Prev | Next | data_like |
data_id
.
minimum_meas_cv
be the integrand table
minimum_meas_cv
corresponding to
this integrand @(@
I_i
@)@.
Let meas_std
and meas_value
correspond to this data table
data_id
.
The minimum cv standard deviation is defined by
@(@
\Delta_i =
@)@
max(meas_std, minimum_meas_cv * |meas_value| )
node_id
for each data point determines the random effects for
child data
.
Note that there are no random effects for
parent data
.
This corresponds to @(@
u = 0
@)@.
data_id
.
meas_noise
.
We use @(@
K_i
@)@ to denote the corresponding set of
covariate_id
values for
which this is the case.
meas_noise_effect
is add_std_scale_none
(add standard deviations and no scaling)
the adjusted standard deviation is
@[@
\delta_i ( \theta ) = \sigma_i + E_i (\theta)
@]@
meas_noise_effect
is add_std_scale_log
(add standard deviations and only scale log density cases)
the adjusted standard deviation is
@[@
\delta_i ( \theta ) = \left\{ \begin{array}{ll}
\sigma_i [ 1 + E_i (\theta) ] & \R{if \; log \; density} \\
\sigma_i + E_i (\theta) & \R{otherwise}
\end{array} \right.
@]@
add_std_scale_all
(add standard deviations and scale all cases)
the adjusted standard deviation is
@[@
\delta_i ( \theta ) = \sigma_i [ 1 + E_i (\theta) ]
@]@
meas_noise_effect
is add_var_scale_none
(add variances and no scaling)
the adjusted standard deviation is
@[@
\delta_i ( \theta ) = \sqrt{ \sigma_i^2 + E_i (\theta) }
@]@
meas_noise_effect
is add_var_scale_log
(add variances and only scale log density cases)
the adjusted standard deviation is
@[@
\delta_i ( \theta ) = \left\{ \begin{array}{ll}
\sigma_i \sqrt{ 1 + E_i (\theta) } & \R{if \; log \; density} \\
\sqrt{ \sigma_i^2 + E_i (\theta) } & \R{otherwise}
\end{array} \right.
@]@
meas_noise_effect
is add_var_scale_all
(add variances and scale all cases)
the adjusted standard deviation is
@[@
\delta_i ( \theta ) = \sigma_i \sqrt{ 1 + E_i (\theta) }
@]@