.
The Effect of Groups
.
What is a scatter plot?
When investigating bivariate data making a scatter plot is the
first step.
BEFORE you add any lines or curves to the scatter plot make a visual
interpretation...in context
Is the association linear looking or not?
“There looks to be a linear association between .... and .... (or not)
If there looks like a linear association then you con preceded with applying a
linear model.
(If there is no obvious association you should reconsider your variables) Duh
.
Scatterplots: Introduction
.
What can we describe from a of scatter plot?
Describe
Describe
Describe
Describe
Describe
Describe
the
the
the
the
the
the
Trend. (Linear or non-Linear)
Association. (Positive or Negative)
Strength. (Weak, Moderate, Strong)
Groups or clusters (possible reasons or causes)
Unusual Values (any worth noting)
Scatter (Even or changing)
If the scatter plot indicates a linear model is appropriate then we can proceed.
Discuss what you see in your scatter plots
"from the scatter plot it appears that as (blah) increases then (blah) tends to
increase also. Am I surprised by this? Why am I surprised or not by this (in
context)
"I would expect that measurements of (blah) and (blah) are in proportion"
Booklet p2 (describe scatter plot & variable types, and research Q. Pg3,
4, 5
Investigate the effect of other variables or groups
.
Scatter plots Features
.
What do you DISCUSS in CONTEXT
Trend
Do you see: a linear trend…
Association
Do you see: a positive association…
as one variable gets
bigger, so does the
other
or a non-linear trend?
“This means...
or a negative association?
as one variable gets
bigger, the other gets
smaller
“This means that...
Strength
Do you see: a strong relationship…
little scatter
or a weak relationship?
lots of scatter
“This means that...
.
Scatter plots (Cont)
.
Groups
Do you see any groupings?
“I notice that... This could be due to...
Unusual Values
Do you see any unusual values?
Is the outlier an error or just different?
Do NOT remove unusual values unless they are errors
Could there be a reason for the unusual values?
“I notice that... Maybe this is...
Scatter
Do you see: constant scatter…
or non-constant scatter?
the scatter looks
like a “fan” or
“funnel”
roughly the same amount
of scatter as you look
across the plot
Other Features?
Context...
“I notice that... This could be due to...
Context...
Context...
What do I see in these scatter plots?
Mean January Air Temperatures
for 30 New Zealand Locations
Average Age New Zealanders are First Married
80
18
17
16
15
14
35
40
45
Latitude (°S)
30
70
28
60
50
26
40
Age
19
Internet Users (%)
Temperature (°C)
20
% of population who are Internet Users vs
GDP per capita for 202 Countries
30
20
24
22
10
20
0
0
10
20
30
40
1930 1940 1950 1960 1970 1980 1990
GDP per capita (thousands of dollars)
Trend
Association
Strength
Groups
Unusual Values
Scatter
Other Features?
Year
“I notice that...
This could be due to...
Maybe this is...
This could be due to...
This means that...
When the....
For values of.... between...