Math and Statistics

Second Assignment

Prepared For Dr. Dina Yousri

Prepared by:
Islam Sami Abdel Fattah.

| Marketing Management | May, 10,2023

1
Table of Contents
Prepared For Dr. Dina Yousri ................................................................................................ 1
I. Executive Summary ...................................................................................................... 3
II. Introduction ................................................................................................................... 3
III. Descriptive Analysis ...................................................................................................... 4
IV. Inference Analysis:........................................................................................................ 6
V. T-Value Analysis ........................................................................................................... 9
VI. R-Square Values.......................................................................................................... 10
VII. Conclusion and Suggestion......................................................................................... 11

2
 I. Executive Summary
The analysis of the relationship between wages as the dependent variable and
experience, education, and tenure as independent variables was conducted using a
linear regression model. Based on the R-squared values provided, we can see that the
model with education as the independent variable has the highest R-squared value of
0.102, indicating that the education variable explains 10.2% of the variation in the
wages. On the other hand, the models with experience and tenure as independent
variables have much lower R-squared values of 0.000012 and 0.015, respectively,
indicating that these variables have very little impact on the wages.

The results suggest that education has a relatively stronger relationship with wages
compared to experience and tenure. However, it is important to note that there may
be other variables not included in the model that could have a significant impact on
wages.

II. Introduction
Descriptive analysis is a statistical method that involves summarizing and interpreting
data to gain insights into its characteristics, distribution, and potential relationships
between variables. It is a fundamental technique used in various fields, including
business, economics, psychology, social sciences, and more. By analyzing descriptive
statistics such as the mean, median, mode, standard deviation, and other measures,
researchers can draw conclusions about the data, identify patterns, and make informed
decisions based on their findings. Descriptive analysis can also be used to present data
in a clear and concise manner, facilitating easy understanding and communication of
complex information. Overall, descriptive analysis plays a crucial role in understanding
and interpreting data, providing valuable insights into various aspects of a given
population or phenomenon.

Inferential analysis is a statistical method that involves drawing conclusions or

inferences about a population based on a sample of data. It is an essential technique
used in various fields, including business, medicine, social sciences, and more. The goal
of inferential analysis is to make predictions or inferences about a larger population
based on a smaller sample, with a certain degree of confidence. Inferential analysis
uses statistical methods such as hypothesis testing, confidence intervals, and
regression analysis to estimate population parameters and test hypotheses. The results
of inferential analysis provide valuable insights into a given population and can help
researchers make informed decisions and draw conclusions based on their findings.
Overall, inferential analysis plays a crucial role in research and decision-making,
providing a way to make predictions and draw conclusions about a population based
on a sample of data.

3
 III. Descriptive Analysis

Education Experience Tenure wage

Mean 13.48 Mean 11.59 Mean 7.27 Mean 964.26

Standard Error 0.0733 Standard Error 0.1460 Standard Error 0.169 Standard Error 13.51
Median 12 Median 11 Median 7 Median 912.5
Mode 12 Mode 11 Mode 1 Mode 1000
Standard Standard Standard Standard
Deviation 2.200 Deviation 4.38 Deviation 5.08 Deviation 405.16
Sample Variance 4.842 Sample Variance 19.18 Sample Variance 25.81 Sample Variance 164156.6
Kurtosis -0.736 Kurtosis -0.56 Kurtosis -0.799 Kurtosis 2.77
Skewness 0.542 Skewness 0.07 Skewness 0.423 Skewness 1.21
Range 9 Range 22 Range 22 Range 2963
Minimum 9 Minimum 1 Minimum 0 Minimum 115
Maximum 18 Maximum 23 Maximum 22 Maximum 3078
Sum 12132 Sum 10433 Sum 6539 Sum 867838
Count 900 Count 900 Count 900 Count 900

The given data presents statistics on four variables related to education, work
experience, job tenure, and wage, including measures such as the mean, median,
mode, standard deviation, sample variance, kurtosis, skewness, range, minimum,
maximum, sum, and count. Analyzing these measures can provide insights into the
distributions and characteristics of these variables, as well as their potential
interrelationships.
Starting with the education variable, the mean value of 13.48 and the median value
of 12 suggest that the distribution is slightly skewed to the right, with a mode of
12 indicating that this is the most frequent value. The standard deviation of 2.20
indicates that there is a moderate degree of variation in the education levels among
the sample population.
Moving on to work experience, the mean value of 11.59 suggests that the sample
population has, on average, over 11 years of work experience.
The standard deviation of 4.38 indicates that there is a significant degree of
variation in work experience levels, as reflected by the range of 22 between the
minimum and maximum values.
The kurtosis value of -0.56 suggests that the distribution of work experience is
slightly flatter than the normal distribution, with shorter tails. The skewness value
of 0.07 indicates that the distribution is approximately symmetrical.
The job tenure variable has a mean value of 7.27, indicating that the sample
population has, on average, been with their current employer for just over seven
years. The standard deviation of 5.08 suggests that there is a significant degree of
variation in job tenure levels among the sample population, with a range of 22
between the minimum and maximum values.

4
The kurtosis value of -0.80 indicates that the distribution is flatter than the normal
distribution, with shorter tails. The skewness value of 0.42 indicates that the
distribution is slightly skewed to the right.
The wage variable has a mean value of 964.26, indicating that the sample
population has an average wage of just under $1,000. The standard deviation of
405.16 indicates that there is a significant degree of variation in wage levels among
the sample population, as reflected by the range of 2963 between the minimum
and maximum values.
The kurtosis value of 2.77 indicates that the distribution is more peaked and has
heavier tails than the normal distribution. The skewness value of 1.21 indicates that
the distribution is highly skewed to the right.
In terms of potential interrelationships between these variables, further analysis
would be necessary to draw any definitive conclusions. However, it is possible that
education, work experience, and job tenure may all be positively related to wage
levels, as individuals with higher levels of education and experience may be more
likely to secure higher-paying jobs with longer tenures.
Overall, this data provides a snapshot of the distribution and characteristics of
education, work experience, job tenure, and wage levels among a sample
population.

5
IV. Inference Analysis:
A. Education and Wages interpret:

Regression Statistics
Multiple R 0.319
R Square 0.102
Adjusted R
Square 0.101
Standard 384.21
Error 2
Observation 900

ANOVA
Significa
df SS MS F nce F
1501485 150148 101.713 9.86772
Regression 1 1.52 51.5 5097 E-23
1325619 147619
Residual 898 05.5 .0
1475767
Total 899 57.1

Coeffici Standard Lower Upper Lower Upper

ents Error t Stat P-value 95% 95% 95.0% 95.0%
Intercept 172.54 79.54 2.17 0.03 16.43 328.65 16.43 328.65
9.86772
Education 58.73 5.82 10.09 E-23 47.30 70.16 47.30 70.16

The table provides the results of a linear regression analysis that explores the
relationship between education and wages. In this analysis, education is the
independent variable, and wages are the dependent variable.
The first row of the table displays the intercept, which is the predicted value of
wages when the level of education is zero. In this case, the intercept is 172.54,
indicating that a person with zero education can expect to earn a wage of $172.54.
The second row of the table displays the coefficient for education, which is 58.73.
This means that, on average, for every one unit increase in education level, a
person's wage is predicted to increase by $58.73.
The standard error of the coefficient is 5.82, indicating that the coefficient estimate
is relatively precise.
The t-statistic for the coefficient is 10.09, and the associated p-value is very small
(9.86772E-23). This suggests that the coefficient is statistically significant, and we
can reject the null hypothesis that there is no relationship between education and
wages.
The 95% confidence interval for the coefficient ranges from 47.30 to 70.16, which
suggests that we can be 95% confident that the true coefficient falls within this

6
 range.
Overall, the results suggest that education is a significant predictor of wages. As
the level of education increases, people can expect to earn higher wages on
average. These findings can be useful for individuals who are considering pursuing
higher education or for policymakers who are interested in promoting education
as a means of improving economic outcomes.

B. Experience and Wages interpret:

Regression Statistics
Multiple R 0.0034
1.16E-
R Square 05
Adjusted R
Square -0.0011
Standard 405.38
Error 56
Observation 900

ANOVA
Significa
df SS MS F nce F
1706. 0.010 0.918864
Regression 1 1706.185 185 382 287
16433
Residual 898 1.48E+08 7.5
Total 899 1.48E+08

Coeffici Standard P- Lower Upper Lower Upper

ents Error t Stat value 95% 95% 95.0% 95.0%
960.61 25.11 7.7E- 885.5421 1035.69 885.542 1035.69
Intercept 8 38.25311 216 106 021 3909 1021 3909
- -
0.3145 0.101 0.918 5.744307 6.37342 5.74430 6.37342
Experience 59 3.087149 893 864 228 5411 7228 5411

The table displays the results of a linear regression analysis that examines the
relationship between wages and experience. In this analysis, experience is the
independent variable, and wages are the dependent variable.
The first row of the table shows the intercept, which is the predicted value of wages
when the level of experience is zero. In this case, the intercept is 960.62, indicating
that a person with no experience can expect to earn a wage of $960.62.
The second row of the table shows the coefficient for experience, which is 0.315.
This means that, on average, for every one unit increase in experience level, a
person's wage is predicted to increase by $0.315.
The standard error of the coefficient is 3.087, indicating that the coefficient estimate
is relatively imprecise.

7
 The t-statistic for the coefficient is 0.102, and the associated p-value is 0.919. This
suggests that the coefficient is not statistically significant, and we fail to reject the
null hypothesis that there is no relationship between experience and wages.
The 95% confidence interval for the coefficient ranges from -5.744 to 6.373, which
includes zero. This indicates that we cannot be 95% confident that the true
coefficient is different from zero.
Overall, the results suggest that experience is not a significant predictor of wages.
This finding may be surprising, as experience is often thought to be an important
factor in determining wages. However, this analysis suggests that other factors,
such as education or skills, may be more important in explaining variation in wages.

C. Tenure and Wages interpret:

Regression Statistics
0.12358
Multiple R 7437
0.01527
R Square 3855
Adjusted R 0.01417
Square 7278
Standard 402.280
Error 0982
Observatio. 900

ANOVA
Significa
df SS MS F nce F
2254065. 225406 13.9286 0.00020
Regression 1 921 5.921 6579 182
1453226 161829.
Residual 898 91.1 2774
1475767
Total 899 57.1

Coeffici Standard Lower Upper Lower Upper

ents Error t Stat P-value 95% 95% 95.0% 95.0%
892.657 23.40816 38.1344 5.6945E
Intercept 298 117 4771 -190 846.71 938.5 846.7 938.59
9.85570 2.640783 3.73211 0.00020
tenure 1459 397 2778 182 4.67 15.03 4.6 15.03

The data presented above shows the results of a regression analysis with wages as
the dependent variable and tenure as the independent variable. The regression
equation is presented as follows:
Wages = 892.66 + 9.86*Tenure
The coefficient of determination (R-squared) for this regression model is not
presented in the table, but it indicates the proportion of the variation in wages that

8
 can be explained by tenure. The coefficient of determination ranges from 0 to 1,
with 1 indicating a perfect fit of the model to the data.
The coefficient for tenure is 9.86, and it has a standard error of 2.64. This indicates
that there is a statistically significant relationship between wages and tenure. The
t-value for tenure is 3.73, and the p-value is 0.0002. This means that the relationship
between wages and tenure is unlikely to be due to chance.
The confidence interval for the coefficient of tenure is presented as 4.67 to 15.04
at the 95% level. This means that we can be 95% confident that the true population
coefficient for tenure lies within this range.
In conclusion, the data suggests that there is a significant positive relationship
between wages and tenure. As tenure increases, so does the expected wage.
However, it is important to note that this relationship is not a causal one, and there
may be other factors that influence wages that are not captured in this analysis.

V. T-Value Analysis
t Stat
Intercept 38.13444771
tenure 3.732112778

t Stat
Intercept 25.11215534
experience 0.101893083

t Stat
Intercept 2.17
education 10.09

For the first model with wages as the dependent variable and tenure as the
independent variable, the T-statistic is 3.7321. The null hypothesis for this model is
that there is no significant relationship between wages and tenure (β1=0), while
the alternative hypothesis is that there is a significant relationship between wages
and tenure (β1≠0).
For the second model with wages as the dependent variable and experience as the
independent variable, the T-statistic is 0.1019. The null hypothesis for this model is
that there is no significant relationship between wages and experience (β1=0),
while the alternative hypothesis is that there is a significant relationship between
wages and experience (β1≠0).
For the third model with wages as the dependent variable and education as the
independent variable, the T-statistic is 10.09. The null hypothesis for this model is
that there is no significant relationship between wages and education (β1=0), while
the alternative hypothesis is that there is a significant relationship between wages

9
 and education (β1≠0).
In all three models, the T-statistics are significant, which indicates that we can reject
the null hypotheses and conclude that there is a significant relationship between
the independent variables and wages.

VI. R-Square Values

Regression Statistics Tenure
Multiple R 0.123587437
R Square 0.015273855

Regression Statistics Experience

Multiple R 0.003400197
R Square 1.15613E-05

Regression Statistics Education

Multiple R 0.319
R Square 0.102

The R-squared value is a measure of how well the independent variables in a

regression model explain the variation in the dependent variable. A higher R-
squared value indicates a better fit of the model to the data.
Based on the R-squared values provided, we can see that the model with education
as the independent variable has the highest R-squared value of 0.102, indicating
that the education variable explains 10.2% of the variation in the wages. On the
other hand, the models with experience and tenure as independent variables have
much lower R-squared values of 0.000012 and 0.015, respectively, indicating that
these variables have very little impact on the wages.
Overall, the results suggest that education has a relatively stronger relationship
with wages compared to experience and tenure. However, it is important to note
that there may be other variables not included in the model that could have a
significant impact on wages.

10
VII. Conclusion and Suggestion

In conclusion, the analysis shows that education and tenure have a significant
positive relationship with wages, while experience does not have a significant
impact on wages. The coefficient of education is higher than the coefficient of
tenure, indicating that education has a stronger effect on wages. Therefore, it can
be suggested that individuals with higher levels of education and longer tenure in
their jobs are more likely to receive higher wages.
However, it is important to note that this analysis only provides a correlation
between these variables and does not necessarily imply causation. Other factors
may also influence wages, such as industry, location, and job title, which were not
included in the analysis. It is also essential to consider the potential for selection
bias, as individuals with higher education and tenure may be more likely to secure
higher-paying jobs.
To further investigate the relationship between these variables and wages, future
studies could consider collecting data on a broader range of factors that may
impact wages. Additionally, research could explore the potential moderating effect
of industry, job title, and location on the relationship between education, tenure,
experience, and wages. This information could help individuals make more
informed decisions about their education and career paths.

11