Alumni Giving

A Final Project Paper

Submitted by:
Espinosa, Liandra Elise C.
Lee, Leroy Kia Soon G.
Okada, Yuki G.
Sese, Luke Irvin V.
Weng, Charleen Mae Y.

Section: C35

Submitted to:
[Name of Professor]

Submitted on:
February 6, 2021
 I. Introduction

The objective of college universities is to be able to produce well educated citizens

equipped to better the nation or society. Considering this, alumni who have graduated from

universities would feel the urge to give back to the institution that built and molded them to be

who they are, especially since their success or future success stems from the foundation that their

respective university provided. Alumnus often give back to their respective university not only to

show gratitude, but also for social purposes. To be able to stay in touch with the community they

grew with, and aid in letting the younger generations experience what they did. According to

Bruggink and Siddiqui (1995), a social sense of obligation, to provide cumulative goods for the

society which is sharpened by feelings of loyalty and empathy to his/her school, drives an

alumnus’ altruism to his/her college. It is significant for universities and colleges to produce

graduates so there will be more alumni that could provide donations. A study has shown that

students are most likely to graduate if they are satisfied with the contact between the teachers and

them. Several factors were acknowledged like the percentage of classes under 20, student/faculty

ratio, and alumni giving rate. The given data was examined thoroughly, and further analysis has

shown that alumni giving rate illustrates a positive trend rather than a weak optimistic trend. It

can be derived that universities with higher graduation rates produced more giving alumni. The

results show a linear relationship between the dependent and independent variables. The alumni

giving rate is expected to increase as the graduation rate increases. Alumni giving rate is also

expected to increase as the percentage of class under 20 increases. Ultimately, the alumni giving

rate is expected to decrease as the student faculty rate decreases.

1
 A. Background of the Case Study

Colleges and universities utilize different ways in generating profit and alumni donations

is one of them. It is imperative to recognize the different factors that may result in the increase in

the percentage of alumni donations. Through this, administrators could conceptualize and

implement different approaches that may encourage more alumni to donate thus increasing their

revenue. Research has proven that students are most likely to graduate if they are satisfied with

the contact between the teachers and them. Hence, it is suspected that smaller class sizes and

lower student-faculty ratios might lead to a higher percentage of satisfied students, making them

graduate which increases the school’s revenue from alumni donations. Through a given data for

48 national universities from America’s Best Colleges Year 2020 Edition that includes the

percentage of classes with fewer than 20 students, the number of students enrolled divided by the

total number of the faculty (student/faculty ratio), and the percentage of alumni that made a

donation to the corresponding university, it is yet to be concluded if there is a relationship

between the dependent and independent variables.

I. Objectives

General Objective:

● To assess if there is a significant relationship between student satisfaction

and higher percentage of graduates.

Specific Objectives:

● To study if the percentage of classes with fewer than 20 students affects

student satisfaction.

● To study if the student faculty ratio affects student satisfaction.

2
 II. Research Problem and Hypothesis

Research Problem:

● The study aims to determine the effect of the percentage of classes with

fewer than 20 students and the student faculty ratio on the alumni giving

rate of the given national universities. It aims to answer the main question:

Does the class size and student faculty ratio affect the percentage of

alumni donations?

Hypotheses:

● Null​: The class size and the student faculty ratio does not affect the

percentage of alumni donations.

H​0​ :​ µ ​≠​0

● Alternative​: The class size and the student faculty ratio affect the

percentage of alumni donations.

H​1​ :​ µ = 0

B. Description of the Dataset

The dataset focuses on the three main variables which are the percentage of classes with

fewer than 20 students, the student faculty ratio, and the alumni giving rate. The percentage of

classes with fewer than 20 students denotes all the classes which have smaller class sizes that

possibly maximizes the contact between the student and the teacher, given that there will be an

intimate training ground for the students. Consequently, the teachers will be able to attend to

his/her students without undivided attention. For the teacher, having a smaller class size will be

less stressful since there are only a small number of students that he/she will attend to that can

3
affect his/her teaching skills positively. Thus, having a smaller class size increases the potential

of both the students and teachers which affects the students’ motivation to graduate. This is

similar to the student/faculty ratio. The alumni giving rate given in the dataset is the main

variable that will be considered since this will determine if both the given factors are true.

Table 1 shows data for 48 national universities (America’s Best Colleges, Year 2000

Edition). The column labeled % of Classes Under 20 shows the percentage of classes offered

with fewer than 20 students. The column labeled Student/Faculty Ratio is the number of students

enrolled divided by the total number of faculty. Finally, the column labeled Alumni Giving Rate

is the percentage of alumni that made a donation to the university.

Table 1.​ ​Data for 48 National Universities

Alumni
Graduatio % of Classes Student-Fac
University State Giving
n Rate Under 20 ulty Ratio
Rate

Boston College MA 85 39 13 25

Brandeis University MA 79 68 8 33

Brown University RI 93 60 8 40

California Institute of Technology CA 85 65 3 46

Carnegie Mellon University PA 75 67 10 28

Case Western Reserve Univ. OH 72 52 8 31

College of William and Mary VA 89 45 12 27

4
Columbia University NY 90 69 7 31

Cornell University NY 91 72 13 35

Dartmouth College NH 94 61 10 53

Duke University NC 92 68 8 45

Emory University GA 84 65 7 37

Georgetown University DC 91 54 10 29

Harvard University MA 97 73 8 46

Johns Hopkins University MD 89 64 9 27

Lehigh University PA 81 55 11 40

Massachusetts Inst. of Technology MA 92 65 6 44

New York University NY 72 63 13 13

Northwestern University IL 90 66 8 30

Pennsylvania State Univ. PA 80 32 19 21

Princeton University NJ 95 68 5 67

Rice University TX 92 62 8 40

Stanford University CA 92 69 7 34

Tufts University MA 87 67 9 29

Tulane University LA 72 56 12 17

U. of California–Berkeley CA 83 58 17 18

5
U. of California–Davis CA 74 32 19 7

U. of California–Irvine CA 74 42 20 9

U. of California–Los Angeles CA 78 41 18 13

U. of California–San Diego CA 80 48 19 8

U. of California–Santa Barbara CA 70 45 20 12

U. of Chicago IL 84 65 4 36

U. of Florida FL 67 31 23 19

U. of Illinois–Urbana Champaign IL 77 29 15 23

U. of Michigan–Ann Arbor MI 83 51 15 13

U. of North Carolina–Chapel Hill NC 82 40 16 26

U. of Notre Dame IN 94 53 13 49

U. of Pennsylvania PA 90 65 7 41

U. of Rochester NY 76 63 10 23

U. of Southern California CA 70 53 13 22

U. of Texas–Austin TX 66 39 21 13

U. of Virginia VA 92 44 13 28

U. of Washington WA 70 37 12 12

U. of Wisconsin–Madison WI 73 37 13 13

Vanderbilt University TN 82 68 9 31

6
Wake Forest University NC 82 59 11 38

Washington University–St. Louis MO 86 73 7 33

Yale University CT 94 77 7 50

I. Type of Data

In the given dataset, the percentage of classes with fewer than 20 students

and the student faculty ratio are the independent variables. On the other hand, the

alumni giving rate is the dependent variable. The percentage of classes with fewer

than 20 students or the class size is considered as a continuous quantitative

variable that can be measured by counting the classes that have less than 20

students. The student/faculty ratio is also a continuous quantitative variable that

can be measured by counting the number of students and the number of teachers.

Lastly, the alumni giving rate is also a continuous quantitative variable that can be

measured by the amount of money that the alumni are donating.

II. Statistical Techniques and Tools

To fully examine the given dataset, Descriptive Statistics will be used. It

will be easier to produce interpretations through a simple presentation of the raw

data. Descriptive statistics provides generalizations which will be helpful in

deducing the given data. However, results are not totally accurate thus Simple

Linear, ANOVA, and Multiple Regression Statistics will also be used. Simple

Linear regression will be helpful in studying the movements of the variables and

how it affects each other. ANOVA will also be considered since there are three

variables and it will lessen the experimental error. Ultimately, Multiple

7
 Regression will be used to have a deeper understanding of the results from the

Simple Linear Regression. It will be helpful in making predictions and

interpretations.

II. Results and Discussions

a. Descriptive Statistics

Table 2. ​Descriptive Statistics for The Graduation Rate

Descriptive Statistics

Mean 83.04166667

Standard Error 1.242337626

Median 83.5

Mode 92

Standard Deviation 8.607167556

Sample Variance 74.08333333

Kurtosis -1.103905497

Skewness -0.282278609

Range 31

Minimum 66

Maximum 97

Sum 3986

Count 48

The table above illustrates the different descriptive statistics such as the measures of

location and the measures of variability. The variable used for this table is the graduation rate.

Through the table, the researchers were able to determine the mean for the variable that is 83.04;

8
the central point or median of the variable that is 83.5; and the mode or the most recurring value

of the variable, that is 92. Upon further analysis, it can also be distinguished that the mean

exhibits accuracy since the mean and median are relatively close to each other and there were no

extreme outliers. As for the variance, it can be seen that the sample variance is 74.08 and the

standard deviation is 8.61, which entails that as the variance goes higher in relation to the mean,

the data will become more spread out. Since the value of the range is 31, it means that the

difference between the maximum value from the minimum value is high, leaving it to have a

higher variance. Given these facts, it can be said that the alumni giving rate in this standpoint

illustrates a positive trend rather than a weak optimistic trend. Despite this, it can also be derived

that universities with higher graduation rates produced more giving alumni.

Table 3. ​Descriptive Statistics for % of Classes Under 20

Descriptive Statistics

Mean 55.72916667

Standard Error 1.904348231

Median 59.5

Mode 65

Standard Deviation 13.19371156

Sample Variance 174.0740248

Kurtosis -0.956615467

Skewness -0.500612795

Range 48

Minimum 29

Maximum 77

9
 Sum 2675

Count 48

Table 3 shows the measures of location and the measures of variability of the variable %

of Classes Under 20, which is also known as the dependent variable for this dataset. It also

represents the percentage of personalized education the university ensured. Based on the table,

the researchers were able to determine that the mean for the variable is 55.73; the central point or

median of the variable is 59.5; and the mode or the most recurring value of the variable that is

65. From the results, it can be derived that a stronger relationship between the students and the

university is more fostered the more personalized the classroom is.

Table 4.​ ​Descriptive Statistics for Student-Faculty Ratio

Descriptive Statistics

Mean 11.54166667

Standard Error 0.700150904

Median 10.5

Mode 13

Standard Deviation 4.850787755

Sample Variance 23.53014184

Kurtosis -0.440337538

Skewness 0.581838493

Range 20

Minimum 3

Maximum 23

10
 Sum 554

Count 48

Table 4 illustrates the student-faculty ratio through descriptive statistics, which also

represents the amount of students per faculty member. From the data above, it can be derived

that the mean is approximately 11.5416666 and the median is 10.5. Since both the mean and

median are relatively near each other, there is a near-symmetrical distribution that can be

observed. Moreover, the average value amounts to 11.54 as the mode is at 13. Given that the

variance is greater than 1, it is considered high. The standard variation amounts to an estimated

4.85 and the sample variance is at 23.53. The range on the other hand is at 20. Considering the

results, it can be discerned that the alumni giving rate increases as the student-faculty ratio

decreases. It also entails that there is a weak relationship with the alumni giving.

Table 5. ​Descriptive Statistics for Alumni Giving Rate

Descriptive Statistics

Mean 29.27083333

Standard Error 1.940091114

Median 29

Mode 13

Standard Deviation 13.44134552

Sample Variance 180.6697695

Kurtosis -0.071942009

Skewness 0.370106739

Range 60

11
 Minimum 7

Maximum 67

Sum 1405

Count 48

As for Table 5, it utilizes the data from the forty-eight universities’ alumni giving rate.

The median amounts to 29, whereas the mean is at 29.27083333, and the mode, which comes out

as 13. It can be observed that the mean and median are of the same value, which entails that the

data set has no extreme outlier since the numbers are symmetrical. Moreover, the standard

deviation is valued at 13 and the sample variance amounts to an estimated 180.67. From this, it

can be derived that the data is scattered or spread out. Since it can also be observed that the range

is 60, the variance is relatively extreme since the amount is quite high.

b. ANOVA, Simple Linear, and Multiple Regression

Graph 1​. ​Alumni Giving Estimated Regression Equation (% of Classes Under 20, Alumni Giving

Rate)

12
 Based on Graph 1, the linear regression equation for the variables % of Classes Under 20

to the Alumni Giving Rate is y = 0.6578x - 7.3861, whereas the coefficient of determination is

0.4169. Since the value for the coefficient of determination is more than or equal to 0.4 and less

than 0.6, it signifies that there is a moderate relationship between the variables % of Classes

Under 20 and the Alumni Giving Rate.

Graph 2. ​Alumni Giving Estimated Regression Equation (Student-Faculty Ratio, Alumni Giving

Rate)

13
 Graph 2 portrays the linear regression equation for the variables Student-Faculty Ratio to

the Alumni Giving Rate. Based on the graph, the estimated linear regression equation is y =

-2.0572x + 53.014 whereas the coefficient of determination is 0.5512, which signifies that there

is a moderate relationship between the independent and dependent variable because the value for

the coefficient of determination is more than or equal to 0.4 and less than 0.6.

Table 6. ​Regression Statistics (% of Classes Under 20, Alumni Giving Rate)

Regression Statistics

Multiple R 0.645650419

R Square 0.416864464

Adjusted R Square 0.404187604

Standard Error 10.37522473

Observations 48

14
 Based on Table 6, it illustrates the regression statistics for the variables % of Classes

Under 20 to the Alumni Giving Rate. From the regression statistics, it can be determined that the

value for the R square is 0.4169, which means that there is a moderate relationship between the

variables % of Classes Under 20 to the Alumni Giving Rate. Besides, the value for the standard

error is 10.3752, which means that there is a high standard error. Thus, this states that the datas

are spread out over a large range of values and the data points are far from the mean of the

variables % of Classes Under 20 and the Alumni Giving Rate.

Table 7.​ ​ANOVA (% of Classes Under 20, Alumni Giving Rate)

df SS MS F Significance F

Regression 1 3539.795908 3539.795908 32.88389085 7.22812E-07

Residual 46 4951.683258 107.6452882

Total 47 8491.479167

Based on the ANOVA Table, the F-test will help in determining whether we should reject the

null hypothesis or accept the alternative hypothesis. From the given table above, since the value

of F is 32.88389085 and it is greater than the F critical value of 4.05, then we must reject the null

hypothesis.

Table 8.​ ​Estimated Regression Equation (% of Classes Under 20, Alumni Giving Rate)

Coefficients Standard Error t Stat P-value Lower 95% Upper 95%

Intercept -7.386067617 6.565472287 -1.124986489 0.266430663 -20.60167789 5.829542655

% of Classes 0.65776869 0.114704802 5.734447737 7.22812E-07 0.4268799 0.88865748

15
Table 8 introduces the estimated regression equation, which will help in determining the

relationship of the variable % of Classes Under 20 to the variable Alumni Giving Rate. The

p-value in the table is one of the possible aspects that will help in determining whether the null

hypothesis should be rejected. Since the p-value for the variable % of Classes Under 20 is

7.22812E-07, this states that the sample data has provided enough evidence to reject the null

hypothesis for the entire population because the p-value is less than the significance level (0.05).

Table 9.​ Regression Statistics (Student-Faculty Ratio, Alumni Giving Rate)

Regression Statistics

Multiple R 0.742397463

R Square 0.551153993

Adjusted R Square 0.541396472

Standard Error 9.102515793

Observations 48

Based on Table 9, it illustrates the regression statistics for the variables Student-Faculty

Ratio and the Alumni Giving Rate. From these summary, the researchers were able to determine

that the value for the R square is 0.5512, which means that there is a moderate relationship

between the variables Student-Faculty Ratio and the Alumni Giving Rate. Besides, the value for

the standard error is 9.1025, which means that there is a low standard deviation. Thus, it states

that the data points are clustered closely around the mean.

Table 10.​ ​ANOVA (Student-Faculty Ratio, Alumni Giving Rate)

16
 df SS MS F Significance F

Regression 1 4680.11265321629 4680.11265321629 56.485037922279 1.54423203237868E-09

Residual 46 3811.36651345038 82.8557937706605

Total 47 8491.47916666667

Based on the ANOVA Table, the F-test will help in determining whether we should reject the

null hypothesis or accept the alternative hypothesis. From the given table above, since the value

of F is 56.485037922279 and it is greater than the F critical value of 4.05, then we must reject

the null hypothesis.

Table 11.​ ​Estimated Regression Equation (Student-Faculty Ratio, Alumni Giving Rate)

Coefficients Standard t Stat P-value Lower 95% Upper 95%

Intercept 53.01382714 3.421450432 15.49454776 7.05881E-20 46.12680463 59.90084966

Student-Faculty -2.057154698 0.273716035 -7.515652861 1.54423E-09 -2.6081165 -1.506192897

relationship of the variable Student-Faculty Ratio to the variable Alumni Giving Rate. The

p-value in the table is one of the possible aspects that will help in determining whether the null

hypothesis should be rejected. Since the p-value for the variable Student-Faculty Ratio is

1.54423E-09, this states that the sample data has provided enough evidence to reject the null

hypothesis for the entire population because the p-value is less than the significance level (0.05).

17
 Table 12. ​Multiple Regression Statistics (% of Classes Under 20, Student-Faculty Ratio, Alumni

Giving Rate)

Regression Statistics

Multiple R 0.749226646

R Square 0.561340567

Adjusted R Square 0.541844593

Standard Error 9.09806748

Observations 48

Table 12 illustrates the regression statistics for the variables % of Classes Under 20,

Student-Faculty Ratio, and the Alumni Giving Rate. Based on the regression statistics, it can be

determined that the value for the R square is 0.5613, which means that there is a moderate

relationship between the variables % of Classes Under 20, Student-Faculty Ratio and the Alumni

Giving Rate. Besides, the value for the standard error is 9.0981, which means that there is a low

standard deviation. Thus, it states that the data points are clustered closely around the mean.

Table 13. ​Multiple Regression ANOVA (% of Classes Under 20, Student-Faculty Ratio, Alumni

Giving Rate)

df SS MS F Significance F

Regression 2 4766.611733 2383.305866 28.79263917 8.86887E-09

Residual 45 3724.867434 82.77483187

Total 47 8491.479167

18
 Based on the ANOVA Table, the F-test will help in determining whether we should reject the

null hypothesis or accept the alternative hypothesis. From the given table, since the value of F is

28.79263917 and it is greater than the F critical value of 3.20, then we must reject the null

hypothesis.

Table 14​. ​Multiple Regression Estimated Regression Equation (% of Classes Under 20,

Student-Faculty Ratio, Alumni Giving Rate)

Coefficients Standard t Stat P-value Lower 95% Upper 95%

Intercept 39.65558347 3.421450432 2.935802792 0.005224787 12.44992604 66.86124091

% of Classes 0.16616863 0.162552049 1.022248753 0.312127503 -0.161228004 0.493565263

Student-Faculty -1.702110272 0.442127127 -3.849820945 0.000370942 -2.592600016 -0.811620528

Table 14 introduces the estimated regression equation, which will help in determining the

relationship of the variable % of Classes Under 20, Student-Faculty Ratio to the variable Alumni

Giving Rate. The p-value in the table is one of the possible aspects that will help in determining

whether the null hypothesis should be rejected. Since the p-value for the variable % of Classes

Under 20 is 0.312127503, this states that there is insufficient evidence to conclude that a

non-zero correlation exists since the p-value is greater than the significance level, which is 0.05.

Besides, the p-value for the variable Student-Faculty Ratio is 0.000370942, which can be stated

that the sample data has provided enough evidence to reject the null hypothesis for the entire

population because the p-value is less than the significance level (0.05).

19
III. Management Implications

a. Conclusion

Alumni Giving is an important source of revenue for colleges and universities. There

were several variables used to measure the factors that affect the donations of the alumnus. In

this research linear relationships were formed between the dependent and independent variables.

The data values that were given proved to be close to each other without having any

outliers due to the mean being close to the median. During this research, both descriptive and

regression analysis was done in order to determine the strength of the relationship between the

variables and the alumni giving rate. In the regression statistics of multiple regression, it was

observed that the % under 20 student faculty ratio and graduation rate all had a direct effect on

the alumni giving rate because both possess strong linear relationships between the independent

and dependent variables as they both have significance levels less than 0.05. Also, the group has

deduced each independent variable that has a significant relationship to the dependent variable.

According to the data statistics, the alumni giving rate is based on the three values that we got;

y=-20.72 + the graduation rate of ​0.75 + the % of classes under 20, ​0.03 - ​the student faculty

ratio which is ​1.19​.

Among the two methods used, the difference between the results of the two are results of

the significance. The first method has a more comprehensive and accurate procedure to create a

correlation between more than 2 variables. While the other method can only measure its

relationship up to 2 variables only which makes it less accurate. Therefore we can say that we

have met the research objectives and problems as we have developed all the necessary tables and

methods to conduct and formulate statistical research about the variables that affect the giving

rate of alumnus. The null hypothesis should be rejected because the p value is less than alpha and

20
it should be concluded that there is a significant relationship between graduation and alumni

giving rate and that there is a significant relationship between graduation rate, % of classes under

20 and student faculty ratio to the alumni giving rate.

b. Recommendations

Since our research was limited to only three variables which affects the alumni giving

rate, we recommend to future researchers that they consider the many other factors that can

affect the alumni giving rate of universities. We can also recommend that more variables shall be

added to the data set such as sports teams, membership of student groups, the jobs of the

alumnis, social class of the alumnis, their college or tertiary education school, the distribution of

the population by the Alumni Association, the number of extracurricular activities provided to

increase the university satisfaction rate, and the rate of Alumni Donation. Adding more variables

could help make the data more accurate and more efficient. Also there is a need for a bigger

population and a test is necessary to provide a more accurate output to form a higher rate of

accuracy that was given to us. Another recommendation is to do the research in other schools/

universities so that you can compare between the data sets and conclude whether the relationship

of the variables are all the same throughout. We can also recommend schools to host more

alumni programs such as homecoming or other alumni events because this is one of the biggest

possible ways to engage alumnis into inter-school activities which may allow them to donate

more cash.

21
IV. References

Bruggink, T. H., & Siddiqui, K. (1995). An Econometric Model of Alumni Giving: A Case

Study for a Liberal Arts College. ​The American Economist,​ ​39(​ 2), 53–60.

https://doi.org/10.1177/056943459503900206

22