Psych 1000: Introduction to Psychology

After Data Collection

• Null Hypothesis Testing

TRENDS IN THE DATA

• Measures of Central Tendency
• Measures of Variability

THE NORMAL DISTRIBUTION

• Standard scores

• Dr. Laura Fazakas-DeHoog lfazakas@uwo.ca

 SAMPLE EXAM QUESTION
Q: A sample that reflects the characteristics
of the larger population from which it was
drawn is referred to as a ________
sample.

a. representative
b. random
c. stratified
d. balanced
e. reliable
 SAMPLE EXAM QUESTION
Q: Which of the following is the strongest
correlation?

a. +.60
b. - .76
c. 0.0
d. +.13
e. +.49
 STATISTICS
Descriptive Statistics – describes the data set.
I. Measures of Central Tendency
• mean
• mode
• median
II. Measures of Variability
• range
• variance
• standard deviation
Inferential Statistics – tests the hypothesis
to make conclusions.
After Data CollectionData Collection…
Need to Test our hypothesis using Statistics
Another Example:

• Alcohol & Coordination study

• 10 participants randomly divided into 2 groups.
• Record the number of catches for each subject.

No Beer Group 2 Beer Group

5 3
4 2
3 1
3 4
____5 3__
Average 4 2.6
Statistics
These two
values are
clearly
different
BUT…
Is this
difference
meaningful?
AND
4
How big are
2.6 those
differences
no compared to the
2 beer
beer variability in the
data?
After Data Collection… No Beer Group
5
4
2 Beer Group
3
2
3 1
Need to test our hypothesis ____
3
5
4
3________
Average 4 2.6

Null Hypothesis Testing

• Assume there are no differences between groups
– All conditions are the same
• The groups won’t all have the EXACT same #s
– if there are no real differences, how much would they differ just
by chance?
• We use statistics to determine what size of a differce is
likely by chance
– If the differences between our groups is larger than what
we’d expect by chance → we reject the idea that our
conditions are all the same (i.e. reject Null hypothesis)
» Conclude we have real group differences
(i.e. support the alternative hypothesis)
After Data Collection…
Need to test our hypothesis

Hypothesis Testing

no differences DIFFERENCES
between groups between groups

Null Hypothesis Alternate Hypothesis

 N = number of
Looking at Data responses
N= 10

8 11 6 7 5 9 5 9 9 11
HISTOGRAM Score Frequency
11 2
5
4 10 0
3 9 3
2 8 1
1
7 1
6 1
5 6 7 8 9 10 11
5 2
 MEASURES OF CENTRAL TENDANCY

8 11 6 7 5 9 5 9 9 11
Score Frequency
11 2
1. MODE – most 10 0
frequently occurring 3
response
9
8 1
7 1
MODE = 9 6 1
5 2
 Looking at Data

MODE = 9
HISTOGRAM Score Frequency
11 2
5
4
10 0
3 9 3
2 8 1
1
7 1
6 1
5 6 7 8 9 10 11
5 2
 MEASURES OF CENTRAL TENDANCY

2. MEDIAN – the middle response after arranging from

lowest score to highest score

Responses - 8 11 6 7 5 9 5 9 9 11

Arrange Scores 5, 5, 6, 7, 8, 9, 9, 9, 11, 11

If N is an even number
average the 2 middle 8.5
scores
 MEASURES OF CENTRAL TENDANCY

3. MEAN – the average of all scores (can be inflated

or deflated by an outlier)

MEAN = sum of all scores

______________
N

(8 + 11 + 6 + 7 + 5 + 9 + 5 + 9 + 9 + 11)
__________________________________
10
Mean = 8
Variability in the Data ….

MEASURES OF VARIABILITY - provide

information about the spread in
the scores
1. RANGE = highest score subtracted by the lowest score

Our Example: 11 - 5 = 6

RANGE = 6
 Variability in the Data ….

MEASURES OF VARIABILITY
2. VARIANCE – how much, on average, each score varies (or
deviates from the mean)

2
VARIANCE = sum of [(each score - the mean) ]
____________________________
N
 Variability in the Data ….

VARIANCE = [sum of (each score - the mean) 2 ]

____________________________
N

[(8-8)2 +(11-8) 2 + (6-8) 2 + (7-8) 2 + (5-8) 2 + (9-8) 2 + (5-8) 2

+ (9-8) 2 +( 9-8) 2 + (11-8) 2]
_______________________________________________________
10

= (0 + 9 + 4 + 1 + 9 + 1 + 9 + 1 + 1 + 9)/10

= 44/10

VARIANCE = 4.4
Variability in the Data ….

3. STANDARD DEVIATION =square root of the varience

S.D. = VARIANCE

OUR EXAMPLE:

S. D. = 4.4

S. D. = 2 . 098
 The Normal Curve ….

50 X Frequency
55 1.0
70 8.0
40 85 30.0
100 50.0
30 115 30.0
130 8.0
145 1.0
20

10

55 70 85 100 115 130 145

 The Normal Curve ….
Mean = Median = Mode IN A NORMAL DISTRIBUTION, THE MEAN MEDIAN
AND MODE ARE ALWYS EQUAL. 50% ABOVE THE MEDIAN AND 50% BELOW

50 % between mean & - 3 S.D. 50 % between mean

& + 3 S.D

50 % 50 %
 The Normal Curve ….

Higher than about

95.8% falls between
97.9 % of the
-2 S.D. and + 2 S.D.
population

68 %
Application

Did you do better in Biochemistry or Philosophy?

Biochem mark: 60 Philosophy mark: 75

0 10 20 30 40 50 60 70 80 90 100
Scores
 Average Average
Biochem Philosophy

0 10 20 30 40 50 60 70 80 90 100
Scores
Standard Scores
(Score - Mean)
_____________
Z=
Standard Deviation

Allows one to compare different distributions

Did you do better in Biochemistry or Philosophy?
Biochem mark: 60 Philosophy mark: 75
(Mean = 50, SD = 10) (Mean = 69, SD = 12)

Z = (60-50)/10 Z =(75-69)/12

Z = +1 Z = .5
 Normal Curve EXAM
In Philosophy, you did better In Biochemistry, you did better
than approx. 69% of the class than 84% of the class
In Biochemistry, you did
What percent of the class better than (34.1% + 34.1%
Did you do better than? +13.6% + 2.1%) = approx.
84% of the class
To answer this, either:
a) Use the percentile rank
OR
These are called
b) Calculate the percentage
percentile scores
of values under the
curve less than
your grade.
 Ethics
• Research with Humans
• Informed Consent
• Process
• Potential risks
• freedom to withdraw from study without penalty
• Freedom from coercion
• Confidentiality & Anonymity
• Minimize harm/discomfort
• Debriefing
ETHICAL ISSUES
– when should deception be used?
– when should “risky” studies be done?
(usually decided when the benefits outweigh the risks)
 Ethics

Research with Animals

• Only when necessary
• Only when data critical to
helping humans
• Maintain the health of the
animals & animal housing
• humane treatment is essential
 NEXT LECTURE

• The Nervous System

• The Neuron: Structure & Function

Reading: Chapter 3