Lecture 5 - Sampling Distribution
Lecture 5 - Sampling Distribution
Reading materials:
Chap 9 (Keller)
1 2
10 12 14 16 18 20 22 24 26
Pizza time
600
500
400
Frequency
100
10
300
200
Frequency
Frequency
5 50
100
10 20 30 40
0 0
6 8 10 12 14 16 18 20 22 24 26
Pizza time
10 20 30
Pizza time Pizza time
90
80
80
70 70
60 60
Frequency
Frequency
50 50
40 40
30 30
20 20
10 10
0 0
13 14 15 16 17 18 19 20 21 22 14 15 16 17 18 19 20 21 22 23
average median
7 8
70
80
50
70 60
40 50
Frequency
Frequency
60
30 50 40
40
20 30
30
20
10 20
10 10
0
0 0
average median
stdev
60
becoming more and more symmetric and bell-shaped
50
and less variable, particularly those for the sample
Frequency
40
30
20
mean
• Also notice that the estimated standard deviation of
10
stdev
11 12
A general result of great importance
The Central Limit Theorem (1)
No matter what model a random sample is taken
from, as the sample size (number of random • Whatever the population
observations) increases, the distribution of the dist. looks like (normal
sample mean becomes closer and closer to the or not), when a sample
normal distribution. And size is large enough, the
No matter what model a random sample is taken distribution of sample
from, and for any sample size n, the standard means will be normal and
deviation of the sample mean is the model standard we can use Z-statistic to
deviation, σ , (the theoretical standard deviation) calculate probability of
divided by n , that is, σ / n =>Called standard any mean value
error of the means (SE).
13 14
The Central Limit Theorem (2) This is the Central Limit Theorem
⎛ σ2 ⎞
X → N ⎜ µ, ⎟
⎝ n ⎠
X −µ
Z= → Z ~ N ( 0,1) as n → ∞.
σ n
15 16
So, how large does n need to be? So, how large does n need to be?
• It depends on the original distribution of X.
– If X has a normal distribution, then the sample mean has a
normal distribution for all sample sizes.
– If X has a distribution that is close to normal, the
approximation is good for small sample sizes (e.g. n=20).
– If X has a distribution that is far from normal, the
approximation requires larger sample sizes (e.g. n=50).
17 18
In general Activity 1
19 20