Errata for Multilevel and Longitudinal Modeling Using Stata
The errata for Multilevel and Longitudinal Modeling Using Stata are
provided below. Click here for an
explanation of how to read an erratum. Click here
to learn how to determine the printing number of a book.
(1)  Chapter 1, p. 20, third paragraph, third sentence 
In the top panel, 80% of this variance is due to subjects,
whereas in the bottom panel, 80% is due to withinsubject variability.

In the bottom panel, 80% of this variance is due to subjects,
whereas in the top panel, 80% is due to withinsubject variability.

(1)  Chapter 1, p. 23, fifth line 
(1)  Chapter 1, p. 29, exercise 1.5.2, line 2 
... components within and between raters.

... components within and between graders.

(1)  Chapter 1, p. 41, footnote 
(1), (2) 
Chapter 1, p. 47, second histogram command in the middle of the page 
histogram levm2 if time==1, normal xtitle(Standardized level2 residuals)

histogram lev2m1 if time==1, normal xtitle(Standardized level2 residuals)

(1)  Chapter 2, p. 54, exercise 2.5, number 3 
Plot mnw versus size, using different symbols for the two treatment groups.

Plot mnw versus size, using different symbols for the three treatment groups.

(1)  Chapter 2, p. 54, exercise 2.6, third variable in variable list 
(1)  Chapter 3, p. 60, commands at the bottom of the page 
. merge school using gcse

. sort school
. merge school using http://www.statapress.com/data/mlmus/gcse

(1), (2)  Chapter 3, p. 61, last line 
(1)  Chapter 3, p. 76, gllamm command line 
. gllamm gcse lrt, i(school) nrf(2) eqs(inter slope) ip(m) nip(15) from(a) copy

. gllamm gcse lrt, i(school) nrf(2) eqs(inter slope) ip(m) nip(15) adapt from(a) copy

(1)  Chapter 3, p. 89, gllamm command line 
. gllamm weight age2, nocons i(id) nrf(2) eqs(inter slope) ip(m) nip(15) from(a) geqs(r1 r2) adapt

. gllamm weight age2, nocons i(id) nrf(2) eqs(inter slope) ip(m) nip(15) geqs(r1 r2) adapt

(1)  Chapter 3, p. 95, exercise 3.1.4, second sentence 
Also obtain ML (or OLS) estimates of
and
by
first subtracting
with at least two observations.

Also obtain ML (or OLS) estimates of
and
first
by subtracting
and then by using the statsby
command for children with at least two observations.

(1)  Chapter 3, p. 97, exercise 3.4, fourth variable in level1 variable list 
Switch the order of exercises 3.5.4 and 3.5.5 so that you
“fit the randomcoefficient model” first.
(1)  Chapter 3, p. 99, exercise 3.6, third description in variable list 
age 14, number of years ...

age  14, number of years ...

(1)  Chapter 3, p. 100, exercise 3.8 
Using (3.2) and (3.3) and the estimates for Model 2 in table 3.1, ...

Using (3.2) and the estimates for Model 2 on page 76, ...

(1)  Chapter 4, p. 102, equation 4.1 
(1)  Chapter 4, p. 114, last line of Stata command 
Replace “Probability” with “Proportion”
so that the yaxis title in figure 4.7 is “Proportion
of onycholysis“.
(1)  Chapter 4, p. 120, last displayed equation 
(1)  Chapter 4, p. 129, fourth equation 
(1)  Chapter 4, p. 138, exercise 4.5.1, last line 
... by case (age), sort: gen lag=y[_n1].

... by case (age), sort: gen lag = wemp[_n1].

(1) 
Chapter 4, p. 140, exercise 4.7.2, space missing between nr and (year) 
... by nr(year), sort: gen lag = union[_n1].

... by nr (year), sort: gen lag = union[_n1].

(1)  Chapter 4, p. 142, exercise 4.9.1 
Estimate the values of the estimated schoolspecific regression ...

Guess the values of the estimated schoolspecific regression ...

(1)  Chapter 5, p. 154, equation (5.2) 
(2)  Chapter 5, p. 154, equation (5.2) 
(1)  Chapter 5, p. 156, table 5.1, estimate of kappa_1 from RCPOM 
(1) 
Chapter 5, p. 158, equation (5.3) and equation in sentence below equation (5.3) 
(1)  Chapter 5, p. 159, equation (5.4) 
(2)  Chapter 5, p. 159, equation (5.4) 
(1), (2)  Chapter 5, p. 167, section 5.11.1, 3rd equation 
(1)  Chapter 5, p. 178, exercise 5.4.1, line 3 
... with a random intercept for graders.

... with a random intercept for essays.

(2)  Chapter 6, p. 182, first equation 
(2)  Chapter 6, p. 190, chapter heading 
6. Randomintercept Poisson regression

6.8 Randomintercept Poisson regression

(2)  Chapter 6, p. 190, chapter subheading 
6. .1 Model specification

6.8.1 Model specification

(1)  Chapter 7, p. 227, table 7.1, log likelihood for model 4 
(1)  Chapter 7, p. 247, caption for figure 7.5 
(left panel: twostage formulation ...)

(left panel: threestage formulation ...)

(1)  Chapter 8, p. 261, line 1 
(1)  References, p. 304 and throughout the book 
Hedeker, D. and R. D. Gibbons. 1996a. Applied Longitudinal Data Analysis. Chichester,
UK: Wiley.

Hedeker, D. and R. D. Gibbons. Forthcoming. Applied Longitudinal Data Analysis. Chichester,
UK: Wiley.
