generate_mpredcc: Generate data from Mean and Predictor Covariance-Connected...
In koekvall/mpredcc: Fully Likelihood-based Principal Components Regression

Generate data from Mean and Predictor Covariance-Connected (MPREDCC) regression model; iid or autoregressive structures supported.

1
2
3

generate_mpredcc(n = 100, alpha, Psi, ssy = 1, ssx = 1, mu_Y = 0,
  mu_X = rep(0, ncol(Psi)), a = NULL, A = NULL, Y_start = NULL,
  X_start = NULL)

`n`	The number of observations to generate.
`alpha`	The p-vector of coefficients such that beta = Psi x alpha.
`Psi`	A p x p SPSD matrix of rank k giving the predictor covariance structure.
`ssy`	Noise variance for response
`ssx`	Noise variance for predictors
`mu_Y`	Mean parameter for responses
`mu_X`	Mean parameter for predictors
`a`	Vector of autoregressive parameters for the response, first element is first lag
`A`	Matrix of autoregressive parameters for the predictors, first p rows is for the first lag
`Y_start`	Starting values if autoregressive responses; default to zeros
`X_start`	Starting values if autoregressive predictors; default to zeros