Take the 2-minute tour ×
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It's 100% free, no registration required.

I was reading this book related to Kalman filters and I didn't understand a couple of things. I have also attached the screenshot of the pages from the book where I had confusion.

The book is Shumway, R.H. and Stoffer, D.S. Time Series Analysis and Its Applications: With R Examples

From the first page, I didn't understand how this was derived

enter image description here

I mean how come we have $p(x_t|x_{t-1}) = f_w(x_t-\phi_{x_{t-1}})$ and has mean 0 and covariance Q. I mean it should be for the $w_t$ which has mean 0 and covariance Q not $p(x_t|x_{t-1})$

From the second page, I didn't understand the following

enter image description here

I mean obviously $p(\mu_t|Y_{t-1} => N(\mu_t^{t-1},P_t^{t-1}))$. But I didn't get how we get that from the integral

From the third page, I didn't get how this was derived

enter image description here

I know I might be asking a lot, but I have spent several days to exactly grasp the derivation of the equations in Kalman filters. I would really appreciate if someone could help me. Thanks in advance

enter image description here

enter image description here

enter image description here

share|improve this question
1  
Your post is on a border of quotation abuse; please give attribution to the book author. –  mbq Jan 4 '13 at 14:27

1 Answer 1

Regarding your first question, $x_t|x_{t-1}$ has the same variance as $w_t$; if in the transition equation $x_t = \Phi x_{t-1} + w_t$ you hold $x_{t-1}$ fixed, the only source of variance in $x_t$ is just $w_t$.

share|improve this answer
    
Yeah $w_t$ and $x_t$ have same variance. But the mean is different. So we can only say that the variance is equal not the distribution of $x_t$ and $w_t$ itself. So how can we write $p(x_t|x_{t-1})= f_w$ –  user34790 Jan 4 '13 at 23:32

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.