Stats Psyc RV 2018 Spring

Statistics!!!
{ The meanest part of AP Psychology

 Hindsight Bias – the tendency to believe after
learning an outcome, that we could have
foreseen the it
 We have a tendency to perceive patterns in

random events
 Judgmental overconfidence – We think we’re

right so much more often than we are
What’s wrong with

common sense?
{ Qualitative { Quantitative
 People are seen as  It’s concise, accurate and
individuals and this can be strictly controlled to
method allows ensure that the results are
researchers to gather replicable and causation is
subjective experiences of
an event. demonstrated.
 Quantitative data also has
 This can provide a unique
insider view of the predictive power --
research question research can be generalised
 This approach is less  It can also be a lot faster
structured than a and easier to analyse than
quantitative approach so qualitative data.
unexpected results and
insights can occur.
 Qualitative research gathers information that
is not in numerical form
 diary entries, open-ended responses, unstructured
interviews and unstructured observations).
 Qualitative data is typically descriptive data and
is harder to analyze than quantitative data.
 Quantitative data is in numerical form which

can be put into categories, or in rank order,
or calculated in units of measurement.
 Quantitative data limits participant responses but
is easier to measure and calculate
 A demand characteristic is a subtle cue that makes
participants aware of what the experimenter
expects to find or how participants are expected to
behave
 Demand characteristics can change the outcome of an
experiment because participants will often alter
their behavior to conform to the experimenters
expectations.
Demand characteristics
 Are variables that are  Investigating the effect of
irrelevant to the cognitive behavioural
hypothesis being tested therapy?
that can alter our  Control for exercise
conclusions
 Investigating the influence of

video games on aggression?
 Control the temperature
Confounding Variables
 This is a graphic
representation of the
relationship between
the two variables
 The slope indicates the
direction (+) or (-)
 The amount of scatter
shows the strength of
the correlation
Scatterplot & Correlation

 Descriptive Statistics
 Organizes data meaningfully
 Includes calculating central tendencies and measures of variation
Descriptive Statistics
Dealing with Data: Central
Tendency
 Central Tendency is a way of capturing scores that are
representative of a set of scores (distribution)
 Mean
 Median
 Mode
Central Tendency: The
Mean
 What most people mean by “average”
 Sum of a set of numbers divided by the number of numbers in

the set
1 2 3 4 5  6 7 8  910 55
  5.5
10 10
 We denote the mean as
X
X
 X
n

Mean
Mean
 so if X  [1,2, 3,4, 5,6,7, 8, 9,10]
 X /n  5.5
 then
 n = the number of numbers in X (in this

case 10)
 Keep in mind that X is a set of numbers and
n is a single number
Median
 The median is the middle point in a distribution; it
separates the distribution into two equal halves
 if X = [1,2,4,6,9,10,12,14,17]
 then 9 is the median
 if X = [1,2,4,6,9,10,11,12,14,17]
 then 9.5 is the median; i.e., (9+10)/2
 There are ways of dealing with repeated numbers in the centre

of the distribution; e.g., if X = [1,2,4,6,9,10,10,10,10,11,12,14,17]
Mode
 The mode is the most frequently occurring score in a
distribution
 if X = [1,2,4,6,6,6,8,10,12,14,17]
 then 6 is the mode
 This is what you use when your data is not numerical
Two bimodal distributions

 Be aware of outliers – those extreme scores
which skew (distort) the data set!
 Skewed data is asymmetrical and influences
which measure of central tendency should be
used
Skewed data
How do you decide what you
need?
 If your data set is skewed you do NOT want the mean, you
want the median (could use mode but not as common)
 Riley had many projects (all out of 100) and while he
was in many ways a fine student, he was disorganized
and would lose assignments. This meant that he had
zeros when he otherwise would have a good score.
 His teacher was tasked with reporting on his grades and

was perplexed what would be the best way to describe
his progress.
Riley’s bad habits

 Riley’s scores:
 90, 95, 0, 83, 89, 0, 95, 0, 89, 95
 What should his teacher use: the mean, the mode, or the
median?
 Mean: 63.6 Median: 89 Mode: 95

 This is essentially a measure of how much
scores vary around the mean
 The amount of variability impacts our ability
to generalize from the data

 If there is little variation in the date then the
averages are more reliable
 If the scores vary widely, then the averages are less
reliable
Standard Deviation
Standard Deviation
Normal curve
 Inferential statistics are numerical data that
allow us to generalize – we infer from
sample data the probability of something
being true for a population
 Representative samples are better than biased
samples
 Less variable observations are more reliable than
those that are more variable

 More cases are better than fewer
Inferential Statistics
 Statistical significance
 The likelihood that a result or relationship is
caused by something other than mere random
chance
 We accept odds of 5 out of 100 that an observed
result is due to chance as the standard
Significance
 We give the WISC to 100 randomly selected pairs of
siblings
Hypothesis: Birth order affects intelligence scores,

specifically older siblings score higher than
younger siblings
 If, in 5 or more of the 100 pairs the younger siblings score as
high or higher than the older, we reject the hypothesis as
false
 If, on the other hand, the older siblings scored higher than
the younger siblings 98 times out of 100, then that would be
significant
Statistical significance is
not the same thing as
importance
A test is more than meets
the eye
Victor Benassi gave his college  Weeks later on the final
psyc students frequent in- exam, the students did
class quizzes. much better on the
material that was self-
Some had questions and testing (75% correct)
answers (review) while others rather than mere review
required students to produce (51% correct)
the answers (self-testing)
An experiment to
remember…

Stats Psyc RV 2018 Spring

Uploaded by

Copyright:

Available Formats

Stats Psyc RV 2018 Spring

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Stats Psyc RV 2018 Spring

Uploaded by

Copyright:

Available Formats

Statistics!!!

{ The meanest part of AP Psychology

 We have a tendency to perceive patterns in

 Judgmental overconfidence – We think we’re

What’s wrong with

is harder to analyze than quantitative data.

 Quantitative data is in numerical form which

 Investigating the influence of

Scatterplot & Correlation

 What most people mean by “average”

 Sum of a set of numbers divided by the number of numbers in

Central Tendency: The

 n = the number of numbers in X (in this

 There are ways of dealing with repeated numbers in the centre

Two bimodal distributions

 His teacher was tasked with reporting on his grades and

Riley’s bad habits

 90, 95, 0, 83, 89, 0, 95, 0, 89, 95

 Mean: 63.6 Median: 89 Mode: 95

to generalize from the data

those that are more variable

result is due to chance as the standard

Hypothesis: Birth order affects intelligence scores,

You might also like