Professional Documents
Culture Documents
another.
The specific functional forms may be linear,
quadratic, logarithmic, exponential, hyperbolic, or
other form
Statistical versus Deterministic Relationships
A relationship between X and Y, characterized as Y
= f(X) is said to be deterministic or non-stochastic
If for each value of the independent variable (X)
there is one and only one corresponding value of
dependent variable (Y).
A relationship between X and Y is said to be
stochastic if for a particular value of X there is a
whole probabilistic distribution of values of Y
REGRESSION VERSUS CORRELATION
e. Error of measurement
2.1 A HYPOTHETICAL EXAMPLE 1
X→
Y 80 100 120 140 160 180 200 220 240 260
↓
Weekly family 55 65 79 80 102 110 120 135 137 150
consumption 60 70 84 93 107 115 136 137 145 152
expenditure Y, $ 65 74 90 95 110 120 140 140 155 175
70 80 94 103 116 130 144 152 165 178
75 85 98 108 118 135 145 157 175 180
– 88 – 113 125 140 – 160 189 185
– – – 115 – – – 162 – 191
Total 325 462 445 707 678 750 685 1043 966 1211
E(Y | Xi ) = f ( Xi )….………………(2.2.1)
E(Y | X ) is a linear function of X
i i
Yi = E(Y | Xi) + Ui
Yˆi overestimates the true E(Y | Xi) for the Xi
shown therein.
for any Xi to the left of the point A, the SRF will
underestimate the true PRF.
𝑆𝐸(𝛼)ඥ𝑉𝑎𝑟(𝛼)
Whereas: 𝑈𝑖 = 𝑦 −
2 2 ( xy ) 2
x2.
Where: var = variance and se = standard error
and where σ2 is the constant homoscedastic.
σˆ2 is the OLS estimator of the true but
unknown σ2
the expression n−2 is known as the number of
degrees of freedom (df).
uˆ2 being the sum of the residuals squared
or the residual sum of squares (RSS) 0r u 2
Once uˆ2 is known, σˆ2 can be easily computed
σˆ2 is known as the standard error of estimate or
the standard error of the regression (se).
NB.
1. The variance of βˆ is directly proportional to σ 2
but inversely proportional to x2
given σ2, if there is substantial variation in the X
values,
β can be measured more accurately than when the Xi
do not vary substantially
given x2 , the larger the variance of σ2 , the larger
the variance of β
1. 2. The variance of αis directly proportional to σ 2
and X2 but inversely proportional to x2 and the
sample size n.
Properties
of Least Square (OLS) Estimators:
Gauss-Markov Theorem
The closeness of the estimate to the population parameter is
measured by
the mean and variance or
standard deviation of the sampling distribution
of the estimates
. well-known theorem Gauss-Markov Theorem s
say the OLS estimators are BLUE .
(Best, Linear, and Unbiased Efficient, Estimator).
An estimator is called BLUE if:
Linear: a linear function of the random variable
Unbiased: its average or expected value is equal to
the true population parameter.
Minimum variance: It has a minimum variance in the
class of linear and unbiased estimators
An unbiased estimator with the least variance is
known as an efficient estimator.
proofs of these properties
A. Linearity: (for )
Proposition: are linear in Y.
the OLS estimator of is given by:
,,
But
Now let,
… is linear in Y
B. Linearity in
Proof: Substitute equation no 2.13 in place of of
equation 2.22
=
=
=
=
we know are constant then
is a linear function of the dependent variable Yi
C. Biasedness
Proposition: are the unbiased estimators of the
true parameters
if is an estimator of
Then
if ˆ is the unbiased estimator of then bias = 0
.. are estimators of the true parameters
Proof (1): Prove that is unbiased i.e.
We know that
,, …………………………………..2.23
………….2.24
since
Therefore, is unbiased estimator of .
Estimators.
= Yˆ Y
Y.
X
.. = deviation of the observation Yi from the
regression line
= deviation of Y from its mean
= deviation of the regressed (predicted) value ( Yˆ ) from the mean
in deviation form
squaring and sum both sides,
But =
but
..
Thus
or
We know
Squaring and summing both sides
since
The limit of R2: The value of R2 falls between zero
and one. i.e. .
INTERPRETATION OF R2