refund (version 0.1-1)

pffrSim: Simulate example data for pffr

Description

Simulates example data for pffr. Scenario "all" generates data from a complex multivariate model $Y_i(t) = \mu(t) + \int X_{1i}(s)\beta_1(s,t)ds + \int X_{2i}(s)\beta_2(s,t)ds + xlin \beta_3(t) + f(xte1, xte2) + f(xsmoo, t) + \beta_4 xconst + \epsilon_i(t)$. Scenarios "int", "ff", "te", "smoo", "lin", "const" generate data from simpler models containing only the respective term(s) in the model equation given above. Specifiying a vector-valued scenario will generate data from a combination of the respective terms. See source code for details. Sparse/irregular response trajectories can be generated by setting propmissing to something greater than 0 (and smaller than 1). The return object then also includes a ydata-item with the sparsified data.

Usage

pffrSim(scenario = "all", n = 100, nxgrid = 40, nygrid = 60, SNR = 10,
  propmissing = 0)

Arguments

scenario

see description

n

number of observations

nxgrid

number of evaluation points of functional covariates

nygrid

number of evaluation points of the functional response

SNR

the signal-to-noise ratio for the generated data: empirical variance of the additive predictor divided by variance of the errors.

propmissing

proportion of missing data in the response, default = 0. See Details.

Value

• a named list with the simulated data, and the true components of the predictor etc as attributes.