All Questions
Tagged with sequence-analysis markov-chains
8
questions
1
vote
0
answers
45
views
Comparing log-loss values for a probabilistic suffix tree?
In the PST package one can estimate the prediction quality of individual sequences using the log-loss, e.g:
R> ex2 <- c("a-a-b", "a-b-a-a-b", "b-b-b-b-a")
R> ex2 <- seqdef(ex2)
R> ...
- 5,018
1
vote
1
answer
86
views
Meaning of lag parameter in PST?
In the pmine() function in PST you can use lags. What is this lag? Does it mean that it ignores the lag first positions in the sequence? Or does it mean that you allow for lags within the subsequences?...
- 5,018
1
vote
1
answer
55
views
What is the meaning of alpha in the context of an information gain pruning function?
In the PST package we use the value C as a cut-off for the information gain function used to prune the tree. The C value, for an alpha of 0.05 is calculated as follows:
C95 <- qchisq(0.95, 1) / 2
...
- 5,018
2
votes
1
answer
118
views
Fitting a VLMC to very long sequences
I am trying to fit a VLMC to a dataset where the longest sequence is 296 states. I do it as shown below:
# Load libraries
library(PST)
library(RCurl)
library(TraMineR)
# Load and transform data
x &...
- 5,018
2
votes
1
answer
98
views
Predicting conditional probabilities based on contexts with only 1 state
It seems that PST cannot predict the conditional probabilities of the next state after contexts which consist of a single state, e.g. EX-EX
Consider this code:
# Load libraries
library(RCurl)
...
- 5,018
2
votes
1
answer
57
views
Calculate lift for context-state relationship in a probabilistic suffix tree?
PST gives me probabilities and conditional probabilities for various contexts and following states. However, it would be very helpful to be able to calculate the lift (and its significance) of the ...
- 5,018
2
votes
1
answer
273
views
Where in the sequence of a Probabilistic Suffix Tree does "e" occur?
In my data there are only missing data (*) on the right side of the sequences. That means that no sequence starts with * and no sequence has any other markers after *. Despite this the PST (...
- 5,018
2
votes
2
answers
107
views
Getting log-likelihood from probabilistic suffix tree
Here is my code:
library(RCurl)
library(TraMineR)
library(PST)
x <- getURL("https://gist.githubusercontent.com/aronlindberg/08228977353bf6dc2edb3ec121f54a29/raw/...
- 5,018