1. Complete the procedure
of your observation in
your observation folder.
• Where did you do it?
• When did you do it?
• What did you do? (start
with creating the coding
scheme)
• Who did you do it to?
For full marks on a
procedure the person
reading it should be able to
replicate what you did
without asking you any
questions.
Have you missed anything?
2. Lesson Objectives
By the end of the lesson you …
• Must be able to describe (AO1) the
observational method and its components.
• Must be able to evaluate (AO2) you
observation.
• Should be able to identify different data types
(nominal, ordinal and interval/ratio).
Pg 6-8
4. Descriptive vs. Inferential
Descriptive Statistics
• Summary of data to illustrate patterns and
relationships – BUT can’t infer conclusions
Inferential Statistics
• Statistical tests that allow us to make
conclusions in relation to our hypothesis.
eg. Mann-Whitney or Spearman’s Rho or
Chi Square.
5. DESCRIPTIVE Data Analysis
y axis label
y axis label
Scattergram to show the
Correlation between variable
1 and variable 2
x axis label
4.5
4
3.5
3
2.5
2
1.5
1
0.5
0
0
2
4
x axis label
Titles are VERY important. Title your axis, the
integers and give the graph a title.
6
8. Categorical
Nominal - measure of central tendency: mode
Data in categories (finished, fell, started)
Continuous
Levels of Data
Interval / Ratio - measure of central tendency:
mean
Precise and measured using units of equal
intervals (1m54s, 1m59s, 2m03s)
Ordinal - measure of central tendency: median
Data which are ranked or in order (1st 2nd 3rd)
Ratio has a definite and meaningful zero point
10. NOMINAL
DATA
ORDINAL
DATA
INTERVAL
DATA
REPEATED
MEASURES
Sign test
Wilcoxon sign test
Related t
test*
MATCHED
PAIRS
Sign test
Wilcoxon sign test
Related t
test*
INDEPENDENT
MEASURES
Chi-squared
Mann-Whitney
'U'
Unrelated t
test*
CORRELATION
Chi-squared
Spearman
Rho
Pearson
moment*
TYPE
DESIGN
* For Parametric tests Parametric criteria must also be met.
11. NOMINAL
DATA
ORDINAL
DATA
INTERVAL
DATA
REPEATED
MEASURES
Sign test
Wilcoxon sign test
Related t
test*
MATCHED
PAIRS
Sign test
Wilcoxon sign test
Related t
test*
INDEPENDENT
MEASURES
Chi-squared
Mann-Whitney
'U'
Unrelated t
test*
CORRELATION
Chi-squared
Spearman
Rho
Pearson
moment*
TYPE
DESIGN
* For Parametric tests Parametric criteria must also be met.
12. An inferential statistical test allows us to make conclusions in relation to our
hypothesis. We choose the appropriate statistical test based on the level of
data that we have collected and the design of the experiment.
When you conduct an inferential statistical test you will always end up with
three values.
• Calculated (observed) – this number is affected by the scores that you
enter into the calculation and is the important number that you need to
compare to the table value to ascertain if you are to accept or reject your
hypothesis.
• Table (critical) – this number is affected by the number or participants /
number of conditions you have. Your calculated value is compared to this.
• Significance level – how confident are we in the conclusion of the test.
13. • Must be able to describe (AO1) the observational
method and its components.
• Must be able to evaluate (AO2) you observation.
• Should be able to identify different data types
(nominal, ordinal and interval/ratio).
15. Lesson Objectives
By the end of the lesson you …
• Must be able to evaluate (AO2) an
observation.
• Must be able to carry out (AO3) an
observation to collect data.
• Should be able to describe (A01) P values and
describe their impact on conclusions.
17. Steps for testing hypotheses
1. Calculate descriptive
statistics
2. Calculate an inferential
statistic
3. Find its probability (p
value)
4. Based on p
value, accept or reject
the null hypothesis
5. Draw conclusion
<
>
≤
≥
less than
greater than
less than or equal to
greater than or
equal to
18. 1. Proportion of girls categorised as early-maturers: California
versus Arizona, p <0.05
2. Degree of agreement with the statement "All in all, it was
worth going to war in Iraq." Republicans vs.
Democrats, p=0.35
3. Rating of overall liking of movie: Film club members vs. nonclub members p = 0.173
4. Difference in reaction time between those consuming
alcohol and those not, p<0.001
5. Number of lawn signs for candidates: Winner vs.
loser, p=0.025
6. Degree of agreement with the statement "By law, abortion
should never be permitted." Women vs. Men, p > 0.05
GREEN = SIGNIFICANT
RED = NON-SIGNIFICANT
19. … is less than or
equal to …
p ≤ 0.05
The probability that
the results are due
to chance …
… 5%
21. • Must be able to evaluate (AO2) an observation.
• Must be able to carry out (AO3) an observation
to collect data.
• Should be able to describe (A01) P values and
describe their impact on conclusions.