Matrix symmetry might depend on numerical precision issues. The older version of JAGS had a bug related to this issue for multivariate normal nodes. This simple function can fix the issue, but new JAGS versions do not require such intervention.

1 |

`x` |
A square matrix. |

The function takes the average as `(x[i, j] + x[j, i]) / 2`

for each off diagonal cells.

A symmetric square matrix.

The function works for any matrix, even for those not intended to be symmetric.

Peter Solymos, solymos@ualberta.ca

1 2 3 4 5 6 |

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.