Quote:
Originally Posted by qweasd
(Post 4913096)
I don't think "release" can be put on a real line without taking serious liberties with interpretation, which is why I called it voodoo. My X axis is not a mystery: it's just 13.0 for ver. 13.0, 13.1 for ver. 13.1, etc.
|
I don’t try to argue with you. I like very much the name “voodoo” that you chose for that type of the the data. When after 1 goes 1.1, and 1.1.2, and then 2.0, but after 4 goes 7, and after 13 goes 13.1, and 13.37, and then 14 it’s complete voodoo. The English language isn’t my native one. Moreover I never learned English language. So I thought “voodoo” is the standard name used in the English language in such a case. Now I know you invented it and I admire that name much more than before. I simply like very much the people which are able to invent something.
Quote:
Originally Posted by qweasd
(Post 4913096)
But assigning it this way is just as arbitrary as mapping each release to an integer, or whatever is that you did...
|
It isn’t whatever. See the descriptions of the axes. X is for the days after Slackware 1.0 and Y is for the days after the previous Slackware release. So both axes display the days. I tried to use the same scale for both axes but the resulting graph was very flat so I gave up and I used the standard scale.
Quote:
Originally Posted by qweasd
(Post 4913096)
After all, the version assignment is a random experiment from hell; it is dependent on everything, including this thread. What is your first column anyway?
|
The first column (X axis): the days since 1993-07-17 (Slackware 1.0 release)*.
The latter column (Y axis): the days since the previous release.
* There’s 121 days till Slackware’s 20th birthday. Let’s celebrate that day when it’ll come!
Quote:
Originally Posted by qweasd
(Post 4913096)
And using trend here is also questionable: the correlation coefficient is pretty low, the spread is huge, and so it is far from certain that the mean went up. But for purely gambling purposes I would bet on the trend, probably because I always found pictures very convincing :)
|
I didn’t plot any trend: qweasd plotted the simple linear regression and allend plotted the regression slope and some standard errors. I don’t consider these plots reasonable or useful.
|