_____________________________________________________________________________________________
BUSI 410  Homework #5
Due 12/8/2009
There are three problems in this assignment. The first two problems are from the text
book. Each of these problems has multiple parts.
Problem 1: Case 93: Starbucks in China
, p. 272.
Read the case and, using the
Starbucks Revenue.xlsx
data set on Blackboard, do
the following analysis:
1) Use years 1991 through 2004 to build your model, i.e., hold out the two most
recent observations for validation and recalibration later.
2) First, choose a leading indicator to predict Starbucks revenues by choosing
between Chinese per capita GDP from two or three years prior.
3) Assess the model DurbinWatson statistic to discover whether or not
unaccounted for trend or cycles remain. Find the dL and dU values from the
website:
http://www.stanford.edu/~clint/bench/dw05a.htm
.
4) Next add either Starbucks revenues from two or three years prior as an inertia
driver. (Prior revenues reflect inertia in consumer behavior, or the tendency for
Starbucks customers to remain loyal, rather than switch to other coffee sources.)
5) Assess the model DurbinWatson statistic to discover whether or not
unaccounted for trend or cycles remain. Find the dL and dU values from the
website:
http://www.stanford.edu/~clint/bench/dw05a.htm
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Fall '09
 MASSA
 Statistics, Forecasting, Regression Analysis, Revenue, commercial vehicle sales

Click to edit the document details