This preview shows pages 1–3. Sign up to view the full content.
Case 32
Michelle Baker
GM 533 Applied Managerial Statistics
Professor davis
[email protected]
November 15, 2010
Executive Summary
In this case the objective is to determine whether or not the amount of days a bill is overdue is
related to the amount of the bill.
Quick Stab Collection Agency (QSCA) is a bill collector
located in an eastern town.
They avoid risky collections and tend to work with small accounts.
This is largely in part because they can be very profitable by buying a $60 debt for $10.
They
then send one letter than appears very official and tends to get a quick return on their investment.
As you will see by the calculations and statistical analysis performed, that the type of bill is the
best predictor of how many days overdue a bill will be.
Introduction
QSCA’s profitability relies largely on how quickly they collect a debt payoff and the size of the
bill.
Of course the discount rate is also a variable in relation to their profitability.
For reference
type 1 are residential accounts and type 2 are commercial accounts.
Based on a random sample
of closed accounts from January through June a data set was yielded to be analyzed.
The goal
would be to see if there is a relationship between number of days and the size of the bill.
The data set include three variables.
The dependent variable is days (Y).
The independent
variables are amount of bill (X
1
) and type of bill (X
2
).
The scatter plots give us a visual of the
relationship of the independent variables separately (Appendix A and Appendix B).
The first is
the graph of the number of days and the size of the bill.
As you can see there is not a positive or
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document negative relationship between the two variables.
The second graph is of the number of days and
the type of bill.
The slope indicates that there is a relationship between the type of bill and the
number of days the bill is overdue.
The following are the hypothesis that we would test for the multiple regression below.
Analysis and Methods
This is the end of the preview. Sign up
to
access the rest of the document.
This note was uploaded on 03/26/2012 for the course STATISTIC GM533 taught by Professor Henry during the Fall '10 term at Keller Graduate School of Management.
 Fall '10
 henry

Click to edit the document details