Abstract
We introduce linear contrasts between treatment group means as a principled way for constructing t-tests and confidence intervals for treatment comparisons. We consider a variety of contrasts, including contrasts for estimating time trends and for finding minimal effective doses. Multiple comparison procedures control the family-wise error rate, and we introduce four commonly used methods by Bonferroni, Tukey, Dunnett, and Scheffé. Finally, we discuss a larger real-life example to demonstrate the use of linear contrasts and highlight the need for careful definition of contrasts to correctly reflect the desired comparisons.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We can do this using a ‘contrast’ \(\mathbf {w}=(1/k,1/k,\dots ,1/k)\), even though its weights do not sum to zero.
- 2.
A small subtlety arises from estimating the contrasts: since all \(t\)-tests are based on the same estimate of the residual variance, the tests are still statistically dependent. The effect is usually so small that we ignore this subtlety in practice.
- 3.
It is plausible that measurements on the same mouse are more similar between timepoints close together than between timepoints further apart, a fact that ANOVA cannot properly capture.
- 4.
If 200 hypotheses seem excessive, consider a simple microarray experiment: here, the difference in expression level is simultaneously tested for thousands of genes.
- 5.
The authors of this study kindly granted permission to use their data. Purely for illustration, we provide some alternative analyses to those in the publication.
References
Abelson, R. P. and D. A. Prentice (1997). “Contrast tests of interaction hypothesis”. In: Psychological Methods 2.4, pp. 315–328.
Benjamini, Y. and Y. Hochberg (1995). “Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing”. In: Journal of the Royal Statistical Society. Series B (Methodological) 57.1, pp. 289–300.
Bretz, F. et al. (2009). “A graphical approach to sequentially rejective multiple test procedures”. In: Statistics in Medicine 28.4, pp. 586–604.
Cox, D. R. (1965). “A remark on multiple comparison methods”. In: Technometrics 7.2, pp. 223–224.
Curran-Everett, D. (2000). “Multiple comparisons: philosophies and illustrations”. In: American Journal of Physiology-Regulatory, Integrative and Comparative Physiology 279, R1–R8.
Dunnett, C. W. (1955). “A multiple comparison procedure for comparing several treatments with a control”. In: Journal of the American Statistical Association 50.272, pp. 1096–1121.
Finney, D. J. (1988). “Was this in your statistics textbook? III. Design and analysis”. In: Experimental Agriculture 24, pp. 421–432.
Lawrence, J. (2019). “Familywise and per-family error rates of multiple comparison procedures”. In: Statistics in Medicine 38.19, pp. 1–13.
Lohasz, C. et al. (2020). “Predicting Metabolism-Related Drug-Drug Interactions Using a Microphysiological Multitissue System”. In: Advanced Biosystems 4.11, pp. 2000079.
Noble, W. S. (2009). “How does multiple testing correction work?” In: Nature Biotechnology 27.12, pp. 1135–1137.
O’Brien, P. C. (1983). “The appropriateness of analysis of variance and multiple-comparison procedures”. In: Biometrics 39.3, pp. 787–788.
Proschan, M. A. and E. H. Brittain (2020). “A primer on strong vs weak control of familywise error rate”. In: Statistics in Medicine 39.9, pp. 1407–1413.
Ruberg, S. J. (1989). “Contrasts for identifying the minimum effective dose”. In: Journal of the American Statistical Association 84.407, pp. 816–822.
Ruberg, S. J. (1995a). “Dose response studies I. Some design considerations”. In: Journal of Biopharmaceutical Statistics 5.1, pp. 1–14.
Ruberg, S. J. (1995b). “Dose response studies II. Analysis and interpretation”. In: Journal of Biopharmaceutical Statistics 5.1, pp. 15–42.
Rupert Jr, G. (2012). Simultaneous statistical inference. Springer Science & Business Media.
Scheffé, H. (1959). The Analysis of Variance. John Wiley & Sons, Inc.
Tukey, J. W. (1949a). “Comparing Individual Means in the Analysis of Variance”. In: Biometrics 5.2, pp. 99–114.
Tukey, J. W. (1991). “The philosophy of multiple comparisons”. In: Statistical Science 6, pp. 100–116.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Kaltenbach, HM. (2021). Comparing Treatment Groups with Linear Contrasts. In: Statistical Design and Analysis of Biological Experiments. Statistics for Biology and Health. Springer, Cham. https://doi.org/10.1007/978-3-030-69641-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-69641-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69640-5
Online ISBN: 978-3-030-69641-2
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)