{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# typosIMCR - Typos from the Og Christian P Robert...

This preview shows pages 1–3. Sign up to view the full content.

Typos from the ’Og Christian P. Robert October 10, 2011 Introducing Monte Carlo Methods with R 1. (Thanks to Kazue Ishida, Japanese translator of the book) The demos for chapters 2 and 5 do not work, due to an upgrade of R that invalidated my (much) older syntax. The demos should be fixed within the package mcsm any time soon. 2. (Thanks to Jerry Sin) On page 11, matrix summation in the matrix com- mands of Figure 1.2 should be matrix multiplication. 3. (Thanks to Liaosa Xu from Virginia Tech) On page 20, when we mention the uniform over the set ( a, b ) : y i ( a + bx i ) > log u i 1 - u i this set is missing (a) an intersection sign before the curly bracket and (b) a ( - 1) y i instead of the y i . It should be n \ i =1 ( a, b ) : ( - 1) y i ( a + bx i ) > log u i 1 - u i 4. (Thanks to Matthieu Gomez) In formula (2.1), the transform for the gamma G ) α, β ) distribution assumes β is a scale parameter, while the remainder of the book takes the opposite convention. 5. In Exercise 2.17, page 58, question d. should be d. Show that the maximum of b - a (1 - b ) a - α is attained at b = a/α . 6. In Exercise 2.21, page 59, in item (ii), || θ || should be replaced by λ and question b. should be removed. 7. On page 71, due to the late inclusion of an extra-exercise in the book, the above exercise in Exercise 3.5 actually means Exercise 3.3. 8. (Thanks to Brad McNeney, Simon Fraser University) The end of Example 3.6 (page 75) is missing a marginal estimate, i.e. there is a x (1 - x ) missing from m ( x ). It should have been obvious from the estimates we derived, 19 and 16, which do not even appear on the support of the posterior distribution represented on Figure 3.5. The R code is given as > mean(y[,1]*apply(y,1,f)/den)/mean(apply(y,1,h)/den) [1] 19.33745 > mean(y[,2]*apply(y,1,f)/den)/mean(apply(y,1,h)/den) [1] 16.54468 1

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
and should have been view source > mean(y[,1]*f(y)/den)/mean(f(y)/den) [1] 94.08314 > mean(y[,2]*f(y)/den)/mean(f(y)/den) [1] 80.42832 A similar modification applies to the remark after eqn. (3.7) (page 76): mean(apply(y,1,h)/den) should be mean(f(y)/den) 9. In Exercise 3.11, page 86, question c, a line got commented by mistake in the L A T E Xfile and it should read Explore the gain in efficiency from this method. Take a = 4 . 5 in part (a) and run an experiment to determine how many normal N (0 , 1) random variables would be needed to calculate P ( Z > 4 . 5) to the same accuracy obtained from using 100 random variables in this importance sampler. 10. (Thanks to Edward Kao, University of Houston) In Exercise 3.17, page 88, question b, it should be X | Y ∼ G a (1 , y ), not X | Y ∼ G a ( y, 1). 11. (Thanks to Kazue Ishida, Japanese translator of the book) In Example 4.4, the R code cannot run as provided and contains several mistakes. (a) in the remark of page 98, the second line of code should be > wachd[wachd<10^(-10)]=10^(-10) in order to eliminate all zeroes (b) in the code page 100, the negative log-perplexities should be put to zero: > plex[plex>0]=0 > plech[plech>0]=0 (this should come right after their definition)
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern