This preview shows pages 1–3. Sign up to view the full content.
1
BME 423 Lecture Notes
 Oct. 7, 2009
II. Types of Error in Inferences and
Power of a Statistical Test
A. The Idea
B. Two Types of Errors
C. What Determines a Test’s Power
1.
Size of Type I Error
2.
Size of Treatment Effect
Glantz
p 179204
A. Trial Types
B. Relative Risk
C. Odds Ratio
I. Association Between Nominal Variables 
Review
Glantz
p 163170
I. Association Between Nominal Variables
Clinical Trials
Patients are randomized to treatment groups and then
the outcome is observed. Studies are prospective.
e.g.,
treatment groups: aspirin vs. placebo
observed outcome: thrombosis/no thrombosis
A. Clinical Trials vs Epidemiological Studies
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document2
Epidemiological Studies
Group is determined by exposure to risk factor.
1) Prospective (cohort
) – Enrolled in study then followed over time to
determine outcome.
2) Retrospective (casecontrol
) – People who have the outcome are
identified/enrolled. Similarly, controls
who do not have the outcome are
identified/enrolled.
This is the end of the preview. Sign up
to
access the rest of the document.
 '06
 D'Argenio
 Biomedical Engineering

Click to edit the document details