PRACTICAL ATTACHMENT REPORT ON ANALYSIS OF BUDGET

ALLOCATED FROM COLLECTED TAX/REVENUE IN 2022 AT

ARBAMINCH CITY

PREPARED BY: AMBACHEW BIHON ID NO: NSR/279/13

SUPERVISORS:

MRS. KIDANE MOLLA

MR. BELAY BELETE

SUBMITTED TO THE ARBAMINCH UNIVERSITY, COLLEGE OF

NATURAL AND COMPUTATIONAL S,SCIENCE DEPARTMENT OF
STATISTICS INPARTIAL FULFILMENT OF THE REQUIREMENT OF
THE PRACTICAL ATTACHMENT COURSE

DURATION OF STAY: FROM 17/11/2016 E.C

SUBMISSION DATE: 30/04/2016 E.C

ARBAMINCH, ETHIOPIA
Declaration

The under signed declared to department of statistics in the college of natural science at Arba
Minch University is that final internship report is my own work and all source of material used to
the final report for internship program have been done.

Student

Name: Ambachew Bihon signature Date:22/04/2016E.C.

The under signed approve that the above student has completed his internship program for two
month period under my supervision.

Approval of office Supervisor

Name: Mrs. Kidane Mola Signature: Date:22/04/2016E.C

Approval of university supervisor

Name: Mr. Belay Belete Signature: Date: 22/04/2016E.C

I
 Acknowledgement

First of all, I would like to express deepest gratitude to almighty God for everything he did to
me.

I would like to tanks my family, friends, relatives and others who helped me when I did this
internship or practical attachment.

And also I extend my gratitude to the host organization advisor kidane Mola and other workers
who initiated me when I did the practical attachment.

I would like to extend my gratitude to my supervisor Mr.Belay Belete who gives direction to me
how to prepare the practical attachment.

Finally, I would like to thanks Arbaminch University specially the department of statistics who
creates this opportunity even the season was not the right season to do this practical attachment.

II
 Table content

Contents page
Acknowledgement ....................................................................................................................................... II
List of table .................................................................................................................................................. IV
List of figure ................................................................................................................................................. IV
Executive summary ...................................................................................................................................... V
1. Introduction .......................................................................................................................................... 1
1.1. background ............................................................................................................................................ 1
1.2. Objectives ..................................................................................................................................... 1
2. Methodology ............................................................................................................................................ 2
2.1. Description of the study area/host institution..................................................................................... 2
2.2 Source and Methods of data collection ............................................................................................... 2
2.3 variables considered ............................................................................................................................ 3
2.4 Method of data analysis ...................................................................................................................... 3
3. Results....................................................................................................................................................... 4
3.1. Descriptive method of data analysis .................................................................................................. 4
3.1.1. Summery statistics ...................................................................................................................... 4
3.2. Inferential method of data analysis .................................................................................................... 8
3.2.1. Multiple linear regression analysis ............................................................................................. 8
4. Conclusion .............................................................................................................................................. 13
5. Recommendation ................................................................................................................................... 13
6. Reference ................................................................................................................................................ 15
Appendix..................................................................................................................................................... 15
Challenges ............................................................................................................................................... 15

III
 List of table

Table1. Percept of salary, non-salary, capital expenditure and budget allocated ......................................... 7

List of figure

Figure 1. Histogram of salary, non-salary, and capital expenditure ............................................................. 5

Figuire 2. Scatterplot of budget allocated vs salary,non-salary,and capital expenditure ............................ 6
Figuire 3. Boxplot of salary,non-salary,capital expenditure and budget allocated ...................................... 6

IV
 Executive summary

The objectives of analysis of budget allocation is to assess the budget allocation of different
sectors. To gain insights into the distribution of funds across different sectors. To assess the
impact of salary, non-salary, and capital expenditure on the total budget allocation.

Arbamich plan and development office is found at the center of Arbaminch city near to
Medihinalem church in south Etiopia.

The source of data collection that I used is secondary source and method of data collection also
secondary data collection which is documents and records. The variables considered are salary,
non-salary, capital expenditure independent variables and budget allocted(independent variable).

The method of data analysis that I used is descriptive method of data analysis and inferential
method of data analysis since my data fits with or convienent for such analysis.

Descriptive method of data analysis is the collecting, organizing, presenting and summerizing of
the data.

Inferential method of data analysis is focuses on making inferences ,drawing conclutions or

generalizations of the data using hypothesis testing, confidence intervals, regression analysis,
analysis of variance (ANOVA), and chi-square tests. Here I used regression analysis which is
multiple linear regression analysis. All the histogram of salary, non-salary, and capital
expenditure shows skewness that is left skewed. The scatterplot shows slight relationship
between the budget allocated and salary, non-salary, and capital expenditure. The boxplot of
salary,non-salary,capital expenditure and budget allocated shows outlier that may affect the
analysis or interpretation of the data if they are influencial and the boxplot of salary,non-
salary,and budget allocated shows skewness that is left skewed. Overall, the coefficient estimates
indicate that all three predictor variables (salary, non-salary, and capital expenditure) have a
statistically significant impact on the response variable. The coefficients suggest a strong
positive relationship between each predictor variable and the response variable. Therefore, we
can conclude that there are significant relationship between salary, non-salary, and capital
expenditure with the response (budget allocated). The ANOVA table suggests that the regression
model, using salary, non-salary, and capital expenditure as predictors, is statistically significant.

V
 1. Introduction

1.1. background

This report deal about the budget allocation of different sectors, the percentage distribution of
the budget among different sectors, the statistical significance of the regression model, the
correlation and relationship between the total budget allocated and each of the independent
variables (salary, non-salary, and capital expenditure). And also explain the description of the
study area/host institution with its foundation and the work of the office.

This report covers Source and Methods of data collection which is secondary source and
documment/record and Method of data analysis which is descriptive and inferencial method of
data analysis. Generally this report covers summeries,table,graphs,relationship between the
dependent variable and indepenedent variables,correlation between pairs of
variables,multicolinearity among independent variables, and the interpretations of different out
put.

1.2. Objectives

General objectives

To assess the budget allocation of different sectors .

To determine the percentage distribution of the budget among different sectors.

To identify the significant predictors (salary, non-salary, and capital expenditure) influencing the
total budget allocation.

To gain insights into the distribution of funds across different sectors.

Specific objectives

To assess the statistical significance of the regression model.

To investigate the relationship between the total budget allocated and the independent variables
(salary, non-salary, and capital expenditure) for the different sectors.

To examine the correlation between the total budget allocated and each of the independent
variables (salary, non-salary, and capital expenditure).

To assess the presence of multicollinearity among the predictor variables.

To assess the impact of salary, non-salary, and capital expenditure on the total budget allocation.

1
 2. Methodology
2.1. Description of the study area/host institution

Arbamich plan and development office is found at the center of Arbaminch city near to

Medihinalem church in south Etiopia.

The authority is responsible in the collection,organization,verification, distribution, analysis and

reporting of data on different fields of work: on
taxes,health,eduacation,trade,industry,tourism,agriculture,women and children issues and so on...
Before 2013 E.C Arbaminch plan and development office was under finance and economic
development office. By that time it was one department of that office (one sector of that
office) and was called department of development plan and economic budget and which was
lead by one directorate. However in 2013 E.C the sector office separated from finance and
economic development office and become independent. Therefore; starting from September,
2013 E.C up to now a day it is known as Arbaminch plan and development office and is
performing different tasks on different fields of work.

Arbaminch plan and development office has three main departments;

 Development plan implementation

 Demography plan implementation

 Socio Economy

And also it has three Supporter departments;

 Guidance of human resource

 Information and statistics of human resource

 Development plan preparation

2.2 Source and Methods of data collection

The source of data collection that I used is secondary source and method of data collection also
secondary data collection which is documents and records .I collected the data by using
documents and recods which is already collected by the host organization (since it is secondary
data).

2
2.3 variables considered

Total budget allocation(dependentvariable): This variable represents the overall budget

allocated to a specific sector.

Independent variables:

Salary : The budget allocated for salaries within each sector.

Non-salary : The budget allocated for non-salary expenses within each sector.

Capital expenditure: The budget allocated for capital expenditure within each sector.

2.4 Method of data analysis

The method of data analysis that I used is descriptive method of data analysis and inferential
method of data analysis since my data fits with or convienent for such analysis.

Descriptive method of data analysis is the collecting, organizing, presenting and summerizing
of the data.

Inferential method of data analysis is focuses on making inferences ,drawing conclutions or

generalizations of the data using hypothesis testing, confidence intervals, regression analysis,
analysis of variance (ANOVA), and chi-square tests. Here I used regression analysis which is
multiple linear regression analysis.

3
 3. Results

3.1. Descriptive method of data analysis

3.1.1. Summery statistics

Variable Mean StDev Minimum Maximum

Salary 11080792 20844485 911408 110806389

Non-salary 6707931 17646035 450000 90804121

Capital 16651670 50398935 0 250029451

expenditure

Budget 34441346 65344674 1361408 300323297

allocated

Interpretation

The average salary which is allocated to the sector is 11,080,792. The values range from a
minimum of 911,408 to a maximum of 110,806,389. The standard deviation indicates the
variability or spread of the salaries around the mean.

The high standard deviation(20844485) suggests significant variability in the salaries.

The average non-salary which is allocated to the sector is 6,707,931. The values range from a
minimum of 450,000 to a maximum of 90,804,121. Similar to the salary variable, the standard
deviation (17646035) is high, indicating a wide range of non-salary amounts.

The average capital expenditure which is allocated to the sector is 16,651,670. The values range
from a minimum of 0 to a maximum of 250,029,451. The standard deviation (50398935) is again
high, indicating significant variability in capital expenditure amounts.

4
The average budget allocated which is allocated to the sector is 34,441,346. The values range
from a minimum of 1,361,408 to a maximum of 300,323,297. The standard deviation
(65344674) is high, indicating a wide range of budget allocations.

Figure 1. Histogram of salary, non-salary, and capital expenditure

Interpretation

As shown from the histogram with normal curve above, all the histogram of salary, non-salary,
and capital expenditure shows skewness that is left skewed.

And also all the histogram of salary, non-salary, and capital expenditure shows outlier, since
some observations are far apart from others observation.

5
Figuire 2. Scatterplot of budget allocated vs salary,non-salary,and capital expenditure

Interpretation

As shown from the figure of scatterplot there is slight relationship between the budget allocated
and salary, non-salary, and capital expenditure. There is also an outliers (unusual observation)
that may affect the analysis or interpretation of the data if they are influencial.

Figuire 3. Boxplot of salary,non-salary,capital expenditure and budget allocated

6
 Interpretation

The boxplot of salary,non-salary,capital expenditure and budget allocated shows outlier that may
affect the analysis or interpretation of the data if they are influencial and the boxplot of
salary,non-salary,and budget allocated shows skewness that is left skewed .

Table1. Percept of salary, non-salary, capital expenditure and budget allocated

N Sector Percentage salary Percentage of percent of capital percent of

o non-salary expenditure budget
allocated
1 Public counsel 72.8327 27.1673 0.0000 0.4160
2 City administration 4.9148 52.4610 42.6243 17.9486
3 Justice office 80.6279 6.4574 12.9147 0.8029
proscription
administration
4 Peace & security 79.4223 20.5777 0.0000 0.4031
5 First level court 57.3110 13.7382 28.9507 0.9716
6 Police 72.3797 15.9272 11.6931 2.2315
7 Plan 64.3101 35.6899 0.0000 0.2470
8 Revenue 86.1635 13.8365 0.0000 1.6188
9 Finance & economic 19.2818 77.2219 3.4962 2.9659
development
10 Public service 60.7918 39.2082 0.0000 0.2909
11 Agriculture 74.9616 19.1470 5.8914 0.3520
12 Rode& transport 59.7349 16.5797 23.6853 0.4378
13 Marketing &cooperative 76.4215 22.5410 0.0000 0.2668
14 Trade & industry 88.9636 11.0364 0.0000 1.0335
15 Culture & truism 68.5650 22.1894 9.2456 0.4486
16 government com 53.8807 46.1193 0.0000 0.2361
17 Youths& sport 25.9494 7.5727 66.4779 1.7938
18 Education 28.2262 15.6006 56.1732 4.1003
19 School 96.1054 3.8946 0.0000 11.9558
20 Health 4.5828 2.2396 93.1776 9.7265
21 Arbaminch dilfana first 80.9840 19.0160 0.0000 4.2330
level hospital
22 Information technology 66.9460 33.0540 0.0000 0.1412
23 Secha health center 72.1110 27.8890 0.0000 1.6999
24 Weza health center 87.7425 12.2575 0.0000 1.3536
25 Women children & 25.4886 4.3500 70.1614 1.4780
Youth
26 Mansplity 7.5898 9.1568 83.2534 31.1423
27 Social a farce 70.9420 29.0580 0.0000 0.2320
28 Inter prize & industry 72.1682 10.2257 17.6062 1.4724
dov.t office

7
Sectors with High Salary Expenditure:
Sectors such as Public Counsel, Justice Office Proscription Administration, Peace & Security,
Revenue, Agriculture, Police, Marketing &cooperative, Trade & industry, school, Trade &
industry, Secha health center, Weza health center, Social a farce , and Inter prize & industry
dov.t office allocate a significant portion of their budget to salaries. This indicates a focus on
human resources and ensuring adequate compensation for employees in these sectors.

Sectors with High Non-Salary Expenditure:

City Administration, Finance & Economic Development, allocate a higher percentage of their
budget to non-salary expenses. This suggests that a substantial portion of their budget is
allocated towards operational costs, services, and programs beyond employee salaries.

Sectors with High Capital Expenditure:

Sectors like Youths& sport, Education, Health , Women children & Youth ,and Education and
Mansplity allocate a notable percentage of their budget to capital expenditure. This indicates a
focus on infrastructure development, facility improvement, and investment in long-term assets.

Sectors with No Capital Expenditure:

Some sectors, including Public Counsel, Peace & Security, Plan, Marketing & Cooperative, and
Social Affairs, do not allocate any percentage of their budget towards capital expenditure. This
suggests that these sectors might have minimal or no investments in infrastructure or long-term
assets. As indicated from the table the sectors in which the highest budget is allocated are city
administration, school, health, and mansplity relative to the other sector . The percentages of
budget allocation vary across sectors, reflecting the different priorities and needs of each sector.

3.2. Inferential method of data analysis

3.2.1. Multiple linear regression analysis

Regression Equation

Budget = 1323 + 0.999980 Salary + 0.999987 Non-salary

allocated + 1.00000 Capital expenditure

8
Hypothesis

Null hypothesis (H0): There is no significant relationship between salary, non salary,capital
expenditure and the response variable(budget allocated).

Alternative hypothesis (HA): There is a significant relationship between salary and the
response variable (budget allocated).

Coefficients

P-
Term Coef SE Coef T-Value Value VIF

Constant 1323 1209 1.09 0.284

Salary 0.999980 0.000049 20317.12 0.000 1.01

Non-salary 0.999987 0.000065 15388.37 0.000 1.26

Capital 1.00000 0.00002 43898.54 0.000 1.26

expenditure

Interpretation

The constant coefficient represents the intercept of the regression model. In this case, the value is
1323. However, the standard error (SE Coef) value of 1209 is relatively high compared to the
coefficient value. The t-value of 1.09 suggests that the coefficient is not statistically significant,
as the p-value of 0.284 is greater than the typical significance level of 0.05. This means that the
constant term may not have a significant impact on the dependent variable.

The coefficient for the "Salary" variable is 0.999980. This suggests that for every unit increase in
the salary, the dependent variable (budget allocated) is expected to increase by approximately
0.999980 units. The extremely small standard error (0.000049) and the very large t-value
(20317.12) indicate that the coefficient is highly statistically significant (p-value of 0.000). The
VIF (Variance Inflation Factor) value of 1.01 suggests that there is no significant
multicollinearity issue between the "Salary" variable and other independent variables in the
model Since if the VIF <10 there is no multicollinearity.

The coefficient for the "Non-salary" variable is 0.999987. This means that for every unit increase
in the non-salary variable, the dependent variable (budget allocated) is expected to increase by
approximately 0.999987 units. The small standard error (0.000065) and the large t-value

9
(15388.37) indicate that the coefficient is highly statistically significant (p-value of 0.000). The
VIF value of 1.26 suggests that there no multicollinearity between the "Non-salary" variable and
other independent variables in the model since VIF < 10.

The coefficient for the "Capital expenditure" variable is 1.00000. This indicates that for every
unit increase in the capital expenditure, the dependent variable (budget allocated) is expected to
increase by 1 unit. The small standard error (0.00002) and the large t-value (43898.54) suggest
that the coefficient is highly statistically significant (p-value of 0.000). The VIF value of 1.26
suggests that there no multicollinearity between the "Capital expenditure" variable and other
independent variables in the model.

Overall, the coefficient estimates indicate that all three predictor variables (salary, non-salary,
and capital expenditure) have a statistically significant impact on the response variable. The
coefficients suggest a strong positive relationship between each predictor variable and the
response variable. Therefore, we can conclude that there are significant relationship between
salary, non-salary, and capital expenditure with the response (budget allocated).

Analysis of Variance

P-
Source DF Adj SS Adj MS F-Value Value

Regression 3 1.15288E+17 3.84293E+16 1.35934E+09 0.000

salary 1 1.16697E+16 1.16697E+16 4.12785E+08 0.000

Non-salary 1 6.69453E+15 6.69453E+15 2.36802E+08 0.000

Capital 1 5.44798E+16 5.44798E+16 1.92708E+09 0.000

expenditure

Error 24 678494416 28270601

Total 27 1.15288E+17

10
Interpretation

The ANOVA table suggests that the regression model, using salary, non-salary, and capital
expenditure as predictors, is statistically significant. The p-value for the regression model is
0.000, which is less than the typical significance level of 0.05, indicating strong evidence against
the null hypothesis. Additionally, the p-values for each individual predictor variable (salary, non-
salary, and capital expenditure) are all 0.000, indicating that each predictor has a significant
contribution to the regression model.

We conclude that overall the ANOVA table suggests that the regression model is a good fit for
the data and that the predictor variables (salary, non-salary, and capital expenditure) collectively
have a significant impact on the response variable.

Correlations

budgetallocte
d salary nonsalary capittalexp

budgetallocted Pearson Correlation 1 .049 .069 .386*

Sig. (2-tailed) .804 .726 .043

N 28 28 28 28

salary Pearson Correlation .049 1 .451* .634**

Sig. (2-tailed) .804 .016 .000

N 28 28 28 28

nonsalary Pearson Correlation .069 .451* 1 .915**

Sig. (2-tailed) .726 .016 .000

N 28 28 28 28

capittalexp Pearson Correlation .386* .634** .915** 1

Sig. (2-tailed) .043 .000 .000

N 28 28 28 28

11
Interpretations

The correlation values range between -1 and 1, where -1 indicates a perfect negative correlation,
0 indicates no correlation, and 1 indicates a perfect positive correlation. The asterisks (*) and
double asterisks (**) indicate the statistical significance of the correlations, with more asterisks
indicating higher significance.While there is no clear boundary to what makes a "strong"
correlation, a coefficient 0 is no correlation, 0-0.39 weak, 0.4-0.59 moderate, and 0.6-1is strong
correlation .

The correlation between budget allocated and salary is positive and weak (0.049). This suggests
a slight positive relationship between the budget allocated and the salary and not significant since
sig value (0.804) > alhpa value (0.05).The correlation between budget allocated and non-salary
expenses is positive and weak (0.069). This indicates a weak positive relationship between the
budget allocated and non-salary expenses.and not significant since sig value (0.726) > alhpa
value (0.05). The correlation between budget allocated and capital expenditure is positive and
weak (0.386). This implies a weak positive relationship between the budget allocated and capital
expenditure and suggests that this correlation is statistically significant since sig value (0.043) <
alhpa value (0.05).

The correlation between salary and non-salary expenses is positive,moderat (0.451) and
signifivcant since sig value (0.016) < alhpa value (0.05. The correlation between salary and
capital expenditure is positive,strong(0.634) and significant since sig value (0.000) < alhpa
value (0.05). The correlation between non-salary expenses and capital expenditure is
positive,strong and significant since sig value (0.000) < alhpa value (0.05. we can conclude
that there is correlation between these paire of independent variables.

12
 4. Conclusion

The sectors in which the highest budget is allocated are city administration, school, health, and
mansplity relative to the other sectors . The percentages of budget allocation vary across sectors,
reflecting the different priorities and needs of each sector.

Overall, the coefficient estimates indicate that all three predictor variables (salary, non-salary,
and capital expenditure) have a statistically significant impact on the response variable. The
coefficients suggest a strong positive relationship between each predictor variable and the
response variable. Therefore, we can conclude that there are significant relationship between
salary, non-salary, and capital expenditure with the response (budget allocated).

The overall ANOVA table suggests that the regression model is a good fit for the data and that
the predictor variables (salary, non-salary, and capital expenditure) collectively have a significant
impact on the response variable.

There is correlation between paire of independent variables and there is no multicollinearity

among independent variables.

13
 5. Recommendation

Public counsel should allocate resources to maintain the high percentage of salary expenditure,
which indicates a focus on human resources.

City administration should reducing the high percentage of non-salary expenditure and
reallocating some of it towards capital expenditure to invest in infrastructure development.

Prioritize essential Services, ensure that sectors providing essential services such as healthcare,
education, and public safety receive adequate funding to meet the needs of the population

Performance evaluations implement a system to evaluate the performance and impact of budget
allocation in different sectors. This can help identify areas of improvement and ensure efficient
utilization of resources.

14
 6. Reference

Bizuharge D.Kidan M. Tadele D.(2014) Arbaminch socio-economic abstract.

Appendix

Challenges

The budget that is given for this practical attachment was not enough for different payments such
as for renting house, food, light, water, transportation and so on.

There were no uploaded statistical software like SPSS and Minitab in the office even there is no
workable computer for practice.

The season that is given for practical attachment is not the right season since most organization’s
work is during winter season due to this case I faced challenges when I find the organization not
only this but also after I got the organization.

Table 1 Budget allocated of the 2022

N Sector Salary Non-salary Capital Total

o expenditure

1 Public counsel 2921635.44 1089800.00 0 4011435.44

2 City administration 8506936.16 90804120.81 73777847.31 173088904.2

3 Justice office proscription 7743113.76

administration 6243113.76 500000.00 1000000.00

4 Peace & security 3087710.88 800000.00 0 3887710.88

5 First level court 5369721.12 1287193.88 2712519.90 9369434.90

6 Police 15575688.60 3427438.00 2516274.97 21519401.57

7 Plan 1531626.84 850000.00 0 2381626.84

8 Revenue 13450842.36 2160000.00 0 15610842.36

9 Finance & economic 28602126.32

development 5515009.56 22087116.76 1000000.00

15
10 Public service 1705532.76 1100000.00 0 2805532.76

11 Agriculture 2544786.00 650000.00 200000.00 3394786.00

12 Rode& transport 2522022.12 700000.00 1000000.00 4222022.12

13 Marketing &cooperative 1966390.64 580000.00 0 2573084.92

14 Trade & industry 8867004.12 1100000 0 9967004.12

15 Culture & truism 2966390.64 960000.00 400000.00 4326390.64

16 government com 1226705.40 1050000.00 0 2276705.40

17 Youths& sport 4488986.52 1310000.00 11500000.00 17298986.52

18 Education 39541678.21
. 11161107.72 6168738.00 22211832.49

19 School 110806389.36 4490389.00 0 115296778.3

20 Health 4298577.12 2100727.00 87398838.44 93798142.56

21 Arbaminch dilfana first level 40821156.48

hospital 33058625.48 7762531.00 0

22

Information technology 911407.68 450000.00 0 1361407.68

23 Secha health center 11821577.84 4572000.00 0 16393577.84

24 Weza health center 11453210.52 1600000.00 0 13053210.52

25 Women children & Youth 3632843.52 620000.00 10000000.00 14252843.52

26 Mansplity 300323297.0
22793845.92 27500000.00 250029451.08

27 Social a farce 1586904.84 650000.00 0 2236904.84

28 Inter prize & industry dov.t 14199582.16

office 10247582.16 1452000.00 2500000.00

Total 310288869.36 187822054.45 466246764.19 964357688.0

16