Two different models were tested: a global organizational justice model (with and without
correlated measurement errors) and a differentiated (distributive, procedural and interactional organizational justice)... justice model (with and without
correlated measurement errors).
Not exact matches
Measurement and sampling
errors (derived in part 1) are larger than in previous analyses of SST because they include the effects of
correlated errors in the observations.
But whatever the
measurement error is, the way I treat processing Tmin and Tmax, I have half the
error they have because Tmin and Tmax are not
correlated, so Tavg as 2
errors, and Tmin day1 is
correlated to Tmin day 2.
There was no way to
correlate climate changes in different parts of the world down to the exact century, since carbon - 14
measurements still had a wide range of
error and other dating techniques were worse.
Modification indices for covariances among
measurement errors suggested that allowing the items «run one or more red lights» and «speed through a yellow light» to
correlate would substantially improve the model fit (and it also made sense conceptually that these two items were related).
However, we recommend that researchers control the
measurement errors (e.g.,
correlated residuals between items) before conducting further analysis.
Errors of
measurements (not depicted) were allowed to
correlate at a given time point.
We allowed
errors for corresponding scores on relationships with mothers and fathers separately to
correlate over the
measurement waves, in order to reduce reporter bias.