The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
In the present vignette, we want to discuss how to specify
multivariate multilevel models using brms. We call a
model multivariate if it contains multiple response variables,
each being predicted by its own set of predictors. Consider an example
from biology. Hadfield, Nutall, Osorio, and Owens (2007) analyzed data
of the Eurasian blue tit (https://en.wikipedia.org/wiki/Eurasian_blue_tit). They
predicted the tarsus
length as well as the
back
color of chicks. Half of the brood were put into
another fosternest
, while the other half stayed in the
fosternest of their own dam
. This allows to separate
genetic from environmental factors. Additionally, we have information
about the hatchdate
and sex
of the chicks (the
latter being known for 94% of the animals).
tarsus back animal dam fosternest hatchdate sex
1 -1.89229718 1.1464212 R187142 R187557 F2102 -0.6874021 Fem
2 1.13610981 -0.7596521 R187154 R187559 F1902 -0.6874021 Male
3 0.98468946 0.1449373 R187341 R187568 A602 -0.4279814 Male
4 0.37900806 0.2555847 R046169 R187518 A1302 -1.4656641 Male
5 -0.07525299 -0.3006992 R046161 R187528 A2602 -1.4656641 Fem
6 -1.13519543 1.5577219 R187409 R187945 C2302 0.3502805 Fem
We begin with a relatively simple multivariate normal model.
bform1 <-
bf(mvbind(tarsus, back) ~ sex + hatchdate + (1|p|fosternest) + (1|q|dam)) +
set_rescor(TRUE)
fit1 <- brm(bform1, data = BTdata, chains = 2, cores = 2)
As can be seen in the model code, we have used mvbind
notation to tell brms that both tarsus
and
back
are separate response variables. The term
(1|p|fosternest)
indicates a varying intercept over
fosternest
. By writing |p|
in between we
indicate that all varying effects of fosternest
should be
modeled as correlated. This makes sense since we actually have two model
parts, one for tarsus
and one for back
. The
indicator p
is arbitrary and can be replaced by other
symbols that comes into your mind (for details about the multilevel
syntax of brms, see help("brmsformula")
and vignette("brms_multilevel")
). Similarly, the term
(1|q|dam)
indicates correlated varying effects of the
genetic mother of the chicks. Alternatively, we could have also modeled
the genetic similarities through pedigrees and corresponding relatedness
matrices, but this is not the focus of this vignette (please see
vignette("brms_phylogenetics")
). The model results are
readily summarized via
Family: MV(gaussian, gaussian)
Links: mu = identity; sigma = identity
mu = identity; sigma = identity
Formula: tarsus ~ sex + hatchdate + (1 | p | fosternest) + (1 | q | dam)
back ~ sex + hatchdate + (1 | p | fosternest) + (1 | q | dam)
Data: BTdata (Number of observations: 828)
Draws: 2 chains, each with iter = 2000; warmup = 1000; thin = 1;
total post-warmup draws = 2000
Multilevel Hyperparameters:
~dam (Number of levels: 106)
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS
sd(tarsus_Intercept) 0.49 0.05 0.39 0.59 1.00 990
sd(back_Intercept) 0.25 0.07 0.10 0.39 1.01 520
cor(tarsus_Intercept,back_Intercept) -0.51 0.21 -0.91 -0.08 1.00 696
Tail_ESS
sd(tarsus_Intercept) 1327
sd(back_Intercept) 683
cor(tarsus_Intercept,back_Intercept) 876
~fosternest (Number of levels: 104)
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS
sd(tarsus_Intercept) 0.27 0.05 0.16 0.38 1.01 842
sd(back_Intercept) 0.35 0.06 0.24 0.46 1.00 655
cor(tarsus_Intercept,back_Intercept) 0.71 0.20 0.25 0.99 1.00 271
Tail_ESS
sd(tarsus_Intercept) 1128
sd(back_Intercept) 1256
cor(tarsus_Intercept,back_Intercept) 505
Regression Coefficients:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
tarsus_Intercept -0.40 0.07 -0.55 -0.27 1.00 1762 1720
back_Intercept -0.01 0.06 -0.13 0.11 1.00 3093 1676
tarsus_sexMale 0.77 0.06 0.66 0.88 1.00 3676 1450
tarsus_sexUNK 0.23 0.13 -0.03 0.49 1.00 4148 1472
tarsus_hatchdate -0.04 0.06 -0.16 0.07 1.00 1493 1599
back_sexMale 0.01 0.07 -0.12 0.14 1.00 3994 1662
back_sexUNK 0.15 0.15 -0.15 0.45 1.00 3393 1772
back_hatchdate -0.09 0.05 -0.19 0.01 1.00 2315 1746
Further Distributional Parameters:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
sigma_tarsus 0.76 0.02 0.72 0.80 1.00 2590 1583
sigma_back 0.90 0.03 0.86 0.95 1.00 3066 1576
Residual Correlations:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
rescor(tarsus,back) -0.05 0.04 -0.12 0.02 1.00 2367 1491
Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
and Tail_ESS are effective sample size measures, and Rhat is the potential
scale reduction factor on split chains (at convergence, Rhat = 1).
The summary output of multivariate models closely resembles those of
univariate models, except that the parameters now have the corresponding
response variable as prefix. Within dams, tarsus length and back color
seem to be negatively correlated, while within fosternests the opposite
is true. This indicates differential effects of genetic and
environmental factors on these two characteristics. Further, the small
residual correlation rescor(tarsus, back)
on the bottom of
the output indicates that there is little unmodeled dependency between
tarsus length and back color. Although not necessary at this point, we
have already computed and stored the LOO information criterion of
fit1
, which we will use for model comparisons. Next, let’s
take a look at some posterior-predictive checks, which give us a first
impression of the model fit.
This looks pretty solid, but we notice a slight unmodeled left
skewness in the distribution of tarsus
. We will come back
to this later on. Next, we want to investigate how much variation in the
response variables can be explained by our model and we use a Bayesian
generalization of the \(R^2\)
coefficient.
Estimate Est.Error Q2.5 Q97.5
R2tarsus 0.4349759 0.02335079 0.3852365 0.4780449
R2back 0.1999334 0.02743501 0.1444006 0.2507715
Clearly, there is much variation in both animal characteristics that we can not explain, but apparently we can explain more of the variation in tarsus length than in back color.
Now, suppose we only want to control for sex
in
tarsus
but not in back
and vice versa for
hatchdate
. Not that this is particular reasonable for the
present example, but it allows us to illustrate how to specify different
formulas for different response variables. We can no longer use
mvbind
syntax and so we have to use a more verbose
approach:
bf_tarsus <- bf(tarsus ~ sex + (1|p|fosternest) + (1|q|dam))
bf_back <- bf(back ~ hatchdate + (1|p|fosternest) + (1|q|dam))
fit2 <- brm(bf_tarsus + bf_back + set_rescor(TRUE),
data = BTdata, chains = 2, cores = 2)
Note that we have literally added the two model parts via
the +
operator, which is in this case equivalent to writing
mvbf(bf_tarsus, bf_back)
. See
help("brmsformula")
and help("mvbrmsformula")
for more details about this syntax. Again, we summarize the model
first.
Family: MV(gaussian, gaussian)
Links: mu = identity; sigma = identity
mu = identity; sigma = identity
Formula: tarsus ~ sex + (1 | p | fosternest) + (1 | q | dam)
back ~ hatchdate + (1 | p | fosternest) + (1 | q | dam)
Data: BTdata (Number of observations: 828)
Draws: 2 chains, each with iter = 2000; warmup = 1000; thin = 1;
total post-warmup draws = 2000
Multilevel Hyperparameters:
~dam (Number of levels: 106)
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS
sd(tarsus_Intercept) 0.48 0.05 0.39 0.58 1.00 623
sd(back_Intercept) 0.25 0.07 0.11 0.39 1.01 339
cor(tarsus_Intercept,back_Intercept) -0.49 0.23 -0.94 -0.04 1.01 343
Tail_ESS
sd(tarsus_Intercept) 1065
sd(back_Intercept) 856
cor(tarsus_Intercept,back_Intercept) 439
~fosternest (Number of levels: 104)
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS
sd(tarsus_Intercept) 0.27 0.05 0.16 0.38 1.01 603
sd(back_Intercept) 0.34 0.06 0.22 0.46 1.01 475
cor(tarsus_Intercept,back_Intercept) 0.66 0.21 0.21 0.98 1.01 205
Tail_ESS
sd(tarsus_Intercept) 1019
sd(back_Intercept) 1064
cor(tarsus_Intercept,back_Intercept) 313
Regression Coefficients:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
tarsus_Intercept -0.41 0.07 -0.54 -0.28 1.00 982 1116
back_Intercept 0.00 0.05 -0.10 0.10 1.00 1364 1291
tarsus_sexMale 0.77 0.06 0.66 0.88 1.00 2445 1291
tarsus_sexUNK 0.23 0.13 -0.03 0.48 1.00 2276 1607
back_hatchdate -0.08 0.05 -0.19 0.02 1.00 1263 1527
Further Distributional Parameters:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
sigma_tarsus 0.76 0.02 0.72 0.80 1.00 1862 1583
sigma_back 0.90 0.03 0.85 0.95 1.00 2497 1220
Residual Correlations:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
rescor(tarsus,back) -0.05 0.04 -0.12 0.02 1.00 1939 1486
Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
and Tail_ESS are effective sample size measures, and Rhat is the potential
scale reduction factor on split chains (at convergence, Rhat = 1).
Let’s find out, how model fit changed due to excluding certain effects from the initial model:
Output of model 'fit1':
Computed from 2000 by 828 log-likelihood matrix.
Estimate SE
elpd_loo -2125.3 33.5
p_loo 175.5 7.3
looic 4250.6 67.0
------
MCSE of elpd_loo is NA.
MCSE and ESS estimates assume MCMC draws (r_eff in [0.4, 2.0]).
Pareto k diagnostic values:
Count Pct. Min. ESS
(-Inf, 0.7] (good) 827 99.9% 102
(0.7, 1] (bad) 1 0.1% <NA>
(1, Inf) (very bad) 0 0.0% <NA>
See help('pareto-k-diagnostic') for details.
Output of model 'fit2':
Computed from 2000 by 828 log-likelihood matrix.
Estimate SE
elpd_loo -2125.9 33.7
p_loo 175.6 7.5
looic 4251.8 67.5
------
MCSE of elpd_loo is NA.
MCSE and ESS estimates assume MCMC draws (r_eff in [0.4, 1.7]).
Pareto k diagnostic values:
Count Pct. Min. ESS
(-Inf, 0.7] (good) 824 99.5% 135
(0.7, 1] (bad) 4 0.5% <NA>
(1, Inf) (very bad) 0 0.0% <NA>
See help('pareto-k-diagnostic') for details.
Model comparisons:
elpd_diff se_diff
fit1 0.0 0.0
fit2 -0.6 1.3
Apparently, there is no noteworthy difference in the model fit.
Accordingly, we do not really need to model sex
and
hatchdate
for both response variables, but there is also no
harm in including them (so I would probably just include them).
To give you a glimpse of the capabilities of brms’
multivariate syntax, we change our model in various directions at the
same time. Remember the slight left skewness of tarsus
,
which we will now model by using the skew_normal
family
instead of the gaussian
family. Since we do not have a
multivariate normal (or student-t) model, anymore, estimating residual
correlations is no longer possible. We make this explicit using the
set_rescor
function. Further, we investigate if the
relationship of back
and hatchdate
is really
linear as previously assumed by fitting a non-linear spline of
hatchdate
. On top of it, we model separate residual
variances of tarsus
for male and female chicks.
bf_tarsus <- bf(tarsus ~ sex + (1|p|fosternest) + (1|q|dam)) +
lf(sigma ~ 0 + sex) + skew_normal()
bf_back <- bf(back ~ s(hatchdate) + (1|p|fosternest) + (1|q|dam)) +
gaussian()
fit3 <- brm(
bf_tarsus + bf_back + set_rescor(FALSE),
data = BTdata, chains = 2, cores = 2,
control = list(adapt_delta = 0.95)
)
Again, we summarize the model and look at some posterior-predictive checks.
Family: MV(skew_normal, gaussian)
Links: mu = identity; sigma = log; alpha = identity
mu = identity; sigma = identity
Formula: tarsus ~ sex + (1 | p | fosternest) + (1 | q | dam)
sigma ~ 0 + sex
back ~ s(hatchdate) + (1 | p | fosternest) + (1 | q | dam)
Data: BTdata (Number of observations: 828)
Draws: 2 chains, each with iter = 2000; warmup = 1000; thin = 1;
total post-warmup draws = 2000
Smoothing Spline Hyperparameters:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
sds(back_shatchdate_1) 1.94 1.06 0.21 4.40 1.00 359 402
Multilevel Hyperparameters:
~dam (Number of levels: 106)
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS
sd(tarsus_Intercept) 0.47 0.05 0.38 0.58 1.00 628
sd(back_Intercept) 0.23 0.07 0.09 0.38 1.01 312
cor(tarsus_Intercept,back_Intercept) -0.54 0.22 -0.95 -0.09 1.01 414
Tail_ESS
sd(tarsus_Intercept) 1053
sd(back_Intercept) 666
cor(tarsus_Intercept,back_Intercept) 646
~fosternest (Number of levels: 104)
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS
sd(tarsus_Intercept) 0.26 0.06 0.16 0.38 1.00 554
sd(back_Intercept) 0.32 0.06 0.20 0.43 1.00 515
cor(tarsus_Intercept,back_Intercept) 0.67 0.22 0.16 0.98 1.04 147
Tail_ESS
sd(tarsus_Intercept) 961
sd(back_Intercept) 879
cor(tarsus_Intercept,back_Intercept) 253
Regression Coefficients:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
tarsus_Intercept -0.41 0.07 -0.54 -0.28 1.00 882 1217
back_Intercept 0.00 0.05 -0.10 0.11 1.00 1234 1355
tarsus_sexMale 0.77 0.06 0.66 0.88 1.00 2952 1532
tarsus_sexUNK 0.22 0.12 -0.02 0.44 1.00 2403 1594
sigma_tarsus_sexFem -0.30 0.04 -0.38 -0.22 1.00 2462 1539
sigma_tarsus_sexMale -0.25 0.04 -0.33 -0.16 1.00 2611 1479
sigma_tarsus_sexUNK -0.40 0.13 -0.65 -0.15 1.00 1906 1635
back_shatchdate_1 -0.24 3.07 -6.02 6.72 1.00 1074 1215
Further Distributional Parameters:
Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
sigma_back 0.90 0.03 0.85 0.95 1.01 2505 1438
alpha_tarsus -1.22 0.45 -1.87 0.12 1.00 1297 446
Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
and Tail_ESS are effective sample size measures, and Rhat is the potential
scale reduction factor on split chains (at convergence, Rhat = 1).
We see that the (log) residual standard deviation of
tarsus
is somewhat larger for chicks whose sex could not be
identified as compared to male or female chicks. Further, we see from
the negative alpha
(skewness) parameter of
tarsus
that the residuals are indeed slightly left-skewed.
Lastly, running
reveals a non-linear relationship of hatchdate
on the
back
color, which seems to change in waves over the course
of the hatch dates.
There are many more modeling options for multivariate models, which
are not discussed in this vignette. Examples include autocorrelation
structures, Gaussian processes, or explicit non-linear predictors (e.g.,
see help("brmsformula")
or
vignette("brms_multilevel")
). In fact, nearly all the
flexibility of univariate models is retained in multivariate models.
Hadfield JD, Nutall A, Osorio D, Owens IPF (2007). Testing the phenotypic gambit: phenotypic, genetic and environmental correlations of colour. Journal of Evolutionary Biology, 20(2), 549-557.
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.