BIOL933 Design, Analysis, and

Interpretation of Experiments

Class 1
Aug 29, 2017
BIOL933 Design, Analysis, and
Interpretation of Experiments
ANOVA

h"ps://statswithcats.wordpress.com/2010/08/27/the-right-tool-for-the-job/
http://www.unh.edu/halelab/BIOL933
http://www.unh.edu/halelab/BIOL933/schedule.htm
Student Evaluation
Homeworks (10) 45%
In-class quiz 5% (Sept 14)
First exam 25% (Oct 9)
Second exam 25% (Dec 1)

More details can be found in the online syllabus.

questions?
 The Normal Distribution

of observation
Frequency

Observed value
 The Normal Distribution
of observation
Frequency

µ
Observed value
 1. A purely mathemaDcal enDty.
The Normal Distribution
of observation
Frequency

µ
Observed value
 1. A purely mathemaDcal enDty.
The Normal Distribution
of observation
Frequency

2. A distribuDon of related individuals.

(what we see)

µ
Observed value
 1. A purely mathemaDcal enDty.
The Normal Distribution
of observation
Frequency

2. A distribuDon of related individuals.

(what we see)

µ 3. A distribuDon of errors.
Observed value (what we think underlies
what we see)
 N = 150

∑Y
i =1
i
µ= = 200 g
N

N
2
(Y
∑ i − µ )
σ2 = i =1
= 100g 2
N
 n<N

∑Y
i =1
i
Y = ≅ 200 g
n

n
2
(Y
∑ i − Y )
s2 = i =1
≅ 100 g 2
n −1
261 g 111 g
 261 g 111 g

3,251 g 2 577 g 2
An unusual
individual?
 The Normal Distribution The Standard Normal Curve
N(0,1)

Area = 1
of observation

of observation
σ2 = 1
Frequency

Frequency
µ 0
Observed values (Yi) Normal scores (Zi)
 The Normal Distribution The Standard Normal Curve
N(0,1)

Area = 1
of observation

of observation
σ2 = 1
Frequency

Frequency
µ 0
Observed values (Yi) Normal scores (Zi)

Yi − µ
Zi =
σ
An unusual
individual?
p = 0.20
An unusual sample
mean (n=20)?
 The Normal Distribution The Standard Normal Curve
N(0,1)

Area = 1
of observation

of observation
σ2 = 1
Frequency

Frequency
µ 0
Observed values (Yi) Normal scores (Zi)

Yi − µ
Zi =
σ
 The Normal Distribution The Standard Normal Curve
N(0,1)

Area = 1
of observation

of observation
σ2 = 1
Frequency

Frequency
µ 0
Observed sample means (Yi(n)) Normal scores (Zi(n))

Yi(n) − µ
Zi(n) =
σ Y (n) σ
σ Y (n) =
n
The following six samples of 10 observations each (n = 10)
were randomly drawn from a normally distributed population
with µ = 40 and σ2 = 100:
The following six samples of 10 observations each (n = 10)
were randomly drawn from a normally distributed population
with µ = 40 and σ2 = 100:
The following six samples of 10 observations each (n = 10)
were randomly drawn from a normally distributed population
with µ = 40 and σ2 = 100:
The following six samples of 10 observations each (n = 10)
were randomly drawn from a normally distributed population
with µ = 40 and σ2 = 100:
The following six samples of 10 observations each (n = 10)
were randomly drawn from a normally distributed population
with µ = 40 and σ2 = 100:
The following six samples of 10 observations each (n = 10)
were randomly drawn from a normally distributed population
with µ = 40 and σ2 = 100:

σ 100
σ Y (n) = = = 10 = 3.16
n 10
 The Normal Distribution The Standard Normal Curve
N(0,1)

Area = 1
of observation

of observation
σ2 = 1
Frequency

Frequency
µ 0
Observed sample means (Yi(n)) Normal scores (Zi(n))

Yi(n) − µ
Zi(n) =
σ Y (n) σ
σ Y (n) =
n
p = 0.000065
Normal Probability Plot
Figure 24.2 (page 566)

n=14
77.7, 76.0, 76.9, 74.6, 74.7,
76.5, 74.2, 75.4, 76.0, 76.0,
73.9, 77.4, 76.6, 77.3
Y = 75.943, s = 1.227

1/14 = 0.0714 square units

1/28 = 0.0357 square units

Lower bound of 14th quantile ≈ 1.465

“Expected” Z14 ≈ 1.80
“Expected” Y14 = sZ14 + Y = 78.1516
Observed Y14 = 77.7
Normal Probability Plot
Figure 24.2 (page 566)

n=14
77.7, 76.0, 76.9, 74.6, 74.7,
76.5, 74.2, 75.4, 76.0, 76.0,
73.9, 77.4, 76.6, 77.3
Y = 75.943, s = 1.227

W = 0.9484
(Pr < W) = 0.5092