Hello!
I dunno why, but I cannot make randtes.coinertia() from ade4 package
working. I have two nice distance matrices (Euclidean):
> dist1
1 2 3 4 5 6 7
2 2.5776799
3 1.7892825 1.0637487
4 1.0557991 2.4270728 2.0626604
5 1.6745483 4.1505805 3.4581614 1.8900295
6 2.5045058 0.8144662 0.7157900 2.6888306 4.1708413
7 4.1367323 1.6058153 2.6451634 3.7795019 5.6220092 2.1504953
8 1.5224318 1.4444836 1.3682047 1.0048085 2.8425813 1.8464349 2.7853605
9 4.5321276 4.5859822 3.8178836 5.4277885 5.7703245 3.7731505 5.6657106
10 4.0389095 1.6702235 2.7327563 3.5495557 5.4279792 2.3611163 0.5540045
8 9
2
3
4
5
6
7
8
9 5.1082493
10 2.5924107 6.0248981
> dist2
1 2 3 4 5 6 7
2 0.9364828
3 1.4333876 1.9160376
4 0.2523886 1.1884864 1.3697080
5 2.3753105 2.5185909 3.7830808 2.4140423
6 1.7928748 1.6959363 1.0841587 1.8848077 4.0827074
7 2.5117723 1.6858232 2.7455418 2.7406021 4.0115957 1.8140011
8 0.6014150 0.3748333 1.8022486 0.8514693 2.2931638 1.8062392 2.0515604
9 2.8802778 3.5524921 1.6707483 2.7134664 4.9800100 2.5480973 4.3439383
10 3.0686316 2.6196374 2.4765500 3.2133783 5.1381903 1.4228493 1.5749603
8 9
2
3
4
5
6
7
8
9 3.3777063
10 2.8790276 3.6806114
And then, I follow from help:
> pco1 = dudi.pco(dist1, nf=2, scannf=F)
> pco2 = dudi.pco(dist2, nf=2, scannf=F)
> coi = coinertia(pco1, pco2, nf=2, scannf=F)
> testco1 = randtest.coinertia(coi, nrepet=1000)
The result is:
> Error in randtest.coinertia(coi, nrepet = 1000) : Not yet available
Could anyone help with this?
Best,
PM
Hello! I dunno why, but I cannot make randtes.coinertia() from ade4 package working. I have two nice distance matrices (Euclidean):> dist11 2 3 4 5 6 7 2 2.5776799 3 1.7892825 1.0637487 4 1.0557991 2.4270728 2.0626604 5 1.6745483 4.1505805 3.4581614 1.8900295 6 2.5045058 0.8144662 0.7157900 2.6888306 4.1708413 7 4.1367323 1.6058153 2.6451634 3.7795019 5.6220092 2.1504953 8 1.5224318 1.4444836 1.3682047 1.0048085 2.8425813 1.8464349 2.7853605 9 4.5321276 4.5859822 3.8178836 5.4277885 5.7703245 3.7731505 5.6657106 10 4.0389095 1.6702235 2.7327563 3.5495557 5.4279792 2.3611163 0.5540045 8 9 2 3 4 5 6 7 8 9 5.1082493 10 2.5924107 6.0248981> dist21 2 3 4 5 6 7 2 0.9364828 3 1.4333876 1.9160376 4 0.2523886 1.1884864 1.3697080 5 2.3753105 2.5185909 3.7830808 2.4140423 6 1.7928748 1.6959363 1.0841587 1.8848077 4.0827074 7 2.5117723 1.6858232 2.7455418 2.7406021 4.0115957 1.8140011 8 0.6014150 0.3748333 1.8022486 0.8514693 2.2931638 1.8062392 2.0515604 9 2.8802778 3.5524921 1.6707483 2.7134664 4.9800100 2.5480973 4.3439383 10 3.0686316 2.6196374 2.4765500 3.2133783 5.1381903 1.4228493 1.5749603 8 9 2 3 4 5 6 7 8 9 3.3777063 10 2.8790276 3.6806114 And then, I follow from help:> pco1 = dudi.pco(dist1, nf=2, scannf=F) > pco2 = dudi.pco(dist2, nf=2, scannf=F) > coi = coinertia(pco1, pco2, nf=2, scannf=F) > testco1 = randtest.coinertia(coi, nrepet=1000)The result is:> Error in randtest.coinertia(coi, nrepet = 1000) : Not yet availableCould anyone help with this? Best, PM
Hi Petar,>> I dunno why, but I cannot make randtes[t].coinertia() from ade4 package >> working. I have two nice distance matrices (Euclidean): >> Could anyone help with this?Yes (sort of). The test has not yet been implemented for dudi.pco, as the message at the end of your listing tells you.>> The result is: > Error in randtest.coinertia(coi, nrepet = 1000) : Not yet availableSo far it has only been implemented for some types of dudi.pca, and for dudi.coa, dudi.fca, and dudi.acm. You might be lucky and find code to do what you want on the ade4 list. http://pbil.univ-lyon1.fr/ADE-4/home.php?lang=eng http://listes.univ-lyon1.fr/wws/info/adelist Regards, Mark. -- View this message in context: http://r.789695.n4.nabble.com/Coinertia-randtest-tp2335696p2335748.html Sent from the R help mailing list archive at Nabble.com.