modTempEff (version 1.5.2)

seas: Specifying a smooth long term trend within a `modTempEff' model


Function employed within the tempeff formula to specify the variable with a smooth effect. The function does not fit the model, it simply returns information exploited by tempeff.


seas(x, ndx = stop("please, provide `ndx' in seas()"))


the long term trend variable
the apparent dimension (i.e. the rank) of the B-spline employed to model the long trend. For instance it could be min(40,n/4) where n is the time series length.


A list with relevant information.


The function is used within the formula of tempeff() when the long term trend of the daily time series is fitted via a smooth term. A standard P-spline with a cubic B-spline basis and a second-order difference penalty is employed.


Eilers, P., Marx, B. (1996). Flexible Smoothing with B-splines and Penalties Statistical Science 11, 89--121.

Wood, S.N. (2006) Generalized Additive Models: An Introduction with R. Chapman and Hall/CRC Press.

See Also

csdl, tempeff