[Type [Pick the date]

the
documen
t title]
[Year]
[Type the abstract of the document here. The abstract is typically a [Type the
short summary of the contents of the document. Type the abstract of
the document here. The abstract is typically a short summary of the document
contents of the document.] subtitle]
HOW HETROSKEDASTICITY CAN BE
DETECTED
Heteroskedasticity is a systematic pattern in the errors where the variances of the errors are not
constant. The word Hetero means different or unequal and is the opposite of Homo which
means same or equal. Word Skedastic means spread or scatter. Hence Homoskedasticity
means equal spread and Heteroskedasticity means unequal spread.

Assumption 5 of the CLRM states that the disturbances should have a constant (equal) variance
independent of t:

Var(ut)=σ2

Therefore, having an equal variance means that the disturbances are homoskedastic. If the
homoskedasticity assumption is violated then

Var(ut)=σt2

Where the only difference is the subscript t, attached to the σt2, which means that the variance
can change for every different observation in the sample t=1, 2, 3, 4, …………….., n.

Looking at the following graphs can help us to understand the situation

Graph no.1: Homoskedastic residuals

Graph no.2: Income-consumption patterns, for low levels of income not many choices, opposite
for high levels

Graph no 3: Improvements in data collection techniques (large banks) or to error learning

models (experience decreases the chance of making large errors)

CONSEQUENCES OF
HETROSKEDASTICITY
1. The OLS estimators are still unbiased and consistent. This is because none of the
explanatory variables is correlated with the error term. So a correctly specified equation
will give us values of estimated coefficient which are very close to the real parameters.

2. Affects the distribution of the estimated coefficients increasing the variances of the
distributions and therefore making the OLS estimators inefficient.

3. Underestimates the variances of the estimators, leading to higher values of t and F

statistics.
DETECTING HETROSKEDASTICITY
There are two ways in general for detecting Heteroskedasticity i.e. Informal Method and Formal
Test Method. The first one is done through graphs and therefore we call it the graphical method.
The second is done through formal tests for Heteroskedasticity,

INFORMAL METHOD
AS

FORMAL TEST METHOD

The lists of Tests are as following

1. The Breusch-Pagan LM Test

2. The Glesjer LM Test

3. The Harvey-Godfrey LM Test

4. The Park LM Test

5. The Goldfeld-Quandt Tets

6. White’s Test

1) The Breusch-Pagan LM Test

Step 1: Estimate the model by OLS and obtain the residuals

Step 2: Run the following auxiliary regression:

2
u^ t =a1 + a2 Z 2t +a3 Z 3t +. ..+ a p Z pt + v t

Step 3: Compute LM=nR2, where n and R2 are from the auxiliary regression.

Step 4: If LM-stat>χ2p-1 critical reject the null and conclude that there is significant evidence of
heteroskedasticity
 2) The Glesjer LM Test

Step 1: Estimate the model by OLS and obtain the residuals

|^ut|=a 1 +a 2 Z 2t +a 3 Z 3 t +. . .+a p Z pt +v t
Step 2: Run the following auxiliary regression:

Step 3: Compute LM=nR2, where n and R2 are from the auxiliary regression.

Step 4: If LM-stat>χ2p-1 critical reject the null and conclude that there is significant evidence of
heteroskedasticity

3) The Harvey-Godfrey LM Test

Step 1: Estimate the model by OLS and obtain the residuals

2
ln { u^ t =a1 +a2 Z 2t +a3 Z 3t +. ..+a p Z pt +v t ¿

Step 2: Run the following auxiliary regression:

Step 3: Compute LM=nR2, where n and R2 are from the auxiliary regression.

Step 4: If LM-stat>χ2p-1 critical reject the null and conclude that there is significant evidence of
heteroskedasticity

4) THE PARK LM TEST

Step 1: Estimate the model by OLS and obtain the residuals

2
ln { u^ t =a1 +a2 ln Z 2t +a3 ln Z 3 t +. . .+a p ln Z pt +v t ¿
Step 2: Run the following auxiliary regression:

Step 3: Compute LM=nR2, where n and R2 are from the auxiliary regression.

Step 4: If LM-stat>χ2p-1 critical reject the null and conclude that there is significant evidence of
heteroskedasticity
 5) The Engle’s ARCH Test

Engle introduced a new concept allowing for hetero-skedasticity to occur in the variance of the
error terms, rather than in the error terms themselves.

The key idea is that the variance of ut depends on the size of the squarred error term lagged
one period u2t-1 for the first order model or:

Var(ut)=γ1+γ2u2t-1

The model can be easily extended for higher orders:

Var(ut)=γ1+γ2u2t-1+…+ γpu2t-p

Step 1: Estimate the model by OLS and obtain the residuals

Step 2: Regress the squared residuals to a constant and lagged terms of squared residuals, the
number of lags will be determined by the hypothesized order of ARCH effects.

Step 3: Compute the LM statistic = (n-ρ)R2 from the LM model and compare it with the chi-
square critical value.

Step 4: Conclude

6) The Goldfeld-Quandt Test

Step 1: Identify one variable that is closely related to the variance of the disturbances, and order
(rank) the observations of this variable in descending order (starting with the highest and going
to the lowest).

Step 2: Split the ordered sample into two equally sized sub-samples by omitting c central
observations, so that the two samples will contain ½(n-c) observations.

Step 3:Run and OLS regression of Y on the X variable that you have used in step 1 for each
sub-sample and obtain the RSS for each equation.

Step 4: Caclulate the F-stat=RSS1/RSS2, where RSS1 is the RSS with the largest value.

Step 5: If F-stat>F-crit(1/2(n-c)-l,1/2(n-c)-k) reject the null of homoskedasticity.

 7) The White’s Test

Step 1: Estimate the model by OLS and obtain the residuals

u^ 2t =a1 +a2 X 2t +a3 X 3t +a 4 X 22t +a5 X 23t +a 6 X 2 t X 3t +v t

Step 2: Run the following auxiliary regression:

Step 3: Compute LM=nR2, where n and R2 are from the auxiliary regression.

Step 4: If LM-stat>χ2p-1 critical reject the null and conclude that there is significant evidence of
heteroskedasticity

HETROSEDASTIC PATTERN OF ERROR