Title |
The projection score - an evaluation criterion for variable subset selection in PCA visualization
|
---|---|
Published in |
BMC Bioinformatics, July 2011
|
DOI | 10.1186/1471-2105-12-307 |
Pubmed ID | |
Authors |
Magnus Fontes, Charlotte Soneson |
Abstract |
In many scientific domains, it is becoming increasingly common to collect high-dimensional data sets, often with an exploratory aim, to generate new and relevant hypotheses. The exploratory perspective often makes statistically guided visualization methods, such as Principal Component Analysis (PCA), the methods of choice. However, the clarity of the obtained visualizations, and thereby the potential to use them to formulate relevant hypotheses, may be confounded by the presence of the many non-informative variables. For microarray data, more easily interpretable visualizations are often obtained by filtering the variable set, for example by removing the variables with the smallest variances or by only including the variables most highly related to a specific response. The resulting visualization may depend heavily on the inclusion criterion, that is, effectively the number of retained variables. To our knowledge, there exists no objective method for determining the optimal inclusion criterion in the context of visualization. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 4 | 5% |
Brazil | 1 | 1% |
Israel | 1 | 1% |
United Kingdom | 1 | 1% |
India | 1 | 1% |
Spain | 1 | 1% |
Belgium | 1 | 1% |
Unknown | 66 | 87% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 26 | 34% |
Researcher | 20 | 26% |
Student > Master | 5 | 7% |
Student > Postgraduate | 4 | 5% |
Student > Bachelor | 4 | 5% |
Other | 8 | 11% |
Unknown | 9 | 12% |
Readers by discipline | Count | As % |
---|---|---|
Agricultural and Biological Sciences | 25 | 33% |
Biochemistry, Genetics and Molecular Biology | 13 | 17% |
Computer Science | 5 | 7% |
Chemistry | 5 | 7% |
Mathematics | 4 | 5% |
Other | 15 | 20% |
Unknown | 9 | 12% |