Crossover Studies with Continuous Variables: Power Analysis
Abstract
The crossover design is a sensitive means of determining the efficacy of new drugs because it eliminates between-subject variability. However, if the response in the first period carries on into the second (carryover effect) or if time factors cannot be kept constant in a lengthy crossover (time effects), its statistical power may be jeopardized. This may be equally true if a negative correlation exists between treatment responses. We recently demonstrated that the crossover design with binary variables is a powerful method even if correlation between treatment responses is negative. Power analysis of crossover trials with continuous variables has not been explicitly studied. Using the Scheffé model for the assessment of treatment effect, carryover effect, and time effect, we drew power curves of hypothesized crossover studies with different levels of correlation between drug response. We demonstrate that the sensitivity of testing is largely dependent on the levels of correlation between drug response. When positive, we have a great deal of sensitivity with which to test treatment effect and little sensitivity to test carryover or time effect. When negative, the opposite is observed. The correlation level in a crossover comparison is a major determinant of the sensitivity of testing. Treatments from one class with one mode of action frequently have a positive correlation and should be particularly considered for crossover comparisons. With treatment comparisons of totally different classes of drugs/modes of action, the opposite is true. It is hoped that this work affects the design of future crossover trials.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The crossover design was selected to limit inter-subject variability between interventions.
“The crossover design was selected to limit the inter-subject variability between the interventions [46].”
From Acute Effects of Coffee Consumption on Self-Reported Gastrointestinal Symptoms, Blood Pressure and Stress Indices in Healthy Individuals (2015) · cites this paper as [46]
Cites
Scheffé, H. (1960) · Soil Science · doi:10.1097/00010694-196006000-00016 · Cited by 5,625 · see citing works
The Two-Period Change-Over Design and Its Use in Clinical Trials
Grizzle, J. E. (1965) · Biometrics · doi:10.2307/2528104 · Cited by 784 · see citing works
The performance of the two‐stage analysis of two‐treatment, two‐period crossover trials
Freeman, P. R. (1989) · Statistics in Medicine · doi:10.1002/sim.4780081202 · Cited by 270 · see citing works
A critique of recent research on the two-treatment crossover design
Fleiss, J. L. (1989) · Controlled Clinical Trials · doi:10.1016/0197-2456(89)90065-2 · Cited by 164 · see citing works
Carryover and the Two-Period Crossover Clinical Trial
Willan, A. R., & Pater, J. L. (1986) · Biometrics · doi:10.2307/2531209 · Cited by 99 · see citing works
The AB/BA crossover: past, present and future?
Senn, S. J. (1994) · Statistical Methods in Medical Research · doi:10.1177/096228029400300402 · Cited by 63 · see citing works
Bayesian analyses of two-treatment crossover studies
Grieve, A. P. (1994) · Statistical Methods in Medical Research · doi:10.1177/096228029400300406 · Cited by 37 · see citing works
Cleophas, T. J., & de Vogel, E. M. (1998) · Pharmacy World & Science · doi:10.1023/a:1008626002664 · Cited by 30 · see citing works
Self-citationCrossover studies: A modified analysis with more power
Cleophas, T. J. (1993) · Clinical Pharmacology & Therapeutics · doi:10.1038/clpt.1993.64 · Cited by 30 · see citing works
Self-citationMisra, R. K. (1966) · Biometrics · doi:10.2307/2528183 · Cited by 11 · see citing works
Crossover Trials with a Binary Response: A Powerful Method Despite the Carryover Effect
Cleophas, T. J., & van Lier, H. J. J. (1996) · The Journal of Clinical Pharmacology · doi:10.1002/j.1552-4604.1996.tb04188.x · Cited by 10 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
PETRI, N., SVANHOLT, P., SOLOW, B., WILDSCHIØDTZ, G., & WINKEL, P. (2008) · Journal of Sleep Research · doi:10.1111/j.1365-2869.2008.00645.x · Cited by 152 · see citing works
Influence of packaging information on consumer liking of chocolate milk
Myung-joo, K. I. M., Lopetcharat, K., & Drake, M. A. (2013) · Journal of Dairy Science · doi:10.3168/jds.2012-6399 · Cited by 113 · see citing works
Physiological responses to touch massage in healthy volunteers
Lindgren, L., Rundgren, S., Winsö, O., Lehtipalo, S., Wiklund, U., Karlsson, M., Stenlund, H. C., Jacobsson, C., & Brulin, C. (2010) · Autonomic Neuroscience · doi:10.1016/j.autneu.2010.06.011 · Cited by 105 · see citing works
Suh, G., Son, H.-G., Ju, Y., Jcho, K. H., Yeon, B. K., Shin, Y. M., Kee, B. S., & Choi, S. (2004) · American Journal of Geriatric Psychiatry · doi:10.1097/00019442-200409000-00009 · Cited by 70 · see citing works
Papakonstantinou, E., Kechribari, I., Sotirakoglou, Κ., Tarantilis, P., Gourdomichali, T., Michas, G., Kravvariti, V., Voumvourakis, K., & Zampelas, A. (2015) · Nutrition Journal · doi:10.1186/s12937-016-0146-0 · Cited by 59 · see citing works
Papakonstantinou, E., Orfanakos, N., Farajian, P., Kapetanakou, A. E., Makariti, I., Grivokostopoulos, N., Ha, M., & Skandamis, P. N. (2017) · Nutrition · doi:10.1016/j.nut.2017.05.011 · Cited by 55 · see citing works
Argaman, Y., Granovsky, Y., Sprecher, E., Sinai, A., Yarnitsky, D., & Weissman‐Fogel, I. (2021) · Journal of Pain · doi:10.1016/j.jpain.2021.11.001 · Cited by 37 · see citing works
Monastero, R., Baschi, R., Nicoletti, A. S. Q., Pilati, L., Pagano, L., Cicero, C. E., Zappia, M., & Brighina, F. (2020) · Journal of Neural Transmission · doi:10.1007/s00702-020-02255-2 · Cited by 27 · see citing works
Fremont, R., Manoochehri, M., Armstrong, N. M., Mattay, V. S., Apud, J. A., Tierney, M. C., Devanand, D. P., Gazes, Y., Habeck, C. G., Wassermann, E. M., et al. (2020) · Journal of Alzheimer s Disease · doi:10.3233/jad-191265 · Cited by 19 · see citing works
Sasagawa, M., Boclair, M. J., & Amieux, P. S. (2021) · Nutrients · doi:10.3390/nu13082801 · Cited by 6 · see citing works
Boeker, M., Jansen, L., Grewe, N., Röhl, J., Schober, D., Seddig-Raufie, D., & Schulz, S. (2013) · PLoS ONE · doi:10.1371/journal.pone.0061425 · Cited by 6 · see citing works
Varón, J., Fromm, R. E., & Marik, P. E. (2003) · CHEST Journal · doi:10.1016/s0012-3692(15)32556-3
Lara‐Corrales, I. (2009) · TSpace (University of Toronto)
Caspi, O., & Schiff, E. (2003) · CHEST Journal · doi:10.1378/chest.123.4.1312
- Authors
- Cleophas, T. J. M., & Zwinderman, A. H.
- Corresponding author
- Cleophas, T. J.M.
- ORCID
- Zwinderman, A. H.
- Venue
- American Journal of Therapeutics
- Published
- 2002-01
- Volume
- 9
- Issue
- 1
- Pages
- 69-73
- ISSN
- 1075-2765 (ISSN-L)
- OpenAlex
- W2111946500
- Cited by
- 15
- References
- 11
- Citations by year
- 2021: 2 · 2020: 3 · 2017: 1 · 2015: 1 · 2013: 2
- FWCI
- 1.14
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- American Journal of Therapeutics (publishedVersion)
- PubMed (publishedVersion)
- Data Archiving and Networked Services (DANS) (submittedVersion)
- Pure Amsterdam UMC (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Social Sciences › Decision Sciences › Management Science and Operations Research › Optimal Experimental Design Methods
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Keywords
- crossover trial, statistical power, residual effects, time effects, continuous response variables, drug efficacy comparison, trial design
- MeSH terms
- Algorithms, Clinical Trials as Topic, Data Interpretation, Statistical, Humans, Models, Theoretical, Pharmacology, Clinical, Probability, Research Design, Time Factors, Cross-Over Studies
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
