Registration for a live webinar on 'Neuroleptic malignant syndrome' is now open.
See webinar detailsWe noted you are experiencing viewing problems
-
Check with your IT department that JWPlatform, JWPlayer and Amazon AWS & CloudFront are not being blocked by your network. The relevant domains are *.jwplatform.com, *.jwpsrv.com, *.jwpcdn.com, jwpltx.com, jwpsrv.a.ssl.fastly.net, *.amazonaws.com and *.cloudfront.net. The relevant ports are 80 and 443.
-
Check the following talk links to see which ones work correctly:
Auto Mode
HTTP Progressive Download Send us your results from the above test links at access@hstalks.com and we will contact you with further advice on troubleshooting your viewing problems. -
No luck yet? More tips for troubleshooting viewing issues
-
Contact HST Support access@hstalks.com
-
Please review our troubleshooting guide for tips and advice on resolving your viewing problems.
-
For additional help, please don't hesitate to contact HST support access@hstalks.com
We hope you have enjoyed this limited-length demo
This is a limited length demo talk; you may
login or
review methods of
obtaining more access.
Printable Handouts
Navigable Slide Index
- Introduction
- Eye-ball your data!
- R session: visualization methods
- More than two dimensions
- Principal component analysis and visualization
- Matrix decomposition with SVD
- Matrix dimensions
- Example data: Italian wines
- PCA score plots
- Loading plots - I
- Loading plots - II
- Biplots
- Scaling
- How many components in a PCA? scree plots
- R session: PCA
- PCA QC example I
- PCA QC example II - batch correction
- Finding differences between groups - t tests
- Finding differences between groups - PCA
- PCA on the spiked-apple data
- Finding differences between groups - PLSDA
- Fitting a PLS(DA) model
- Interpretation of PLS models - spike-in data
- Alternatives
- R session: PLS
- Data fusion
- Useful R packages
- Conclusions
- Acknowledgements
Topics Covered
- Principal Component Analysis (PCA)
- PLS and PLSDA
- Class discrimination
- Variable selection
Links
Series:
Categories:
Therapeutic Areas:
Talk Citation
Wehrens, R. (2023, July 6). Multivariate statistics and metabolomics [Video file]. In The Biomedical & Life Sciences Collection, Henry Stewart Talks. Retrieved October 14, 2024, from https://doi.org/10.69645/ULUZ4936.Export Citation (RIS)
Publication History
Financial Disclosures
- Dr. Ron Wehrens has not informed HSTalks of any commercial/financial relationship that it is appropriate to disclose.
Other Talks in the Series: Bioinformatics for Metabolomics
Transcript
Please wait while the transcript is being prepared...
0:00
Hello, my name is Ron Wehrens.
I am a researcher at Wageningen University and Research at the Biometrics Department.
And today I'm going to talk about "Multivariate Statistics in the Context of Metabolomics".
0:14
So, whenever you do data analysis,
it's really important to look at your data and
to visualize them in several different ways.
This is also discussed in the lecture on univariate statistics.
And one of the reasons for doing this is that
the human mind is a very good pattern recognizer,
so we are able to see patterns that are very hard to pick up by automated methods.
So things that we might pick up are outliers,
or we might see relationships between variables.
And we might also assess whether the plots that
we see confirm our expectations on the data.
So, one of the key elements of doing
graphics is trying to visualize information in each graph.
And you can do that in a good way and in a bad way.
A very good reference on making good graphics is the book by Bill Cleveland,
already more than 20 years old, "Visualizing Data".
And I would recommend anyone to pick up a copy at the library and look at it.
1:09
R is one of
the most popular data analysis programs
currently around and it is also the program that we are using in this lecture series.
This is a small exercise,
showing you the power of some of
the built-in visualization tools that are there in R. So,
you can simply copy and paste the commands that are on
this slide and take a break from this lecture,
do the R session, do the examples,
and when you're ready, come back to this lecture,
and we can proceed.