simulation.generation.data: Generate simulation data
In MokyoZhou/lassoenet: An Interactive Implementation of Penalised Regressions

Description Usage Arguments Value Details Author(s) Examples

This function generates data for the simulation studies. This function is extremely adaptive and allows for many different data set ups. The function offers variability on: dimension of the data.frame, user-defined coefficient vector, 2 types of correlation matrixs, different correlation levels, varation of the model error sigma and the option to split the data.frame into a training and a testing set.

1 2	simulation.generation.data(n = n, coeff = coeff, matrix.option = 1, collinear = collinear, sig = sig, split.prop = 0.8, option = 1)

`n`	The number of rows in the `data.frame`
`coeff`	A vector a true coefficients
`matrix.option`	1: Using an Exchangeable correlation matrix to simulate the predictors 2: Using an Autoregressive correlation matrix to simulate the predictors
`collinear`	The correlation levels within the `matrix.option`
`sig`	The model inherent error, the σ^2
`split.prop`	An element specifying the training proportion. Note the testing proportion will be 1 - the training proportion.
`option`	1: split the dataset according to `c(split.prop, 1 - split.prop)` 2: Use the whole dataset. Note When `option = 2`, the `split.prop` will be ignored

A list of elements:

`ytrain`	return ONLY when `option = 1`, this is the training proportion for y
`xtrain`	return ONLY when `option = 1`, this is the training set for the predictors
`ytest`	return ONLY when `option = 1`, this is the testing proportion for y
`xtest`	return ONLY when `option = 1`, this is the testing proportion for the predictors
`resample.data`	return ONLY when `option = 2`, this is the whole dataset

This is the data generating function for the simulation functions: simulation.collinear and simulation.adlasso

Mokyo Zhou

#100 observations, true coefficient vector is c(1,2,3,4), using the exchangeable correlation matrix,
#correlation level within the exchangeable matrix is 0.3, model sigma is 2, splitting
#the dataset into 0.8/0.2.
result <- simulation.generation.data(n = 100, coeff = c(1,2,3,4), matrix.option = 1,
collinear = 0.3, sig = 2,split.prop = 0.8, option = 1)