Chapter 13
Simple Linear Regression
and Correlation:
Inferential Methods
Suppose we were to investigate the relationship
between y = the first-year college grade point
average and x = high school grade point average.
The first-year college grade point average and the high school
The equation
Isgrade point for
average
the first-year an
collegedo additive
NOT
grade probabilistic
have average
point a deterministic relationship.
determined solely model
is: by the high school grade point average?
y determinis tic function of x random deviation
f (x ) e
A relationship in which the value of y is completely determined by the value
Whereandeterministically
eindependent
is an “error”
variable x isvariable
A description of the relationship between two variables that are not
of called a deterministic relationship.
related can be given by a probabilistic model.
The simple linear regression model assumes that there is a line with y-intercept a and
slope b, called the population regression line.
When a value of the independent variable x is fixed and an observation on the
dependent variable y is made,
y a bx e
y Population regression line
(slope b)
e1 deviation e in the equation, all observed (x,
a Without the random
y) points would fall exactly on theepopulation
2
regression line.
x1 x2 x
Basic Assumptions of the Simple
Linear Regression Model
1. The distribution of e at any particular x
value has mean value 0. that is, me = 0.
2. The standard deviation of e is the same for
any particular value of x. This standard
deviation is denoted by s.
3. The distribution of e at any particular value
of x is normal.
4. The random deviations e1, e2, . . ., en
associated with different observations are
independent of one another.
Let’s look at the heights and weights of a
population of adult women.
How much
Weights of women
Are some that
of these
would
areweights
5 We
feet tall an adult
will vary
Where wantmore
would the likely
you
female
– in other What
words, weigh
thereif
would
This standard
distribution
than
expect others?
the is
is a she were
distribution
you expect5offeet
deviations
normally
What
weights would
population
for of this
adult all
fortall?
other
thesewhonormal
distributed.
distribution
regression
females areline look
to
5 feet
Weight
heights?
distributionslike? to be
tall.
be?
the same.
60 62 64 66 68
60 62 64 66 68
60
60 62
62 64
64 66
66 68
68
Height
Basic Assumptions of the Simple
Linear Regression Model Revisited
1. The distribution of ofey at
The distribution any
at any particular
particular value of x x
value has mean value 0. that is, me = 0.
is normal.
2. The standard deviation of e is the same for
any particular value of x. This standard
deviation is denoted by s.
Remember the variable e is a measure of the
3. Theextent distribution of
that individual y-values e at any particular value
deviate
offrom
x the
is population
normal. regression line.
For any particular x value, the standard deviation
of y equals the standard deviation of e.
4. The random deviations e1, e2, . . ., en
associated with different observations are
independent of one another.
We use yˆ a bx to estimate the true
population regression line.
Sxy
b = point estimate of b = S
xx
a = point estimate of a = y - bx
where x y 2
Sxy xy
and S x2
x
xx
n n
Let x* denote a specific value of the predictor variable x.
Then a + bx* has two different interpretations:
1. It is a point estimate of the mean y value when x = x*.
2. It is a point prediction of an individual y value to be
observed when x = x*.
Medical researches have noted that adolescent females are much
more likely to deliver low-birth-weight babies than are adult females.
Because low-birth-weight babies have higher mortality rates, a
number of studies have examined the relationship between birth
weight and mother’s age for babies born to young mothers.
The following data is on x = maternal age (in years) and y = birth
weight of baby (in grams).
x 15 17 18 15 16 19 17 16 18 19
The scatterplot shows a
y 2289 3393 3271 2648 2897 3327 2970 2535 3138 3573
linear pattern and the
3500 spread in the y values
Baby’s Weight (g)
appears to be similar across
3000 Sketch a scatterplot of these data.
the range of x values. This
2500 supports the
appropriateness of the
15 16 17 18 19 simple linear regression
Mother’s Age (yrs)
Birth Weight Continued . . .
The following data is on x = maternal age (in years) and y = birth
weight of baby (in grams).
x 15 17 18 15 16 19 17 16 18 19
y 2289 3393 3271 2648 2897 3327 2970 2535 3138 3573
n 10 x 170 y 30,Summary
041 statistics
computed from the sample
x 2910 xy 515,600 y 91,785
2 2
,351
data are:
S 515,600
170 30,041 4903.0
xy
10 Using these summary
170 2 The estimated regression line is:
statistics
Sxx 2910 20.0 y = -1163.45 + 245.15x
10
4903.0
b 245.15
20.0
a 3004.1 (245.1)(17.0) 1163.45
Birth Weight Continued . . . of babies increase approximately 245.15 grams for each
The weight
increase of 1 year in the mother’s age.
The following data is on x = maternal age (in years) and y = birth
weight of baby (in grams).
x 15 17 18 15 16 19 17 16 18 19
y 2289 3393 3271 2648 2897 3327 2970 2535 3138 3573
yˆ 1163.45 245.15x What is the point estimate for the
mean weight of babies born to 18-
1163.45 245.15(18) 3249year-old
.25 grams
mothers?
This is the point estimate for the
This is also the prediction of the weight
3500 mean weight of all babies born to
Baby’s Weight (g)
of a single baby born to a mother 18
18-year-old mothers.
3000
years of age.
2500
15 16 17 18 19
Mother’s Age (yrs)
