Technical Appendix to: A New Model of Trend Ination

This appendix develops a posterior simulation algorithm for AR-trend-bound: the bounded ination model given in (5). The other models are restricted special cases of this model and, thus, the MCMC algorithm is re-stricted in the obvious manner in each case. The one exception of this is the UC-SV model of Stock and Watson (2007), which we label Trend-SV in the paper. This involves one extra state equation for the stochastic volatility in the ination de\u85ning trend ination. This is drawn using the stochastic volatility described in this appendix. Except for the parameters a and b, the prior is described in Section 3.2. The priors for a and b are assumed to be uniform on the intervals (a; a) and (b; b) respectively, where a = 0, a = 1:5, b = 3:5 and b = 5. The MCMC algorithm sequentially draw from (we suppress the depen-dence on y0): 1. p( j y; ; h; ); 2. p( j y; ; h; ); The views expressed in this paper are those of the authors and do not necessarily reect the views of the Federal Reserve Bank of New York or the Federal Reserve System