Wolkite University

College of Business and Economics

Department of Management (Major in MBA)
Home takes exam on Econometrics &S.W application (MBA522); Lab session

General instructions

 Attempt all questions

 Use Stata software for all questions and include your Stata dofile for all questions as
an appendix.
 Interpret the results as clearly as possible
 Mimic from each other makes your result zero.
 Submission date is two day before final exam
 It is an individual assignment
 Have data from the course instructors’
 Weight: 15-25% of total mark

1. Use data “assign1.xml” for the following questions.

i. Create a permanent log of your output with file name. ‘test1’ and ‘.log’
extension to file name.
ii. Set a memory size of 12 Mb
iii. Change the variable names into into GEN, REA, WRI & ACI for the
respective columns
iv. Create variable labels. The label for GEN, REA, WRI & ACI, gender of
respondents, reading, writing and academic index respectively.
v. What are the storage types of all variables?
vi. Type in the Command window: “describe”. Then discuss in detail all the
result you have obtained in your result window with their importance?
vii. Run “label list” & Codebook command. Then discuss in detail all the result
you have obtained in your result window with their importance
viii. Have you seen any miss values in your data? If not, skip Qu. “ix”; if yes
answer Qu. “ix”.
ix. How many missing value you have seen? , and call up data editor, handling all
missing values. Use “41” numeric data for all missing values.
x. Creating value labels for GEN as “0” if the observation is male, “1”
otherwise.
xi. Variable AcI is the same as the square of ACI. Hence, generate the variable
AcI from ACI variable.
xii. Graph “boxplot GEN”, interpret it.
xiii. What is the correlation between GEN, REA, WRI and ACI?, briefly explain it
xiv. Test the hypothesis that the ACI equals 100. What is your decision rule at 5%
significance level?
xv. Indicate the descriptive statistics of your data. Interpret accordingly.
xvi. Obtain summary statistics for REA and WRI for each value of GENDER.
xvii. Testing equality of means between groups by using “ANOVA” analysis.

1
 xviii. Save this dataset as a Stata dataset with the name: qor1.dta
xix. Run regression ACI on GEN, REA, & WRI. Interpret the regression results
you have obtained in your window results. Evaluate the reliability of your
results estimates.
a. Checking normality of Variables and Transforming variables or test for
Linearity of the Model, and find the solution if you have detect the
problem.
b. Checking for linear relationships, and find the solution if you have detect
the problem.
c. Checking for points that exert undue influence on the coefficients
d. Checking for constant error variance (homoscedasticity), find the solution
if you have detect the problem.
e. Checking model specification, find the solution if you have detect the
problem.
f. Checking for Multicollinearity, find the solution if you have detect the
problem.
g. Checking normality of residuals or test for Normal Errors, and find the
solution if you have detected the problem.
xx. Run logit and probit regression gender on all other variables. Then run “mfx”
command. Interpret your result. What makes different from OLS regression?
2. Use “sysuse elampi2.dta” then try the following questions.
i. Make five graphs of api99: histogram, kdensity plot, boxplot, symmetry plot and
normal quantile plot.
ii. What is the correlation between api99 and meals?
iii. Regress api99 on meals. What does the output tell you?
iv. Regress api00 on all other variable and interpret your results accordingly.
v. Create and list the fitted (predicted) values.
vi. Graph meals and api99 with and without the regression line.
vii. Look at the correlations among the variables api99 meals ell avg_ed using the
corr and pwcorr commands. Explain how these commands are different. Make a
scatterplot matrix for these variables and relate the correlation results to the
scatterplot matrix.
viii. Perform a regression predicting api99 from meals and ell. Interpret the output.
ix. Detecting Unusual and Influential Data, and find the solution for the problem.
x. Tests for Normality of Residuals, and find the solution for the problem.
xi. Tests for Heteroscedasticity, and find the solution for the problem.
xii. Tests for Multicollinearity, and find the solution for the problem.
xiii. Tests for Non-Linearity, and find the solution for the problem.
xiv. Tests for Model Specification, and find the solution for the problem.
xv. Test for Independence in Errors (Test for Autocorrelation), and find the solution
for the problem.

2
3. This “hdp.xlsx data” is designed to assess the factors that affect mathematical
economics achievements of students of Wollega university Shambu campus
departments of Agricultural economics and management students.
i. Change the variable names into GEN, INC, SCO, BOK, PFR, ACD, ASS,
IMP and INS for the respective columns
ii. Run regression Score (dependent variable) on other independent variables,
GEN, INC, BOK, PFR, ASS and IST. Interpret your results.
iii. Based on equation (ii) which variable is the substantially influential?
iv. Run this command: reg SCO GEN INC SCO BOK PFR ACD ASS IMP
and INS. Interpret you results. Which variables are not significant and which
variables are highly significant? What do you think the reasons? Briefly
Justify.
v. Test multi collinarity and hetroscedasticity, misspecification of the model and
linearity of the model. Then if your data faced any of the above problems find
solution accordingly.
4. Based on the “title of your research proposal”, collect hypothetical data at least for
30 observations and for at least two independent variables and dependent variable.
Then, come up with the chapter three and four of your Research methodology:
“result and discussion of Econometrics analysis” (hint: use as an example the
material I gave you)
NB: You report must be including the following points
Model specification
Result and Discussion
o Descriptive Analysis: mean, standard deviation, min, max with
explanation
o Econometrics Analysis: Regression Analysis, tests (priori criteria, 1st
order test, 2nd order test)
o Interpretation
Look the following example
My Research title: Determinants of Poverty in Ethiopia”
Dependent variable: whether household is poverty or not
Independent variables: Income, saving, family size, etc
Observati Poverty Income Saving Family size
on
1 1 1200 200 7
2 0 2500 500 3
3 0 3000 520 2
4 1 300 25 7
5 1 258 10 5
6 0 6000 2000 3
7 1 100 5 5
8 0 5000 2500 2
9 1 300 0 6
10 0 3600 1000 1
11 0 3500 561 4
12 0 3400 358 2

3
13 0 3600 478 5
14 1 800 100 3
15 0 5700 2560 4
16 1 900 140 5
17 1 850 25 8
18 1 560 100 5
19 1 475 55 1
20 0 5000 2580 1
21 1 358 15 5
22 1 600 25 4
23 1 750 24 5
24 0 4800 2000 4
25 1 523 15 4
26 0 7800 3200 1
27 1 6584 3450 5
28 0 8540 3600 1
29 0 5840 2504 4
30 1 412 15 2

Give value for your life @ hence, being committed!!!