Error variance specification in State-space models

[ErikG]

Hi,

Why are the variances for the errors in equations in State Space models specified as:

@state ... + [var=exp(c(1))]

and not just

@state ... + [var=c(1)]

is exp() here the exponential function? Is it to ensure non-negative variances?

Should one take the natural logarithm of the the estimated c(1) parameter in the first case in order to obtain the extimated variance of the error term?

Thanks,
Erik

[startz]

Hi,

Why are the variances for the errors in equations in State Space models specified as:

@state ... + [var=exp(c(1))]

and not just

@state ... + [var=c(1)]

is exp() here the exponential function? Is it to ensure non-negative variances?

Yes.

Should one take the natural logarithm of the the estimated c(1) parameter in the first case in order to obtain the extimated variance of the error term?

Nope, the estimated variance is exp(c(1)).