Skip to main content
. Author manuscript; available in PMC: 2011 May 27.
Published in final edited form as: Ann Appl Stat. 2010;4(2):871–892. doi: 10.1214/09-AOAS297SUPPA

Fig 4.

Fig 4

Posterior distributions of log10 g for the FMR1 data. g in (A)–(D) is the scaled variance in the beta distribution assumed for (A) measurement error rate c (due to inappropriate bisulfite conversion); (B) failure of maintenance rate 1 − μ; (C) parent de novo rate δp and (D) daughter de novo rate δd. In (E), gm reflects deviation from the stationarity assumption. See Table 3 for guidelines on the interpretation of values of log10g. The y-axis in (C) has a wide range.