Skip to main content
. 2001 Jun 15;69(1):159–178. doi: 10.1086/321279

Figure 4.

Figure 4

Posterior probability distribution of θ, generated by application of the MCMC algorithm to the data reported by Hästbacka et al. (1992), for five markers—EcoRI, TAGA, StyI, CA, and CCTT—when, for θ, either a uniform prior probability distribution (black line) or a prior distribution based on an HGS (gray bars) was used. Exons are indicated by vertical lines, introns by the thick unbroken horizontal lines, and both regulatory and nongenic regions by dotted horizontal lines at the top of the figure. The dotted horizontal line near the bottom of the figure indicates the cutoff for intervals to be included in the Bayesian 95% credible set of values for either posterior distribution. Proportions exceeding this cutoff are included in the credible set (analogous to the classic 95%CI). The mode (i.e., the most probable interval) and the second most probable interval of the posterior distribution, obtained by use of an HGS, together contain ∼22% of the iterations of the MCMC and cover a 7-kb region that includes the exon containing the DTD mutation.