corrcoef - vectors of different lengths

21 次查看（过去 30 天）
Richard
Richard 2012-4-2
How is it possible to find the correlation between vectors of different lengths? For example:
clear all
time1 = 1 + (365-1).*rand(1,12);
time2 = 1 + (365-1).*rand(1,24);
data1 = 1 + (20-1).*rand(1,12);
data2 = 1 + (20-1).*rand(1,24);
usually I would find the correlation with:
R = corrcoef(data1,data2);
but the vectors need to be the same lengths! How would I achieve this?

请先登录，再回答此问题。

采纳的回答

Andrei Bobrov
Andrei Bobrov 2012-4-2
try use function interp1
eg
data1 = 1 + (20-1).*rand(1,12);
data2 = 1 + (20-1).*rand(1,24);
d2 = interp1(1:numel(data1),data1,linspace(1,numel(data1),numel(data2)));
R = corrcoef(d2,data2)
OR
d2 = data2(1:2:end)
R = corrcoef(data1,d2)
  2 个评论
Richard
Richard 2012-4-2
with the first method mentioned, does this basically just make data1 into 24 points instead of 12?

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Correlation and Convolution 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