Professional Documents
Culture Documents
Test statistics
To test the null hypothesis we need to quantify the strength
of the evidence against it
This is done using test statistics
when the test statistic is larger, there is more evidence against the
null hypothesis
Greek
Mean 4.0
SD 0.4
750
Mean 4.5
SD 0.8
500
250
Small sample
size (N = 5)
Large
sample size
(N = 12)
Mean
SD
SE
Mean
SD
SE
4.1
0.5
0.23
3.9
0.1
0.06
4.9
0.6
0.29
4.4
0.5
0.21
5.2
1.1
0.49
3.7
0.3
0.13
4.1
0.8
0.23
4.1
0.2
0.07
4.6
0.6
0.18
3.9
0.4
0.10
4.7
0.5
0.15
3.8
0.3
0.10
Small sample
size (N = 5)
Large
sample size
(N = 12)
Mean
SD
SE
Mean
SD
SE
4.1
0.5
0.23
3.9
0.1
0.06
4.9
0.6
0.29
4.4
0.5
0.21
5.2
1.1
0.49
3.7
0.3
0.13
4.1
0.8
0.23
4.1
0.2
0.07
4.6
0.6
0.18
3.9
0.4
0.10
4.7
0.5
0.15
3.8
0.3
0.10
SE =
1
N1
1
N2
0.506 Kg = 0.8
1
5
1
5
SD
SE
4.1
0.5
0.23
4.9
0.6
0.29
5.2
1.1
0.49
3.6
0.7
0.30
0.5
Z =
0.8
1
5
Z = 0.99
1
5
The SE
formula
From Z back to Kg
So, 16.1% of differences between pairs of
samples of N=5 drawn from the population of UK
cats will be 0.5Kg or larger
This is the same as saying the probability of a
single comparison producing a difference of 0.5Kg
or greater is 16.1%
SE =
SD12 SD22
+
N1
N2
SD
SE
4.1
0.5
0.23
4.9
0.6
0.29
5.2
1.1
0.49
3.6
0.7
0.30
0.5
Z =
0.52
5
1.29 =
0.72
+
5
0.5
0.38
Small sample
size (N = 5)
Large
sample size
(N = 12)
Mean
SD
SE
Mean
SD
SE
4.1
0.5
0.23
3.9
0.1
0.06
4.9
0.6
0.29
4.4
0.5
0.21
5.2
1.1
0.49
3.7
0.3
0.13
4.1
0.8
0.23
4.1
0.2
0.07
4.6
0.6
0.18
3.9
0.4
0.10
4.7
0.5
0.15
3.8
0.3
0.10
Z =
4.1 3.7
0.52
5
1.53 =
0.32
+
5
0.4
0.26
Z =
4.6 4.1
0.62
12
2.73 =
0.22
+
12
0.5
0.18
Important caveat
What I have described today is called a Z test
But, the formula for estimating the SE of the difference
between 2 means used in the Z test is only accurate when
the individual sample sizes are 30 or more
This is because the estimate of the population SD is not accurate
test statistic