¥t-Tests [starting easy, but contains most of the ideas]
HProgram 3dttest
åUsed
to test if the mean of a set of values is significantly different from a constant (usually 0) or the mean of another set of values.
HAssumptions
åValues
in each set are normally distributed
åEqual
variance in both sets
åValues
in each set are independent Þ unpaired
t-test
åValues
in each set are dependent Þ paired
t-test
HExample: 20 subjects are tested for the effects of 2 drugs A
and B
åCase
1: 10 subjects were given drug A and the other 10 subjects given drug B.
íUnpaired t-test is used to test: mA = mB? (mean
response is different?)
íEquivalent to one-way ANOVA with between-subjects design of equal
sample size
Þ can also run 3dANOVA (treating subjects as
multiple measurements)
åCase
2: 20 subjects were given both drugs at different times.
íPaired t-test is used to test: mA = mB?
åCase
3: 20 subjects were given drug A.
ít-test is used to test if drug effect is significant at
group level: mA = 0?