diff --git a/docs/reference/GP.html b/docs/reference/GP.html new file mode 100644 index 00000000..e6b9f406 --- /dev/null +++ b/docs/reference/GP.html @@ -0,0 +1,116 @@ + +Specify dynamic Gaussian processes — GP • mvgam + Skip to contents + + +
+
+
+

Specify dynamic Gaussian processes

+ Source: R/gp.R +
GP.Rd
+
+ +
+

Set up low-rank approximate Gaussian Process trend models using Hilbert +basis expansions in mvgam. This function does not evaluate its arguments – +it exists purely to help set up a model with particular GP +trend models.

+
+ +
+

Usage

+ 
GP()
+
+ +
+

Value

+ + +

An object of class mvgam_trend, which contains a list of +arguments to be interpreted by the parsing functions in mvgam

+ + +
+
+

Details

+

A GP trend is estimated for each series using +Hilbert space approximate Gaussian Processes. +In mvgam, latent squared exponential GP trends are approximated using by +default 20 basis functions and using a multiplicative factor of c = 5/4, +which saves computational costs compared to fitting full GPs while adequately estimating +GP alpha and rho parameters.

+
+
+

See also

+

gp

+
+ +
+ + +
+ + + + + + + diff --git a/docs/reference/RW.html b/docs/reference/RW.html index 06c0a096..d7d3f489 100644 --- a/docs/reference/RW.html +++ b/docs/reference/RW.html @@ -1,8 +1,8 @@ -Specify autoregressive dynamic processes — RW • mvgamSpecify autoregressive dynamic processes — RW • mvgamDetails of formula specifications in mvgam — mvgam_formulae • mvgam + Skip to contents + + +
+
+
+

Details of formula specifications in mvgam

+ Source: R/mvgam_formulae.R +
mvgam_formulae.Rd
+
+ +
+

Details of formula specifications in mvgam

+
+ + +
+

Details

+

mvgam will accept an observation model formula and an optional +process model formula (via the argument trend_formula). Neither of these formulae can +be specified as lists, contrary to the accepted behaviour in some mgcv or brms models. +

+Note that it is possible to supply an empty formula where +there are no predictors or intercepts in the observation model (i.e. y ~ 0 or y ~ -1). +In this case, an intercept-only observation model will be set up but the intercept coefficient +will be fixed at zero. This can be handy if you wish to fit pure State-Space models where +the variation in the dynamic trend controls the average expectation, and/or where intercepts +are non-identifiable. +

+The formulae supplied to mvgam are exactly like those supplied to +glm except that smooth terms, s, +te, +ti and +t2, +time-varying effects using dynamic, as well as +Gaussian Process functions using gp, +can be added to the right hand side (and . is not supported in mvgam formulae). +

+Further details on specifying different kinds of smooth functions, and how to control their behaviours +by modifying their potential complexities and / or how the penalties behave, can be found in the +extensive documentation for the mgcv package.

+
+
+

See also

+

mvgam, +formula.gam, +gam.models, +jagam, +gam, +s, +formula

+
+
+

Author

+

Nicholas J Clark

+
+ +
+ + +
+ + + + + + + diff --git a/docs/reference/mvgam_trends.html b/docs/reference/mvgam_trends.html index 636f9844..2f2fa4d8 100644 --- a/docs/reference/mvgam_trends.html +++ b/docs/reference/mvgam_trends.html @@ -66,9 +66,9 @@

Details

AR(p = 1, 2, or 3)

  • VAR()(only available in Stan)

  • PW() (piecewise linear or logistic trends; only available in Stan)

    • -

  • 'GP' (Gaussian Process with squared exponential kernel; +

  • GP() (Gaussian Process with squared exponential kernel; only available in Stan)

    • -

    For all types apart from 'GP', moving average and/or correlated +

    For all types apart from GP() and PW(), moving average and/or correlated process error terms can also be estimated (for example, RW(cor = TRUE) will set up a multivariate Random Walk if data contains >1 series). Character strings can also be supplied instead of the various trend functions. The full list of possible models that are @@ -123,7 +123,7 @@

    References

    See also

    -

    RW, AR, VAR, PW

    +

    RW, AR, VAR, PW, GP