I have got a stationery Markov chain distribution: ans = 0.1444 0.0456 0.0138 0.0126 0.0116 0.0107 0.0052 0.1444 0.0456 0.0138 0.0126 0.0116 0.0107 0.0052 0.1222 0.0386 0.0116 0.0106 0.0098 0.0091 0.0044 0.1444 0.0456 0.0138 0.0126 0.0116 0.0107 0.0052 0.1222 0.0386 0.0116 0.0106 0.0098 0.0091 0.0044 0.1889 0.0596 0.0180 0.0164 0.0151 0.0140 0.0067 0.1333 0.0421 0.0127 0.0116 0.0107 0.0099 0.0048 in which I would like to sample from. Using datasample(A,128) makes the output mostly zero all, or certain lines 1 all. If I wanna use the median/mean of the distribution, it will arise the same issue. Does anyone know of a way to sample a Markov chain distribution correctly?

how to sample a Markov chain distribution

Amir

8 Mär. 2016

0 Antworten

9 Ansichten (30 Tage)

Melden Sie sich an, um diese Frage zu beantworten.

Follow Question

Melden Sie sich an, um diese Frage zu beantworten.

Follow Question

Ältere Kommentare anzeigen

In MATLAB Online öffnen

0 Stimmen

I have got a stationery Markov chain distribution:

ans =
1444    0.0456    0.0138    0.0126    0.0116    0.0107    0.0052
1444    0.0456    0.0138    0.0126    0.0116    0.0107    0.0052
1222    0.0386    0.0116    0.0106    0.0098    0.0091    0.0044
1444    0.0456    0.0138    0.0126    0.0116    0.0107    0.0052
1222    0.0386    0.0116    0.0106    0.0098    0.0091    0.0044
1889    0.0596    0.0180    0.0164    0.0151    0.0140    0.0067
1333    0.0421    0.0127    0.0116    0.0107    0.0099    0.0048

in which I would like to sample from. Using

datasample(A,128)

makes the output mostly zero all, or certain lines 1 all. If I wanna use the median/mean of the distribution, it will arise the same issue. Does anyone know of a way to sample a Markov chain distribution correctly?