Академический Документы
Профессиональный Документы
Культура Документы
Treatments Treatments
are equal differ
Decision (HO true) (HA true)
Based on Do Not O.K. Type II error
the Data Reject HO β
• increases? Power ↑
• decreases? Power ↓
• N increases? Power ↑
• variability increases? Power ↓
• POWER:
If a limited pool of subjects is available, what is the
likelihood of finding a statistically significant effect of
a given magnitude if one truly exists?
Before We Can Determine Sample Size We Need
To Answer The Following:
H 0: 1 = 2 vs. HA : 1 2
Some Basic Sample Size Formulas
1. level
2. level (1 – power)
3. Expected population proportions (p1, p2)
Some Basic Sample Size Formulas
1. level
2. level (1 – power)
3. Expected population difference (= |1 - 2|)
4. Expected population standard deviation (1 , 2)
The Standard Normal Distribution
N(0,1)
0 z1-
N(0,1) refers to standard normal (mean 0 and variance 1)
prob[N(0,1) > z1-/2 ] = /2 prob[N(0,1) > z1- ] =
Dichotomous Outcome (2 Independent Samples)
• Test H0: p1 = p2 vs. HA: p1 p2
• Assuming two-sided alternative and equal allocation
2
z1-/2 2 pq z1 p1q1 p2 q2
n per / group
n z1 / 2 2 pq
Power
p1q1 p2 q2
n per / group
2
1 2
2 z
1 / 2 z1
2
2
Continuous Outcome
(2 Independent Samples)
n
Power z1 / 2
12 22
• = 1 - 2 = 10 mg/dl
• 1= 2 = (50 mg/dl)
• z1-/2 = 1.96 z1- = 1.28
• n per group = 525
• Suppose 10% loss to follow-up expected,
adjust n = 525 / 0.9 = 584 per group
• These two basic formulas address common settings
but are often inappropriate
• Note: Only the basics of sample size are covered here. It’s
always a good idea to consult a statistician