A simulated study of historical controls using real data

Biometrics. 1981 Mar;37(1):169-76.

Abstract

Data from the first and second National Wilms' Tumor study were used to simulate how use of the first study's historical controls in the design and analysis of the second study might have influenced the conclusions of the investigations. It was seen that the conclusions from a fully-randomized study can differ in substances from one using historical controls.

Publication types

  • Comparative Study
  • Research Support, U.S. Gov't, P.H.S.

MeSH terms

  • Clinical Trials as Topic / methods*
  • Data Collection
  • Double-Blind Method
  • Humans
  • Models, Biological
  • Research Design
  • United States
  • Wilms Tumor / drug therapy
  • Wilms Tumor / history*