February, 2003
© 2000, 2001, 2003 Scott S. Emerson, M.D., Ph.D.
Hierarchy of Statistical Goals: 6
Use of Probability Model
Summary measure for comparison should most often be driven by scientific issues
·Thresholds may be most important clinically
·Means allow estimates of total costs/benefits
·Medians less sensitive to outliers
-Sometimes clinical importance is not proportional to magnitude of measurements
-However, sometimes effect of intervention is only on outliers