method). The methods were used to investigate the shape of relationship of body mass index with systolic blood pressure and diastolic blood pressure.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 32

1. 1.

   Abecasis G. R., Auton A., Brooks L. D., DePristo M. A., Durbin R. M., Handsaker R. E., … McVean G. A. (2012 ). An integrated map of genetic variation from 1,092 human genomes. Nature, 491(7422), 56–65.

   Not in our library10.1038/nature11632

2. 2.

   Angrist, J., Imbens, G., & Rubin, D. (1996 ). Identification of causal effects using instrumental variables. Journal of the American Statistical Association, 91(434), 444–455.

   Not in our library

3. 3.

   Arellano, M. (2003 ). Advances in economics and econometrics, theory and applications, Eight World Congress (Vol. II, pp. 358–364). Cambridge: Cambridge University Press.

   Not in our library

4. 4.

   Bagnardi, V., Zambon, A., Quatto, P., & Corrao, G. (2004 ). Flexible meta‐regression functions for modeling aggregate dose–response data, with an application to alcohol and mortality. American Journal of Epidemiology, 159(11), 1077–1086.

   Not in our library10.1093/aje/kwh142

5. 5.
   Mendelian Randomization Analysis With Multiple Genetic Variants Using Summarized Data · 2013

   No notice
6. 6.

   Burgess, S., Davies, N. M., & Thompson, S. G. (2014 ). Instrumental variable analysis with a nonlinear exposure–outcome relationship. Epidemiology, 25(6), 877–885.

   Not in our library10.1097/ede.0000000000000161

7. 7.
   Using published data in Mendelian randomization: a blueprint for efficient identification of causal risk factors · 2015

   No notice
8. 8.

   Burgess, S., & Thompson, S. G. (2011 ). Bias in causal estimates from Mendelian randomization studies with weak instruments. Statistics in Medicine, 30(11), 1312–1323.

   Not in our library10.1002/sim.4197

9. 9.
   Use of allele scores as instrumental variables for Mendelian randomization · 2013

   No notice
10. 10.

    Burgess, S., & Thompson, S. G. (2015 ). Mendelian randomization: Methods for using genetic variants in causal estimation. Boca Raton, FL: CRC Press.

    Not in our library

11. 11.

    Carroll, R. J., Ruppert, D., Stefanski, L. A., Crainiceanu, C. M. (2006 ). Measurement error in nonlinear models: A modern perspective. Boca Raton, FL: CRC Press.

    Not in our library

12. 12.

    Didelez, V., & Sheehan, N. (2007 ). Mendelian randomization as an instrumental variable approach to causal inference. Statistical Methods in Medical Research, 16(4), 309–330.

    Not in our library10.1177/0962280206077743

13. 13.

    Ebrahim, S., & Smith, G. D. (2008 ). Mendelian randomization: Can genetic epidemiology help redress the failures of observational epidemiology? Human Genetics, 123(1), 15–33.

    Not in our library10.1007/s00439-007-0448-6

14. 14.

    Flegal, K. M., Kit, B. K., Orpana, H., & Graubard, B. I. (2013 ). Association of all‐cause mortality with overweight and obesity using standard body mass index categories: A systematic review and meta‐analysis. Journal of the American Medical Association, 309(1), 71–82.

    Not in our library10.1001/jama.2012.113905

15. 15.

    Hernán, M. A., & Robins, J. M. (2006 ). Instruments for causal inference: An epidemiologist's dream? Epidemiology, 17(4), 360–372.

    Not in our library10.1097/01.ede.0000222409.00878.37

16. 16.

    Horowitz, J. L. (2011 ). Applied nonparametric instrumental variables estimation. Econometrica, 79(2), 347–394.

    Not in our library

17. 17.

    Hosseini, M., Ataei, N., Aghamohammadi, A., Yousefifard, M., Taslimi, S., Ataei, F. (2010 ). The relation of body mass index and blood pressure in iranian children and adolescents aged 7–18 years old. Iranian Journal of Public Health, 39(4), 126–134.

    Not in our library

18. 18.

    Imbens, G. W., & Angrist, J. D. (1994 ). Identification and estimation of local average treatment effects. Econometrica, 62(2), 467–475.

    Not in our library

19. 19.

    Kaufman, J. S., Asuzu, M. C., Mufunda, J., Forrester T., Wilks, R., Luke, A. … Cooper R. S. (1997 ). Relationship between blood pressure and body mass index in lean populations. Hypertension, 30(6), 1511–1516.

    Not in our library10.1161/01.hyp.30.6.1511

20. 20.

    Keogh, R. H., Strawbridge, A., & White, I. R. (2012 ). Effects of classical exposure measurement error on the shape of exposure–disease associations. Epidemiologic Methods, 1, 13–32.

    Not in our library

21. 21.

    Leblanc, M. É., Croteau, S., Ferland, A., Bussières J., Cloutier L., Hould F. S., … Poirier P. (2013 ). Blood pressure assessment in severe obesity: Validation of a forearm approach. Obesity, 21(12), E533–E541.

    Not in our library10.1002/oby.20458

22. 22.

    Locke A. E., Kahali B., Berndt S. I., Justice A. E., Pers T. H., Day F. R., … Speliotes E. K. (2015 ). Genetic studies of body mass index yield new insights for obesity biology. Nature, 518(7538), 197–206.

    Not in our library10.1038/nature14177

23. 23.

    Newey, W. K., & Powell, J. L. (2003 ). Instrumental variable estimation of nonparametric models. Econometrica, 71(5), 1565–1578.

    Not in our library

24. 24.

    Nielsen, G. A., & Andersen, L. B. (2003 ). The association between high blood pressure, physical fitness, and body mass index in adolescents. Preventive Medicine, 36(2), 229–234.

    Not in our library10.1016/s0091-7435(02)00017-8

25. 25.

    Royston, P., & Altman, D. G. (1994 ). Regression using fractional polynomials of continuous covariates: Parsimonious parametric modelling. Journal of Applied Statistics, 43(3), 429–467.

    Not in our library

26. 26.

    Royston, P., Ambler, G., & Sauerbrei, W. (1999 ). The use of fractional polynomials to model continuous risk variables in epidemiology. International Journal of Epidemiology, 28(5), 964–974.

    Not in our library10.1093/ije/28.5.964

27. 27.

    Silverwood R. J., Holmes M. V., Dale C. E., Lawlor D. A., Whittaker J. C., Smith G. D., … Dudbridge F. (2014 ). Testing for non‐linear causal effects using a binary genotype in a Mendelian randomization study: Application to alcohol and cardiovascular traits. International Journal of Epidemiology, 43(6), 1781–1790.

    Not in our library10.1093/ije/dyu187

28. 28.

    Small, D. S. (2014 ). Commentary: Interpretation and sensitivity analysis for the localized average causal effect curve. Epidemiology, 25(6), 886–888.

    Not in our library10.1097/ede.0000000000000187

29. 29.
    UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age · 2015

    No notice
30. 30.

    Thomas, D., Lawlor, D., & Thompson, J. (2007 ). Re: Estimation of bias in nongenetic observational studies using “Mendelian triangulation” by Bautista et al. Annals of Epidemiology, 17(7), 511–513.

    Not in our library10.1016/j.annepidem.2006.12.005

31. 31.

    Thompson, S. G., & Sharp, S. J. (1999 ). Explaining heterogeneity in meta‐analysis: a comparison of methods. Statistics in Medicine, 18(20), 2693–2708.

    Not in our library10.1002/(sici)1097-0258(19991030)18:20<2693::aid-sim235>3.0.co;2-v

32. 32.

    Yau, L. H., & Little, R. J. (2001 ). Inference for the complier‐average causal effect from longitudinal data subject to noncompliance and missing data, with application to a job training assessment for the unemployed. Journal of the American Statistical Association, 96(456), 1232–1244.

    Not in our library

Cited by papers we hold 10

• Using genetic association data to guide drug discovery and development: Review of methods and applications · 2023
  No notice
• Surrogate Adiposity Markers and Mortality · 2023
  No notice
• Association of Habitual Alcohol Intake With Risk of Cardiovascular Disease · 2022
  No notice
• C-reactive protein and cancer risk: a pan-cancer study of prospective cohort and Mendelian randomization analysis · 2022
  No notice
• Obesity and risk of female reproductive conditions: A Mendelian randomisation study · 2022
  Corrected
• Mendelian randomisation for mediation analysis: current methods and challenges for implementation · 2021
  No notice
• Use of genetic variation to separate the effects of early and later life adiposity on disease risk: mendelian randomisation study · 2020
  No notice
• No causal effects of serum urate levels on the risk of chronic kidney disease: A Mendelian randomization study · 2019
  No notice
• Body mass index and all cause mortality in HUNT and UK Biobank studies: linear and non-linear mendelian randomisation analyses · 2019
  No notice
• The relationship between sleep duration, cognition and dementia: a Mendelian randomization study · 2019
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.