Welcome to Analysis of

Behavioural Data

CHAPTER 6
INSTRUCTOR: NICOLE JENNI
 The Normal Curve
Normal curve
◦ Specific bell-shaped curve that is unimodal,
symmetric, and defined mathematically

Area under the Normal curve

◦ Since this shape is defined by math, you can
determine where a given score sits in
relation to other scores in the distribution
Many variables are
normally distributed in
the population.
 N=4

The Normal Curve

◦ As the sample size increases, the shape of N=30
the distribution becomes more like the
normal curve.
◦ **If the population distribution is normal

N=140
 Standardization using z scores
Standardization
◦ Way to convert individual scores from different normal
distributions to a shared normal distribution with a
known mean, standard deviation, and percentile
◦ Allows comparisons across different ‘units’

z score
◦ Number of standard deviations a particular score is from
the mean
◦ Always has mean of 0 and a standard deviation of 1.0
We can interpret z scores in terms of the
standard deviation

A z score of 1.16 means you scored 1.16 standard

deviations above the mean
A z score of -2.5 means…
The Normal Distribution of Intelligence Scores

Raw scores: 55 70 85 100 115 130 145

Z scores: -3 -2 -1 0 1 2 3

“metric” of Population Mean : μ = 100

this variable Population Standard Deviation : σ = 15
 Estimating z-scores
➢Sign of our z-score represents whether
Subject IQ Scores Z-score
that score falls above or below the mean
1 115 +1
➢Z-scores are in standard deviation units 2 85 -1
3 130 +2
4 70 - 2
𝝁= 100 5 120 + 1.33
𝝈= 15 6 95 - 0.33
Calculate a z-score from a raw-score
◦ Step 1: Subtract the mean of the population from the raw score.

◦ Step 2: Divide by the standard deviation of the population.

z score to raw score formula

Quick practice: Covert an IQ score of 120 to a z-
(𝑋 − 𝜇) score. IQ tests are standardized to have a mean
𝑧= of 100, and a standard deviation of 15.
𝜎
z=(120-100)/15
(𝑋 − 𝑀) z=20/15
𝑧=
𝑠 z=1.33333
Characteristics that make z scores interpretable, useful
1. The mean of a distribution of z scores is always 0
◦ Formula makes “deviation scores” (𝑋 − 𝜇)
𝑧=
2. The standard deviation of a distribution of z scores is 𝜎
always 1
◦ Divides by SD, which puts deviation scores in the “units” of standard
deviation

3. The distribution of z scores is the same shape as its

corresponding set of raw scores
◦ Positive skew, negative skew, bell-shaped
◦ We’re typically going to see and interpret bell-shaped
 Z scores back into raw scores
◦ Step 1: Multiply the z score by the standard deviation of the population.

◦ Step 2: Add the mean of the population to this product.

z score to raw score formula

Quick practice: Covert z-score of z= -1.5 back
into raw score. IQ tests are standardized to have
𝑋 = 𝑧(𝜎) + 𝜇 a mean of 100, and a standard deviation of 15.
X = (-1.5*15) + 100
𝑋 = 𝑧(𝑠) + 𝑀
X = -22.5 + 100
X = 77.5
How can we compare
scores when variables use
different metrics?
EXAMPLE: THE GRADUATE RECORD EXAM (GRE)
HT TPS://PSYCH.UBC.CA/GRADUATE/ADMISSIONS/
The GRE
Verbal Quantitative Analytical Psychology
Reasoning Reasoning Writing Subject

Range: Range: Range:

Range:
130- 130- 200-
0-6
170 170 990

https://www.ets.org/s/gre/pdf/gre_interpreting_scores.pdf
We can use the mean and SD to compare
scores across variables
Verbal Quantitative Analytical Psychology
Reasoning Reasoning Writing Subject
Range: Range: Range: Range:
130-170 130-170 0-6 200-990

μ = 150.24 μ = 153.07 μ = 3.55 μ = 618

σ = 8.44 σ = 9.24 σ = 0.86 σ = 106

https://www.ets.org/s/gre/pdf/gre_interpreting_scores.pdf
If you score 160, 150, 5, 700, did you perform “better”
on verbal, psychology… or analytical?
➢ Need to change the metric of each score so they match, and then we can compare them.
➢ To change the metric, we use both the mean and the standard deviation to create z.

Verbal Quantitative Analytical Psychology

Reasoning Reasoning Writing Subject
Range: 130- Range: 130- Range: Range: 200-
170 170 0-6 990

μ = 150.24 μ = 153.07 μ = 3.55 μ = 618

σ = 8.44 σ = 9.24 σ = 0.86 σ = 106

Let’s practice
Q1. Can we calculate a z score for a nominal
variable?

a. Yes
b. No
c. I have no idea
Q2. Converting a raw score to a z score
Verbal If you scored 160 what is
your z score?
Reasoning
𝑋−𝜇
Range: 130-170 𝑧=
𝜎
A. -1.16
μ = 150.24 B. 1.01
C. 1.16
σ = 8.44 D. 36.76
Q3. Your friend says they got a z score of -2.5.
What is their raw score?
Verbal 𝑋 = 𝑧(𝑠) + 𝑀
Reasoning
A. 171.34
Range: 130-170
B. 129.14
C. -18.10
μ = 150.24
D. -21.10

σ = 8.44
Q4. Which score is most impressive? Why?
B. D.
A. Verbal C. Analytical
Quantitative Psychology
Reasoning Writing
Reasoning Subject
Range: 130-170 Range: 130-170 Range: 0-6 Range: 200-990

μ = 150.24 μ = 153.07 μ = 3.55 μ = 618

σ = 8.44 σ = 9.24 σ = 0.86 σ = 106

score of 160 score of 167 score of 5.5 score of 600

z= z= z= z=
Transforming z-scores to percentiles
Transforming z scores into percentiles
◦ The standard shape of the normal curve allows us to know the approximate
percentages under different parts of the curve.
◦ The shape is known and 100% of the population falls beneath the normal curve.
◦ The percentage of any area under the normal curve can be determined.
The Normal Distribution of Intelligence Scores

To commit to memory:
68% of scores fall within 1 SD of mean
95% of scores fall within 2 SD of mean
A z score maps a raw score onto the standard normal
distribution so we can interpret it. Example z=1.16

68% of people score

within ±1 standard
deviation of the mean.
95% of people score
within ±2 standard
deviation of the mean.

z scores -3 -2 -1 0 1 2 3

1.16
Q5: What percentage of scores fall
between z=-1.00 and z= 2.00

A. 13.5%
B. 48%
C. 81.5%
D. 83.5%

Raw scores: 55 70 85 100 115 130 145

Z scores: -3 -2 -1 0 1 2 3
Q6. What % of scores fall below this score?
A. 97.72%
B. 47.72%
C. 2.28%
D. 2.15%
Q7. What % of scores fall below a z score of 1?
A. 95.44%
B. 84.13%
C. 68.26%
D. 34.13%

z scores -3 -2 -1 0 1 2 3
32
On the test, if you score the mean plus one standard
deviation, your z score = 1, better than 84.13%

*As long as scores are

fairly normally
distributed

z scores -3 -2 -1 0 1 2 3
34
 Practice Problem
You need to do better than 84% of test takers on the GRE to get a
graduate school interview. Your test score is made up of 3
components:
1) Verbal Reasoning (μ = 150 σ = 8)
2) Quantitative Reasoning (μ = 160 σ = 10)
3) Analytical Writing (μ = 5 σ = 2)

Your results came back and you scored a 157 on verbal, 172 on
Quant and a 7.1 on Writing. Did you get a grad school interview?!
A) YES
B) NO
 Normal curve is a frequency distribution….
We know the area under the Normal
curve
◦ Since this shape is defined by math, we can
determine where a given score sits in
relation to other scores in the distribution

We can use this to compare one raw score to a

distribution of other raw scores
 If we randomly sample 1 person from the
population, what is the probability they will
have an IQ score of 115 or higher?
A) 84%
B) 13.5%
C) 2.1%
D) 15.6%
 If we randomly sample 1 person from the
population, what is the probability they will
have an IQ score between 70 and 100?
A) 68%
B) 47.5%
C) 13.5%
D) 15.6%
We can use the Normal Distribution in
different ways
Precise “area under the
curve”

z score z statistic
Compare one sample’s
Compare one raw score to a
mean score to a distribution
distribution of other raw
of other possible sample
scores
mean scores

We work on this calculation and Coming up: Calculating and interpreting

interpretation yesterday for use in hypothesis testing
 Homework
FOR THURSDAY LOOKING AHEAD
oPractice, Practice, Practice!!! o Midterm next Tuesday Feb 6
oThursday: Wrap up Ch 6 oCh 1-6

oReview for MT