16 reputation
1
bio website
location
age
visits member for 2 years, 7 months
seen Apr 25 '12 at 4:53

Apr
25
comment What is augmented data when simulating stochastic differential equations using Gibbs Sampler?
actually, a better question is, how is ${y}_{1}^{\*}$ related to ${y}_{1}$? My guess is, the latter is an initial value.
Apr
24
comment What is augmented data when simulating stochastic differential equations using Gibbs Sampler?
wait! Then, what would be ${\Delta}^{+}$ be? Since between ${y}_{1}$ and ${y}_{2}$ have M=20 points (i.e. augmented data). They are $y_{1,0}^{\*}$,...,$y_{1,M}^{\*}$
Apr
23
comment What is augmented data when simulating stochastic differential equations using Gibbs Sampler?
I guess they use M=20 so it is more accurate?
Apr
23
comment What is augmented data when simulating stochastic differential equations using Gibbs Sampler?
But, M=20 not 4, in the paper, page 6(page # is 276) bottom paragraph. btw, what is $\Delta$ with a cross sign on the top (that same paragraph), is that a plus sign?
Apr
23
comment What is augmented data when simulating stochastic differential equations using Gibbs Sampler?
thanks, that makes a lot of sense now. Just to confirm, in this case, since it's weekly data, so I am filling in 4 other days of the week.
Apr
23
comment What is augmented data when simulating stochastic differential equations using Gibbs Sampler?
What data augmentation is, is basically filling in missing values. Why are we filling in missing values/data augmenting? What's the point here?
Apr
23
comment What is augmented data when simulating stochastic differential equations using Gibbs Sampler?
Thanks for pointing that out, I should've digged into that paper.