PART I TRUE OR FALSE (0.

5pt each)
1. The main objective of regression analysis is to measure the strength of linear
association between two variables. F
2. In correlation analysis there is asymmetry in the way the dependent and
explanatory variables are treated. F
3. In deterministic relationship Y = f ( x ) is deterministic if for each value of X there
is one and only one corresponding value of Y. T
4. In Statistical relationship Y =(X) is statistical if for each value of X there is a
whole probabilistic distribution values of Y. T
5. A stochastic relationship with only two explanatory variables is simple linear
regression model. F
PART II CHOOSES THE BEST ANSWERS (1pt each)
1. In the equation Y = βo + β1 X + U, the term Y is__________________
A. Dependent variables
B. Independent variable
C. Slope parameter
D. Intercept parameter
E. Error term
2. One of the following is not among the basic assumptions underlying linear
regression model?
A. The model is linear in parameters
B. Random variable (Ui) is a random real variable.
C. The mean value of random variable (Ui) in any particular period is zero.
D. The variance of the random variable (Ui) is constant in each period.
E. No autocorrelation among consecutive error terms (Ui)
F. None of above

1|Page
3. From the following which one is correct statement about non- deterministic
relationship among two variables?
A. Involves variables that are not random.
B. For each value of X there is one and only one corresponding value of Y
C. Involves variables that are random or stochastic, that have probability
distributions
D. For each value of X there is a whole probabilistic distribution values of Y
E. A and B F. C and D.
4. A relationship between X and Y is ________when for each value of the
independent variable (X) there is one and only one corresponding value of the
dependent variables (Y)
A. stochastic relation
B. ships
C. statistical relationships
D. Non deterministic relationships
E. Deterministic relationships
F. A and C G. B and D
5. The OLS estimator is derived by________________
A. Minimizing the sum of squared residuals.
B. Minimizing the sum of absolute residuals.
C. Making sure that the standard error of the regression equals to standard error of
the slope estimator
D. Connecting the Yi corresponding to the lowest Xi observation with the Yi
corresponding to the highest Xi observation.
E. All of the above
F. None of the above

2|Page
6. The main advantage of using multiple regression analysis over differences
in means testing is that the regression technique
A. Gives you quantitative estimates of a unit change in X.
B. Assumes that the error terms are generated from a normal distribution.
C. Allows you to calculate p- values for the significance of your results.
D. Provides you with a measure of your goodness of fit.
7. Regressor is also known as _____________________
A. Explanatory variable
B. Explained variable
C. Response variable
D. Dependent variable
8. From the following which one is not the factor that attribute for the straight
line of deviation form observation.
A. Error of aggregation
B. Omission of variables from the function
C. Random behavior of human beings
D. Imperfect specification of the mathematical form of the model.
E. All except D
F. None of the above
9. Which one the statement is true regarding residuals in regression analysis?
A. Mean of residuals is always Zero
B. Mean of residuals is always less than Zero
C. Mean of residuals is always greater than Zero
D. There is no such rule for residuals.
E. All of above.

3|Page
10. The following estimation are calculated and given for you

∑ x 1 y=5,∑
x1
2=225 , ∑ 2=18 , ∑ x 1 x 2=10
x2
∑ x 2 y=22
What is the value of coefficient β̇ ᴖ ?
A. 1.24 B. -0.033 C. 12.3 D. -1.65 E. None of the above
11. The value of R2 always ___________________
A. Lies above 0. C. Lies between -1 and 0
B. Lies above 1. D. Lies between 1 and 1.5 E. None of the above
12. In the equation y= βo + β1X1 + β1X2 + U, the term X1 and X2 is ________
A. Dependent variables
B. Independent variable
C. Slope parameter
D. Intercept parameter
E. Error term
13. From the following which one is correct about the coefficient of
determination ( r 2 )?
A. It is a non-negative quantity
B. Its limits are 0 ≤ r 2 ≤ 1
C. an r 2 of 1 means a perfect fit, that is Yi= Yi for each i
D. an r 2 of zero means that there is no relationship between the regress and the
repressor.
E. All of the above are correct
F. None of the above
14. The assumption of homoscedasticity was expressed as______________
A. E (Ui ¿ ¿2=o i 2 B. E (Ui ¿ ¿2= o 2 C. E (Ui ¿ ¿2= 0 D. E (Ui) = 0
15. The ratio of total sum of squares and Explained sum of squares is _______
A. Co-efficient of correlation. B. Co-efficient of determination.

4|Page
 C. Co- efficient of variation D. Co-efficient of co-variation.
16. The meaning of linearity in regression theory is __________________
A. Linear in variables
B. Linear in variables non-linear in parameters
C. Linear in parameters
D. Linear in variables and parameters
17. E (Ui,Uj) = 0, when i≠j is termed as,_______________
A. Hetroscedasticity
B. Multi-collinearity
C. No Auto-correlation
D. Homoscedasticity
18. The property of an estimator E (β^) 1 = β1 is termed as ________________
A. Linearity B. Unbiasedness C. Efficiency D. Accuracy
19. In statistics the reliability of an estimate is measured by its _____________
A. Standard error B. Student value C. F value D. P- value
E. All of the above
20. Choose the correct one from the following
A. 0 ≤ R2 ≤ 1 B. 0 < R2< 1 C. 0 ≥ R2 ≥1 D. 0 > R2> 1
PART III WORKOUT depending on the given information calculates the
following follow necessary steps (25%)
1. The following table contains observations on the quantity demanded (Y) of
contain commodity, its price (X1) and consumers income (X2).
N 1 2 3 4 5 6 7 8 9 10
Quantity demanded(Y) 100 75 80 70 50 65 90 100 170 80
Price (X1) 5 7 6 6 8 7 5 4 3 9
Income(X2) 1000 600 1200 500 300 400 1300 1100 1300 300
Assuming a linear multiple regression model of the form
Y1 = βo + β1X1 + β1X2 + μi

5|Page
I. Estimate the parameter of the form its deviation and interpret their meaning
II. Find the residual sum square and compute the variance and standard errors of
the parameters.
III. Compute the coefficient of determination ( R2 ) and adjusted R2
IV. Test the significance of the estimates at 5% significance level
2. Consider the model: Y= βo + β1X1 + β1X2 +Ui on the basis of information
given below answer the following question.
∑ X 21 = 1600 ∑ X 1 X 2 = 2150
∑ X 22 = 73650 ∑ X 1Y = 4200
∑Y = 400 ∑ X 1 = 125
∑Y 21 = 14000
a. Find the OLS estimate of the slope coefficient and interpret their meaning
b. Compute variance of ^β 1 and ^β 2
c. Test the significant of partial slope coefficients at 5% level of significant
d. Compute R2 and interpret the result
∑ xiyi
3. Proof that ^β o = Y^ - ^β 1 ^
X 1 and ^β 1 = 2
∑ xi

Part I Choose the best answers (ganamo)

1. Which one of the following assumption is wrong about CLR/OLS assumption?
A. the error term has a zero population mean.
B. all explanatory variables are uncorrelated with the error term.
C. observations of the error term are uncorrelated with each other.
D. the distribution of error term around the explanatory is not constant.
E. no explanatory is a perfect linear function of any other explanatory variables.
2. Sample regression function is the estimated version of the_________
A. Estimated version of population regression function

6|Page
B. Estimated version of population correlation function
C. Not an estimated version of population regression function
D. Both b & c
3. Standard error of an estimator is a measure of
A. population estimator
B. precision of the estimator
C. power of the estimator
D. confidence interval of the estimator
4. Which of the following theorem is utilized to justify the normality assumption of
random variables regression model?
A. Euler’s theorem
B. Chebyshev’s theorem
C. Gauss markov theorem
D. Central limit theorem
5. Choose the correct one from the following
A. r 2 = RSS/TSS
B. r 2 = ESS/TSS
C. r 2 = TSS/ESS
D. r 2 = TSS/RSS
6. Rejecting a true hypothesis results in this type of error
A. Type I error
B. Type II error
C. Structural error
D. Hypothesis error
7. One of the assumptions of CLRM is that the number of observations in the
sample must be greater the number of ____________

7|Page
A. Repressor
B. Regressands
C. Dependent variable
D. Dependent and independent variable
8. Degree of freedom refers to:_________
A. Number of observation minus number of constraint
B. Number of observation plus number of constraint
C. number of constraint minus Number of observation
D. None of the above
Part II: matching (1pts)
A B
1. Partial correlation coefficient A. Test the overall significance level
2. Coefficient of multiple determinations B. the regression coefficient
3. R2
4. Correlation
5. T-test and z-test

8|Page
9|Page