STAT 225 Lecture 5 Notes
Scatter Plots and Trend lines
Whenever we want to analyze two qualitative variables simultaneously we learned how to used cross
tabulations.
Examining the relationship between two numeric variables graphically:
When we have
2 quantitative variables
and we want to look at the relationship between them, we
look at a scatter plot. If the scatter plot looks linear, then we implement a least squares regression
analysis or
trend line
analysis to get an equation of a line that uses
x
(Explanatory or Independent
variable)
to explain what happens with
y
(Response or Dependent variable).
Ex.
Storm Data
is a publication of the National Climatic Data Center that contains a listing of
tornadoes, thunderstorms, floods, lightning, temperature extremes, and other weather phenomena.
Table 10.4 in text summarizes the annual number of tornadoes in the U.S. between 1953 and 2005.
Investigate the linear relationship between Year and Number of Tornadoes.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentIf a linear relationship between the two variables exists we eventually would like to be able to write
down the equation corresponding to this relationship:
y a x b
a is the slope of the line, i.e.
rise
a
run
b denotes the yintercept of the line.
It is easy to see that if we had such an equation we could easily make predictions for y given some
particular value of x.
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '08
 MARTIN
 Least Squares, Regression Analysis, Scatter Plots, Scatter plot, Data center, linear relationship

Click to edit the document details