sur: Simulated Data from Seemingly Unrelated Regressions

In SIN: A SINful Approach to Selection of Gaussian Graphical Markov Models

Description

The data are simulated from a bivariate seemingly unrelated regressions model with two response variables (Y_1, Y_2) and two covariates (X_1, X_2). The sample is only of size 8.

Usage

data(sur)

Format

A list providing a summary of the data. The list contains:

sur$means	:	the mean vector,
sur$stddev	:	the vector of standard deviations,
sur$corr	:	the correlation matrix, and
sur$n	:	the sample size.

Details

The data were used by Drton \& Richardson (2004) to illustrate the possibility of a multimodal likelihood in seemingly unrelated regressions.

Source

Drton, M. \& Richardson, T.S. (2004) Multimodality of the likelihood in the bivariate seemingly unrelated regressions model. Biometrika 91(2): 383-392.

Examples

data(sur)
sur$means
sur$stddev
sur$corr
sur$n

Example output

   X1    X2    Y1    Y2 
 0.49 -0.37  0.62  0.35 
  X1   X2   Y1   Y2 
0.91 1.93 1.60 4.01 
        X1      X2     Y1     Y2
X1  1.0000 -0.2957 0.7057 0.0814
X2 -0.2957  1.0000 0.2468 0.9120
Y1  0.7057  0.2468 1.0000 0.4840
Y2  0.0814  0.9120 0.4840 1.0000
[1] 8

SIN documentation built on May 2, 2019, 8:23 a.m.