Getting parameters of statistic using probplot()

2014 9 5
2 个回答
回答已采纳
更新时间：2014 9 8
3 次查看（30 天）

0 个投票

Hi all, I kindly ask you a couple of suggestion. I'm using probplot() with my sets of data, in order to understand if they come from certain distribution; the results are good and the data fit, in particular they come from Rayleigh (it is clear looking at the picture: most of my points overlap the dashed line) but I need to know also with which parameter I can say it, mathematically. Another good information would be the error, so the distance between the dashed line and my points. Thanks in advance to who will help me.

请先登录，再回答此问题。

 采纳的回答

dpb
dpb 2014-9-5
编辑：dpb 2014-9-6

1 个投票

probplot only does the visualization; for some reason TMW didn't deign to return the parameters for the data fit--seems like a reasonable expectation of the user, though, agreed.
You'll have to use fitdist or the tool to estimate the parameters and then use those to evaluate the expected values from the functional form.

更多回答（1 个）

Fran
Fran 2014-9-8

0 个投票

Hi dbp,
thanks for your hint, may I ask you to be a bit more detailed? I took a look on how to use fitdist, but once I create a probability distribution object fitting the chosen distribution with my data, I don't know how to calculate the error. I found too many information in the forum and probably I'm getting confused.
Thanks in advance! I really appreciate it.

类别

在 帮助中心 和 File Exchange 中查找有关 Half-Normal Distribution 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by