Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Modeling: Identification of change points #4

Open
kunalbhutani opened this issue May 6, 2015 · 3 comments
Open

Modeling: Identification of change points #4

kunalbhutani opened this issue May 6, 2015 · 3 comments

Comments

@kunalbhutani
Copy link
Contributor

To look at differences in trends that might indicative of a change. Find changepoint that show a difference in mean or variance after a time point.
@kunalbhutani
Copy link
Contributor Author

Using the R package: http://www.jstatsoft.org/v58/i03/paper

kunalbhutani added a commit that referenced this issue May 7, 2015
@kunalbhutani
Added changepoint code to calculate changepoints as related to mean, …
b594e42 
…variance or both mean and variance.

Look at http://www.jstatsoft.org/v58/i03/paper for more details.

Issue #4.
kunalbhutani added a commit that referenced this issue May 7, 2015
@kunalbhutani
Refactored changepoint code to play better with new loading code.
6c11129 
Issue #4
kunalbhutani added a commit that referenced this issue May 7, 2015
@kunalbhutani
Added code to look at change points for different scaling factors:
dc2a005 
1. Median scaled
2. Z-Scores
3. Log Transformed

The median scaled values are the ones that is used by Metabolomics and
is the most stable with this data as well. The output graphs can be seen
in analysis/metabolomics/05072015 .

Issue #4
@kunalbhutani
Copy link
Contributor Author

Example of Median Stability

run6-2-eicosatrienoylglycerophosphocholine -log
run6-2-eicosatrienoylglycerophosphocholine -median
run6-2-eicosatrienoylglycerophosphocholine -zscore

Example of Median Agreeing with Z-score instead of Raw

run6-2-hydroxyhippurate salicylurate -log
run6-2-hydroxyhippurate salicylurate -median
run6-2-hydroxyhippurate salicylurate -zscore

Since we are going to manually tagging these anyways, these distinctions might not matter.

@kunalbhutani
Copy link
Contributor Author

It would be interesting to see multivariate changepoints in terms of maybe certain pathways. This can be explored through another R-package: http://arxiv.org/pdf/1309.3295.pdf

@kunalbhutani kunalbhutani mentioned this issue May 8, 2015
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@kunalbhutani