Two-Variable Statistics And Linear Regression - Sharp EL-512 Instruction Manual

Display Key in:
35
I
d m a
I
1
45
l D ATA l
2
55 x 5
[
data
]
7
65 x 2
[
data
]
9
Key in: Display:
Mean:
e m
53.88888889
Standard Deviation:
§<§ [s i]
9.279607271
Variance: i g a 86.11111111
Correct Data (CD):
The last entry above is an error and must be changed to 60 x 2.
Key in: Display
65 [X ] 2 7
60 [X ] 2 (
m
§ 9
Note: When you correct the mis-entry before pressing the (
d aw
) key, use [cp] key.
3. Two-Variable Statistics and Linear Regression.
In addition to the same statistical functions for Y as fo r X in single-variable statistics,
the sum of the products of samples Z X Y is added in two-variable statistics.
In Linear Regression there are three important values; r, a, and b. The correlation
coefficient r shows the relationship between two variables fo r a particular sample.
The value of r is between —1 and 1. If r equals —1 or 1, all points on the correla­
tion diagram are on a line. The further the value of r is from —1 and 1, the less the
points are massing about the line and the less reliable is the correlation. If r is more
than 0, it shows a positive correlation (Y is in proportion to X) and if r is less than 0,
it is a negative correlation (Y is inverse proportion to X).
The equation for the straight line is Y = a + b X . The point at which the line crosses
the Y axis is a. The slope is b.
r Correlation coefficient
Sxy
S
jcx
' Syy
a a = y — b x ) Coefficient of linear
b b _ $ x y > regression equation
Sxx ) Y = a + b x
/ V -v - \ 2
45