ASSOSA UNIVERSITY

SCHOOL OF GRADUATE STUDIES

MBA PROGRAM

Introduction to Econometrics MBA-M211

GROUP ASSIGNMENT

SUBMITTED TO: Eshetu Seid (PhD)

SUBMITTED By: GROUP one

1 Abdu seid M MG0001/13

2 Assefa demeke M MG0014/13

3 Bewiket Birhanu M MG0019/13

4 Kiflu Melaku M MG0031/13

5 Lijalem Esubalew M MG0032/13

6 Solomon Asefa M MG0045/13

7 Yaregal kasahun M MG0053/13

8 Melese Haymanot M MG0035/13

GILGEL BELES-CENTER
JUNE 26, 2014
 PART I: SAY TRUE OR FALSE AND EXPLAIN

QUESTION 1. False, Because

Heteroscedasticity is mainly due to the presence of outlier in the data. Outlier in

heteroscedasticity means that the observations that are either small or large with respect to the

other observations are present in the sample. Heteroscedasticity is also caused due to omission

of variables from the model.

Heteroscedasticity is a problem because ordinary least squares (OLS) regression assumes that

all residuals are drawn from a population that has a constant variance (homoscedasticity). To

satisfy the regression assumptions and be able to trust the results, the residuals should have a

constant variance.

QUESTION 2. True, Because

The t-distribution is defined by the degrees of freedom. These are related to the sample size.

The t-distribution is most useful for small sample sizes, when the population standard

deviation is not known, or both. As the sample size increases, the t-distribution becomes more

similar to a normal distribution.

PART II: Multiple choice questions and explanations

Answers

QUESTION 1. A) multicollinearity

Reasons

Multicollinearity is a statistical concept where several independent variables in a model are

correlated. Two variables are considered to be perfectly collinear if their correlation coefficient

is +/- 1.0. Multicollinearity among independent variables will result in less reliable statistical

inferences.

1|Page
Multicollinearity exists whenever an independent variable is highly correlated with one or more

of the other independent variables in a multiple regression equation. Multicollinearity is a

problem because it undermines the statistical significance of an independent variable.

QUESTION 2. Answers

What is multicollinearity? Collinearity (or multicollinearity) is the undesirable situation where

the correlations among the independent variables are strong. In some cases, multiple regression

results may seem paradoxical. For instance, the model may fit the data well (high F-Test), even

though none of the X variables has a statistically significant impact on explaining Y. How is

this possible? When two X variables are highly correlated, they both convey essentially the

same information. When this happens, the X variables are collinear and the results show

multicollinearity. To help us assess multicollinearity, SPSS tells us the Variance Inflation

Factor (VIF) that measures multicollinearity in the model. Why is multicollinearity a problem?

Multicollinearity increases the standard errors of the coefficients. Increased standard errors in

turn means that coefficients for some independent variables may be found not to be

significantly different from 0, whereas without multicollinearity and with lower standard

errors, these same coefficients might have been found to be significant and the researcher may

not have come to null findings in the first place. In other words, multicollinearity misleadingly

inflates the standard errors. Thus, it makes some variables statistically insignificant while they

should be otherwise significant. It is like two or more people singing loudly at the same time.

One cannot discern which is which. They offset each other. How to detect multicollinearity?

Formally, variance inflation factors (VIF) measure how much the variance of the estimated

coefficients are increased over the case of no correlation among the X variables. If no two X

variables are correlated, then all the VIFs will be 1. If VIF for one of the variables is around or

greater than 5, there is collinearity associated with that variable. The easy solution is: If there

are two or more variables that will have a VIF around or greater than 5, one of these variables

2|Page
must be removed from the regression model. The VIF for a predictor is calculated using this

formula.

QUESTION 3.(C). Heteroscedasticity

In statistics, heteroskedasticity (or heteroscedasticity) happens when the standard deviations of

a predicted variable, monitored over different values of an independent variable or as related

to prior time periods, are non-constant.

QUESTION 4.

One of the assumptions made about residuals/errors in OLS regression is that the errors have

the same but unknown variance. This is known as constant variance or homoscedasticity. When

this assumption is violated, the problem is known as heteroscedasticity.

Consequences of Heteroscedasticity

• The OLS estimators and regression predictions based on them remains unbiased and

consistent.

• The OLS estimators are no longer the BLUE (Best Linear Unbiased Estimators)

because they are no longer efficient, so the regression predictions will be inefficient

too.

• Because of the inconsistency of the covariance matrix of the estimated regression

coefficients, the tests of hypotheses, (t-test, F-test) are no longer valid.

The following 4 tests for detecting heteroscedasticity:

1. Bartlett Test

3|Page
 2. Breusch Pagan Test

3. Score Test

4. F-Test

QUESTION 5. A) unbiased

The estimated parameters are unbiased estimators of the population parameters. So, the

expected or mean values of the estimated parameters are equal to the true population

parameters:

QUESTION. B) Autocorrelation

Autocorrelation refers to the degree of correlation between the values of the same variables

across different observations in the data. The concept of autocorrelation is most often

discussed in the context of the time series data in which observations occur at different points

in time (e.g., air temperature measured on different days of the month). For example, one

might expect the air temperature on the 1st day of the month to be more similar to the

temperature on the 2nd day compared to the 31st day. If the temperature values that occurred

closer together in time are, in fact, more similar than the temperature values that occurred

farther apart in time, the data would be autocorrelated.

Part III

A) Give an interpretation to the coefficient of determination

Answer. The coefficient of determination measures the proportion of variability in the values

of dependent variable ( price) explained by its linear relation with the independent variables

𝐸𝑥𝑝𝑙𝑎𝑖𝑛𝑒𝑑 𝑣𝑎𝑟𝑖𝑎𝑡𝑖𝑜𝑛
( BDR, Bath, Hsize, Lsize, Age and Poor). 𝑅 2 = , The expression for
𝑇𝑜𝑡𝑎𝑙 𝑣𝑎𝑟𝑖𝑎𝑡𝑖𝑜𝑛

adjusted , or is written below:

4|Page
where, n is the sample size and k denotes the number of slope coefficients corresponding to the

independent variables. Then:

Or:

Hence, value of for the regression is calculated below:

The R2 is 0.85. Our R2 is between 0 and 1 inclusive. That is 0 ≤ 0.85 ≤ 1. This means that 85%

of the variability in home selling price is explained by its linear relationship ( BDR, Bath,

Hsize, Lsize, Age and Poor) and 15% of variation is due to other factors or chance which are

not part of the model. The adjusted R-square, a measure of explanatory power, is 0.8546. The

standard error of the regression is 0.45, which is an estimate of the variation of the observed

price about the regression line

B). Ceteris paribus .significance of coefficient of each variable is different from zero this

Variables Coefficient Standard error t-statistics

Intercept 109.7 22.1 4.964

BDR 0.567 1.23 0.461

Bath 26.9 9.76 2.756

Hsize .239 0.021 11.381

Lsize 0.005 0.00072 6.944

Age 0.1 0.23 0.435

Poor -56.9 12.23 -4.652

5|Page
We have calculated t-statistics or each independent variable in the above table.

The next step is ;-

If t-statistics is greater than 1.96 and less than -1.96 the coefficient on each variable is

statistically significantly different from zero.

• The t-statistics for the coefficient on BDR = 0.567/1.23 = 0.461<1.96

Therefore, BDR is not statistically significantly different from zero.

• The t-statistics for the coefficient on Bath = 269/9.76= 27.56 >1.96

Therefore, Bath is statistically significantly different from zero.

• The t-statistics for the coefficient on Hsize = 0.239/0.021= 11.38 >1.96

Therefore, Hsize is statistically significantly different from zero.

• The t-statistics for the coefficient on Age = 0.1/0.23= 0.43 <1.96

Therefore, Age is not statistically significantly different from zero.

• The t-statistics for the coefficient on Lsize = 0.005/0.00072= 6.94 >1.96

Therefore, Lsize is statistically significantly different from zero.

• The t-statistics for the coefficient on Poor = -56.9/12.3= -4.63 <1.96

Therefore, Poor is statistically significantly different from zero.

The coefficient of Bath, Hsize, Lsize and poor is significantly different from zero, so reject

the null hypothesis and and accept alternative hypothesis according to 5% critical value.

According to the result the coefficient of BDR, Age is not statistically significantly different

from zero. Accept the null hypothesis and reject alternative hypothesis.

6|Page
C) The fitted equation is

Price = 109.7+26.9Bath+0.239Hsize +0.005Lsize – 56.9Poor

D) There are two types of variables in the model. In a study of price, multiple regression

analysis is done to examine the relationship between home price and six potential predictors.

These are dependent variable i.e., home price, and independent variables include six variables

such as BDR, Bath, Hsize Lsize ,Age and Poor. The independent variables have its own

coefficients which tells each nature of relationship with the dependent variable home price.

The Constant is the predicted value of home price when all of the independent variables have

a value of zero.

Generally, we expect the following results estimated coefficients of each significant variable,

we hold all other independent variables remain constant.

1. We first see the sign of each coefficient like BDR, BTH, Hsize Lsize ,Age explanatory

variables are positively affecting the dependent variable home price. the independent

variable poor negatively affects the dependent variable home price

2. The degree of coefficients of explanatory variables that change the home price

price= BDR, ceteris paribus

= 0.567*1 = 0.567 units

=0.567*1000,where price=$1000

=$567

If one increment of BDR leads to the home price increase by $567 ceteris paribus

price = Bath, ceteris paribus

=26.9*1 = 26.9 units

=26.9*$1000, where price = $1000

7|Page
 = $26900

If one increment of Bath leads to the home price increase by $26900 ceteris paribus.

price = Haise ,ceteris paribus

=.239*1 = 0.239 units

=.239* $1000, where price=$1000

= $239

If the Bath changes by one lead to the home price increases by $239, ceteris paribus.

price =  Lsize ,ceteris paribus

=.005*1 = 0.005 units

=.005*$1000 ,where price=$1000

= $5

If the Lsize changes by one lead to the home price increases by $5, ceteris paribus.

According to the result the effect of Lsize is $5,on $1000 Home price and it very low when

compared with the effect of other explanatory variables on home price .it is insignificant. But

other tests are required.

price =  Age, ceteris paribus

= 0.1*1 = 0.1 units

=.1*$1000 ,where price=$1000

= $100

If the Age changes by one lead to the home price increase by $100, ceteris paribus.

price =  Poor, ceteris paribus

=(-56.9)*1 = -56.9 units

=(-56.9)*$1000 ,where price=$1000

= $(-56900)

If the poor changes by one lead to the home price decrease by $56900, ceteris paribus.

8|Page
The from 6 explanatory variable’s home r should focused on 5 significant explanatory

variables, like BDR, Bath, Hsize, Age and poor. These variables have significant effect on the

dependent variable home price. The coefficient of BDR, Bath, Hsize, Age and poor is

significantly different from zero, so reject the null hypothesis and and accept alternative

hypothesis according to p-values. Further tests are reburied .

According to the result the effect of Lsize is $5,on $1000 Home price and it very low when

compared with the effect of other explanatory variables on home price . The coefficient of

Lsize is insignificant. Accept the null hypothesis and reject alternative hypothesis. But other

tests are required.

➢ Autonomous price is 109.7 ( α)

➢ If BDR is increase by one, we expect price increase by 0.567 (By B1)

➢ If Bath is increased by one, we expect price increase by 26.9 (By B2)

➢ If Hsize is increased by one, we expect price increase by 0.239 (By B3)

➢ If Lsize is increased by one, we expect price increase by 0.005 (By B4)

➢ If Age is increased by one, we expect price loss by 0.1 (By B5)

➢ If poor is increased by one, we expect price decrease by 56.9 (By B6)

9|Page