![]() ![]() On page 553, line -3: the text “the mean value of the jth biomarker among mice in the control group equals the mean value of the jth biomarker among mice in the treatment group” should say “the expected value of the jth biomarker among mice in the control group equals the expected value of the jth biomarker among mice in the treatment group”. Similarly, “mean blood pressure of mice in the treatment group” should say “the expected blood pressure of mice in the treatment group”. On page 553, line 14: the text “mean blood pressure of mice in the control group” should say “the expected blood pressure of mice in the control group”, to avoid confusion between sample mean and population mean. On the top of page 550, the text “can be obtaining by” should read “can be obtained by”. On page 536, the sentence “We now omit 20 entries in the 50 × 2 data matrix at random.” should read “We now omit 20 entries in the 50 × 4 data matrix at random.” Thanks to Tammo Ricklefs. ![]() On page 515, the sentence “Table 12.3 illustrates the setup” should say “Table 12.2 illustrates the setup”. On page 509, the sentence “Each principal component vector is unique, up to a sign flip.” should be replaced with “While in theory the principal components need not be unique, in almost all practical settings they are (up to sign flips).” Thanks to Michael Causey. On page 508, immediately under Figure 12.4, the variable name “UrbanPop” is misspelled as “UrpanPop”. On page 479, the denominator of the x-axis label for Figure 11.7 is missing a vertical bar “|”. R file on the Resources page for the corrected lab. See the Chapter 10 Jupyter notebook, Rmarkdown file, or. An introduction to statistical learning code#On pages 448 and 451: several code blocks require some small changes, because in keras 2.6.0, the function predict_classes() has been deprecated. ![]() Each of these least squares solutions gives zero error on the training data, but typically very poor test set performance due to extremely high variance.\footnote" On page 226, replace the text “the variance is infinite so the method cannot be used at all.” with the text “there are infinitely many solutions. On page 165, the 3rd column of Table 4.10 mentions a z-statistic. : In the paragraph before Section 4.5, the text should read “this data set has $n=10,000$ and $p=2$”. Predicted default status = Yes: 328 203 531 When Income is not included as a covariate, the 1st 2 rows of this table are as follows: However, earlier results in this chapter did not include Income as a covariate. , Table 4.9: this table results from including Income as a covariate. Predicted default status = Yes: 46 89 135 , Table 4.8: this table results from including Income as a covariate. On pages 156-158, some corrections are needed: On page 143, the footnote should mention (4.15), not (4.13). “ should read “The syntax lstat:age tells R to include an interaction term between lstat and age.” Thanks to Dwight Wynne. On page 116, the sentence “The syntax lstat:black tells R to include an interaction term between lstat and black. Thanks to Umberto Picchini and Denis Kazakov. ![]() On page 111, the variable "age" is actually "proportion of owner-occupied units built prior to 1940". The 2nd row should be labeled Region and the 3rd row should be labeled Region. On page 86, in Table 3.8, the model output for the “South” and “West” regions have been swapped. In the caption of Figure 2.2 on page 17, “Income” should be in units of $1,000, not units of $10,000. In Table 1.1 on page 14, the Credit data set involves information about credit card debt for 400 customers, not for 10,000 customers. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |