analyses:konstantopoulos2011
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revisionNext revisionBoth sides next revision | ||
analyses:konstantopoulos2011 [2020/05/01 14:01] – Wolfgang Viechtbauer | analyses:konstantopoulos2011 [2021/10/20 19:03] – Wolfgang Viechtbauer | ||
---|---|---|---|
Line 260: | Line 260: | ||
We can fit the same model using a multivariate parameterization, | We can fit the same model using a multivariate parameterization, | ||
<code rsplus> | <code rsplus> | ||
- | res.mv <- rma.mv(yi, vi, random = ~ factor(study) | district, data=dat) | + | res.mv <- rma.mv(yi, vi, random = ~ study | district, data=dat) |
print(res.mv, | print(res.mv, | ||
</ | </ | ||
Line 268: | Line 268: | ||
Variance Components: | Variance Components: | ||
- | outer factor: district | + | outer factor: district (nlvls = 11) |
- | inner factor: | + | inner factor: study (nlvls = 56) |
| | ||
Line 286: | Line 286: | ||
Signif. codes: | Signif. codes: | ||
</ | </ | ||
- | The '' | + | The '' |
As long as $\rho$ is estimated to be positive, the multilevel and multivariate parametrizations are in essence identical. In fact, the log likelihoods of the two models should be identical, which we can confirm with: | As long as $\rho$ is estimated to be positive, the multilevel and multivariate parametrizations are in essence identical. In fact, the log likelihoods of the two models should be identical, which we can confirm with: | ||
Line 348: | Line 348: | ||
Finally, for illustration purposes, it is instructive to examine what can happen when we fit an overparameterized model. For example, suppose we combine the multilevel and multivariate structures above in a single model: | Finally, for illustration purposes, it is instructive to examine what can happen when we fit an overparameterized model. For example, suppose we combine the multilevel and multivariate structures above in a single model: | ||
<code rsplus> | <code rsplus> | ||
- | res.op <- rma.mv(yi, vi, random = list(~ | + | res.op <- rma.mv(yi, vi, random = list(~ study | district, ~ 1 | district, ~ 1 | study), data=dat) |
print(res.op, | print(res.op, | ||
</ | </ | ||
Line 360: | Line 360: | ||
sigma^2.2 | sigma^2.2 | ||
- | outer factor: district | + | outer factor: district (nlvls = 11) |
- | inner factor: | + | inner factor: study (nlvls = 56) |
| |
analyses/konstantopoulos2011.txt · Last modified: 2022/08/22 16:00 by Wolfgang Viechtbauer