Calculating And Graphing Paired-Variable Statistical Data; Linear Regression Graph; Med-Med Graph - Casio FX-9750G Quick Start Manual

18-4 Calculating and Graphing Paired-Variable
Statistical Data
Under "Plotting a Scatter Diagram," we displayed a scatter diagram and then per-
formed a logarithmic regression calculation. Let's use the same procedure to look at
the six regression functions.
k k k k k Linear Regression Graph
P.289 Linear regression plots a straight line that passes close to as many data points as
possible, and returns values for the slope and
of the line.
The graphic representation of this relationship is a linear regression graph.
!Q1(GRPH)6(SET)c
(Graph Type)
(Scatter) 1(Scat)
!Q1(GRPH)1(GPH1)
(GPH1)
1(X)
(X)
The following are the meanings of the above parameters.
k k k k k Med-Med Graph
P.289 When it is suspected that there are a number of extreme values, a Med-Med graph
can be used in place of the least squares method. This is also a type of linear regres-
sion, but it minimizes the effects of extreme values. It is especially useful in produc-
ing highly reliable linear regression from data that includes irregular fluctuations,
such as seasonal surveys.
6(DRAW)
a ......
Regression coefficient (slope)
b ......
Regression constant term (intercept)
r ......
Correlation coefficient
2(Med)
y y
-intercept ( -coordinate when
1 2 3 4 5
1 2 3 4 5
x
= 0)
6
6
297