gam.fun: Train generalized additive models
In xqnwang/fuma: Forecast uncertainty based on model averaging (FUMA)

Description Usage Arguments Value Examples

Fit a generalized additive model(GAM) for data to capture the relationship between the relationship between the X and each column of Y.

1	gam.fun(X, Y, LogY = TRUE, k = 10, parallel = FALSE, num.cores = 2)

`X`	a dataframe with `n` rows and `c` columns, where `n` is the number of observations and `c` is the number of explanatory variables.
`Y`	a dataframe with `n` rows and `F` columns. Each column is considered as a response variable to fit the generalized additive model.
`LogY`	logical. If `TRUE` then the logarithmic form of `Y` becomes the response variable.
`k`	the dimension of the basis used to represent the smooth term when `mgcv` package is used to fit GAM. If `k` is not specified then basis specific defaults are used.
`parallel`	logical. If `TRUE` then the model training is conducted in parallel.
`num.cores`	the specified amount of parallel processes to be used if parallel = TRUE.

gam.fun returns a list with F generalized additive models for each response variable.

1
2
3

X <- as.data.frame(state.x77[, "Murder"])
Y <- as.data.frame(state.x77[, c("Population", "Illiteracy", "Income", "Frost")])
gam.fit <- gam.fun(X, Y, LogY = FALSE, k = 10)