Home

Errata (2nd Edition)

To view tables and graphs referred to in the errata, please log in.

p. 20 Please ignore the second word in Chapter 2 ("Kare").
p. 49 Caption of Figure 3.2: third sentence should start with "A categorical outcome variable, if it is plotted, will appear on the categorical axis"
p. 146 Problem 7.1, part (a): add at the beginning "Consider the following customer: Age=40, Experience=10, Income=84, Family=2, CCAvg=2, Education_2=1, Education_3=0, Mortgage=0, Securities Account=0, CD Account=0, Online=1 and Credit card = 1."
p. 195 The term "log" refers to the natural logarithm (ln).
p. 207 Table 10.3 is not based on the correct dataset. The corrected table is: .
However, this table can be completely ignored without losing necessary information.
p. 230 Figure 11.4, bottom most table, the six 1 values in the "Predicted Class" column should be zeros. The rest of the output is correct (the error is due to an earlier output bug in XLMiner that has been fixed).
p. 277 Question 13.3, the first sentence should read "The data shown in Figure 13.7 and the output in Figure 13.8 are from a subset of a dataset on cosmetic purchases (Cosmetics-small.xls) given in binary matrix form."
p. 319 The residual plot in Figure 16.3 is incorrect. The correct figure is shown below:
p. 320 The term "log" used throughout the chapter refers to the natural logarithm (ln).
p. 335 Problem 16.1 part (d) - XLMiner now creates dummies for each category. The comment in parentheses should read: "(XLMiner will create 12 dummies; use only 11 and drop the April dummy)".
p. 335 Problem 16.1 part (f) should read: "Fit linear regression models to Air, Rail and to Auto with additive seasonality and an appropriate trend. For Air and Rail, fit a linear trend. For Rail, use a quadratic trend. Remember to use only pre-event data. Once the models are estimated, use them to forecast each of the three post-event series."
p. 340 Problem 16.6 part (b)(i) should read "which month tends to have the highest average sales during the year?".
p. 342 Problem 16.6 part (e) should read "Continuing with model B [with log(Sales) as output], create an ACF plot until lag 15 for the forecast errors. Now fit an AR model with lag 2 [ARIMA(2,0,0)] to the forecast errors."
p. 358 Problem 17.6 part (b) should open with: "The forecaster was tasked to generate forecasts for 4 quarters ahead. He therefore partitioned the data such that the last 4 quarters were designated as the validation period. The forecaster approached the forecasting task by using multiplicative Holt–Winter’s exponential smoothing..."
END ERRATA