Trace:

en:ca_dca_examples

This shows you the differences between two versions of the page.

Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||

en:ca_dca_examples [2018/04/12 23:55] David Zelený [Example 2: DCA of river valley data] |
en:ca_dca_examples [2018/04/13 00:01] David Zelený [Example 2: DCA on Vltava river valley dataset] |
||
---|---|---|---|

Line 41: | Line 41: | ||

It is evident that sample 19 is quite different from the rest of data, and correspondence analysis even greatly exaggerates this difference. Here is where the detrending of ordination axes comes as an option (see further, and for DCA on Danube meadow dataset see [[en:ca_dca?&#exercise_3|Exercise 3]] below). | It is evident that sample 19 is quite different from the rest of data, and correspondence analysis even greatly exaggerates this difference. Here is where the detrending of ordination axes comes as an option (see further, and for DCA on Danube meadow dataset see [[en:ca_dca?&#exercise_3|Exercise 3]] below). | ||

- | ==== Example 2: DCA on Vltava river valley dataset ==== | + | ==== Example 2: DCA on Vltava river valley dataset to decide whether linear or unimodal ordination method should be used ==== |

+ | To decide whether the compositional data are homogeneous or heterogeneous, respectively (and thus more suitable for linear or unimodal ordination methods, respectively), we may calculate detrended correspondance analysis (DCA) first and check the length of the first ordination axis (in units of S.D.) to decide. | ||

<code rsplus> | <code rsplus> | ||

Line 61: | Line 62: | ||

</code> | </code> | ||

- | The length of first axis is 4.5 S.D. units, which means that (according to [[en:references|Lepš & Šmilauer 2001]]) unimodal ordination methods are preferable. | + | The length of first axis is 4.5 S.D. units, which means that (according to [[en:references|Lepš & Šmilauer 2003]]) unimodal ordination methods are preferable. |

I won't draw ordination diagram of the result here - since this example is focused only on the decision whether the ''vltava'' dataset is homogeneous or heterogeneous, it is not relevant here. However, note that the section [[en:indirect_ordination_viz|Ordination diagrams]] is devoted to drawing ordination diagrams using this dataset. | I won't draw ordination diagram of the result here - since this example is focused only on the decision whether the ''vltava'' dataset is homogeneous or heterogeneous, it is not relevant here. However, note that the section [[en:indirect_ordination_viz|Ordination diagrams]] is devoted to drawing ordination diagrams using this dataset. | ||

Line 83: | Line 84: | ||

(Showed only 8 of all 96 unconstrained eigenvalues) | (Showed only 8 of all 96 unconstrained eigenvalues) | ||

</code> | </code> | ||

- | As you can see, total inertia is 7.372, and if needed, variation captured by particular axes can be calculated as eigenvalue/total inertia (e.g., for the first axis, 0.5533/7.372*100 = 7.50%)((However, see this note from Jari Oksanen on this topic, copied from [[http://r-forge.r-project.org/forum/forum.php?thread_id=25406&forum_id=194&group_id=68|this]] discussion: //The concept of total inertia does not exist in DCA. Alternative software use the total inertia from other ordination methods such as orthogonal correspondence analysis. Just call cca() for your data to get the total inertia of orthogonal CA. However, that really has no relevance for DCA, although that statistics is commonly used and ritually reported in papers.//)) | + | As you can see, total inertia is 7.372, and if needed, variation captured by particular axes can be calculated as eigenvalue/total inertia (e.g., for the first axis, 0.553/7.372*100 = 7.50%)((However, see this note from Jari Oksanen on this topic, copied from [[http://r-forge.r-project.org/forum/forum.php?thread_id=25406&forum_id=194&group_id=68|this]] discussion: //The concept of total inertia does not exist in DCA. Alternative software use the total inertia from other ordination methods such as orthogonal correspondence analysis. Just call cca() for your data to get the total inertia of orthogonal CA. However, that really has no relevance for DCA, although that statistics is commonly used and ritually reported in papers.//)) |

en/ca_dca_examples.txt · Last modified: 2019/02/26 23:32 by David Zelený