Erdmann, S., Edelmann, D., & Kieser, M. (2022). Using Real World Data to Predict Health Outcomes - The Prediction Design. Biometrical Journal (under revision).
Summary
External data is used to predict the outcome of patients of a single-arm study investigating the new treatment. Then, the predicted outcomes (i.e. the synthetic controls) are compared to the “real” outcomes of the patients under the new experimental treatment in order to calculate the treatment effect.
Calculated sample size:
Click on “Calculate sample size” to see the result. For a description of the input parameters see the “notation” tab.
Calculated sample size:
Number of patients n1,n1s,n1RCT needed to detect efficacy with a power of p and significance level α for an assumed treatment effect of Δ (for n0 under the assumptions made) when applying the prediction design, performing a single-arm trial* or an RCT*, as well as factor fs=n1/n1s,fRCT=n1/n1RCT representing the fraction of sample size n1 needed compared to conducting a single-arm trial or an RCT, respectively:
* For comparison of results, the sample sizes are calculated for a
-
single-arm study, where the sample size planning is based on one-sample t-test with one-sided significance level α/2, power 1-β and effect size ∆
-
new RCT, where the sample size planning is based on two-sample t-test with one-sided significance level α/2, power 1-β and assumed effect size ∆
by using the pwr package (Champely, 2020). Results are comparable for σ12=σ12=1 only.
References
Chang, W., Cheng, J., Allaire, J., Sievert, C., Schloerke, B., Xie, Y., Allen, J., McPherson, J., Dipert, A., and Borges, B. (2021). shiny: Web Application Framework for R. R package version 1.7.1. https://CRAN.R-project.org/package=shiny
Champely, S. (2020). pwr: Basic Functions for Power Analysis. R package version 1.3-0. https://CRAN.R-project.org/package=pwr
Griffiths, W. E., Judge, G. G., Hill, R. C., Lütkepohl, H., & Lee, T.-C. (1985). The theory and practice of econometrics: Wiley.
Maintainer
Stella Erdmann, Institute of Medical Biometry, University of Heidelberg, email: erdmann@imbi.uni-heidelberg.de.
Beta version 0.2
R version 4.0.3 (2020-10-10) – “Bunny-Wunnies Freak Out” Copyright (C) 2020 The R Foundation for Statistical Computing Platform: x86_64-w64-mingw32/x64 (64-bit)
Simulation results:
Click on “Start simulation” to see the simulation results. For a description of the input parameters see the “notation” tab.
Simulation results:
Boxplots and mean of sample sizes n1=(n11, …,n1K), type I errors α1=(α11, …,α1K) and type II errors β1=(β11, …,β1K) (indicated by black, grey and blue cross) calculated based on K historical data sets of size n0 and B single-arm trial data sets of size n1k each for Δ, a power of p = 1 - β (β indicated by blue dotted line) and significance level α (indicated by grey dotted line).
References
Chang, W., Cheng, J., Allaire, J., Sievert, C., Schloerke, B., Xie, Y., Allen, J., McPherson, J., Dipert, A., and Borges, B. (2021). shiny: Web Application Framework for R. R package version 1.7.1. https://CRAN.R-project.org/package=shiny
Champely, S. (2020). pwr: Basic Functions for Power Analysis. R package version 1.3-0. https://CRAN.R-project.org/package=pwr
Griffiths, W. E., Judge, G. G., Hill, R. C., Lütkepohl, H., & Lee, T.-C. (1985). The theory and practice of econometrics: Wiley.
Maintainer
Stella Erdmann, Institute of Medical Biometry, University of Heidelberg, email: erdmann@imbi.uni-heidelberg.de.
Beta version 0.2
R version 4.0.3 (2020-10-10) – “Bunny-Wunnies Freak Out” Copyright (C) 2020 The R Foundation for Statistical Computing Platform: x86_64-w64-mingw32/x64 (64-bit)
References
Chang, W., Cheng, J., Allaire, J., Sievert, C., Schloerke, B., Xie, Y., Allen, J., McPherson, J., Dipert, A., and Borges, B. (2021). shiny: Web Application Framework for R. R package version 1.7.1. https://CRAN.R-project.org/package=shiny
Champely, S. (2020). pwr: Basic Functions for Power Analysis. R package version 1.3-0. https://CRAN.R-project.org/package=pwr
Griffiths, W. E., Judge, G. G., Hill, R. C., Lütkepohl, H., & Lee, T.-C. (1985). The theory and practice of econometrics: Wiley.
Maintainer
Stella Erdmann, Institute of Medical Biometry, University of Heidelberg, email: erdmann@imbi.uni-heidelberg.de.
Beta version 0.2
R version 4.0.3 (2020-10-10) – “Bunny-Wunnies Freak Out” Copyright (C) 2020 The R Foundation for Statistical Computing Platform: x86_64-w64-mingw32/x64 (64-bit)