Skip to main content
. Author manuscript; available in PMC: 2010 Jul 26.
Published in final edited form as: Stat Sin. 2009;19(4):1641–1663.

Figure 7.

Figure 7

Comparison of estimates based on the IMR prior with a Gaussian prior N (0, γI), and g-prior N (0, γ(X′X)−1), with γ = 1 and 106 for a data set with p = 100. When n ≥ p, estimates based on the IM prior had the lowest bias and MSE; while when n < p, they performed equally well as the N (0, I) prior.