Statistical considerations for a parallel trial where the outcome is a measurement

Note: The power calculation uses the non-central t function, pt(x,df,ncen), and it's inverse qt
Power=pt(qt(.025,n-2,0),n-2,-(delta/sigma)/sqrt(4/n)), power is truncated rather than rounded.
If power is specified the other parameters are found by searching.

Request

Significance Level — sided (default is 0.05, two-sided)

Standard Deviation of the outcome variable (if known)

Enter two of the following three values and the remaining value will be calculated

  1. Total number of patients
  2. Power (usually 0.8 or 0.9)
  3. Minimal detectable difference (specify one of the following):
    1. Difference in means
    2. % Location of the mean of one treatement group in terms of a percentile of the other treatment group.

Response (for previous request)

(no request has been submitted)

This software developed by David Schoenfeld, Ph.D. (dschoenfeld@partners.org), with support from the MGH Mallinckrodt General Clinical Research Center. Javascript version developed by REMorse.

These calculations are based on assumptions which may not be true for the clinical trial that you are planning. We do not guarantee the accuracy of these calculations or their suitability for your application. We suggest that you speak to a biostatistical consultant when planning a clinical trial. Please contact us if you have any questions or problems using this software