Linear Regression Report on Retention Rate and Graduation Rate in Online Colleges

SOUTHERN CROSS UNIVERSITY
ASSIGNMENT COVER SHEET
Student Name: Nitin Kataria
Student ID No.: 23147058
Unit Name: Economics and quantitative analysis
Unit Code: ECO82001
Tutor’s name: Michael Kortt
Assignment No.: 4
Assignment Title: Linear regression report
Due date: 11/02/2019
Date submitted: 10/02/2019
Declaration:
I have read and understand the Rules Relating to Awards (Rule 3 Section 18 – Academic
Misconduct Including Plagiarism) as contained in the SCU Policy Library. I understand the
penalties that apply for plagiarism and agree to be bound by these rules. The work I am
submitting electronically is entirely my own work.
Nitin
Kataria
Date: 10/02/2019

Purpose
This report aims at investigating the relationship between retention rate (RR) and graduation
rate (GR) in online colleges in the US. More specifically, the report uses data from Online
Edu with 29 online institutions in the US.
Background
The shifting nature of the American economy, high competition in the employment industry,
and the preference of employers for knowledgeable, skilled employees have influenced the
increase in the desire for higher education. There has been a significant increase in the need
for graduates with postsecondary qualifications over the last five decades. The high demand
for higher education has led to a corresponding increase in the number of organizations to
meet the demand (Baum, Kurose, and McPherson, 2013). This is in addition to the recent
growth of online universities. Despite the increase in the enrolment for higher education, few
students graduate and most of them drop out before completing the required period.
The study on the association between retention and graduation is significant because the
graduation rate gives insight into the number of students that completed their degrees in a
timely manner after enrolling. Additionally, it is a transparent metric useful in the
measurement of the quality of the school (Sanford, and Hunter, 2011).
Method
The research used data obtained from the OnlineEdu.xlsx on 29 online academic institutions
in the US. The total number of observations is 29, and two variables namely retention rate
(independent variable) and graduation rate (dependent rate); all are continuous variables. A
descriptive analysis was carried out in the form of mean, standard deviation, maximum and
minimum. To find out the connection between the studies variables, the researcher adopted a
correlation approach including a Personal correlation coefficient. The report also used a

scatter plot to visually examine the relation between the variables under study (Mukaka,
2012). A regression analysis was also used to ascertain the relation between the RR and GR.
Moreover, analysis of variance (ANOVA), a goodness of fit and hypothesis testing for the
slope was undertaken.
According to Sedgwick (2012), the Pearson correlation coefficient values range between 0
and 1. The nearer the value is to 0 the weaker the association, whereas the nearer the value
approaches 1, the stronger the association. R- Squared is the value of the goodness of fit and
also falls between 0 and 1. Similarly, the closer the value of the goodness of fit, the poor the
fit and a value closer to 1 shows strong goodness of fit. A 5% level of significance was used
in all the tests. All the data analysis was carried out using MS Excel Data Analysis Toolpak.
The hypothesis for the ANOVA is as shown below:
H0: Regression model is not significant
H1: Regression model is significant
The hypothesis testing for the slope is as indicated below:
H0: there is no variation between zero and the slope
H1: There is a variation between zero and the slope.
Results
Descriptive Analysis of RR and GR