# How to compute the time lag by cross-correlation of ir-regular time series, accurately?

7 ビュー (過去 30 日間)
Andi 2023 年 5 月 27 日
コメント済み: KSSV 2023 年 5 月 29 日
HI everyone,
My data set consists of monthly observations of two parameters (already normalized) over a 50 years time window?
I require to compute the time-lag between these two time series on yearly basis, at first. IN addition, I also need to compute the time lag over 5 years windows or any other window length.
May someone suggest how i can accurately compute the phase lag.
Here is what I did so far:
% Data presentation
tim=datenum(cd_ev(:,3),cd_ev(:,4),cd_ev(:,5),cd_ev(:,6),cd_ev(:,7),cd_ev(:,8));
p1=cd_ev(:, 9);
p2=cd_ev(:, 10);
figure(1)
plot(tim, p1)
hold on
plot(tim, p2)
hold off
Cross-correlation result
[c,lags] = xcorr(p1,p2);
[c,lags] = xcorr(p1,p2,'normalized');
figure(2)
stem(lags,c)
Thank you!
##### 3 件のコメント1 件の古いコメントを表示1 件の古いコメントを非表示
Andi 2023 年 5 月 29 日
@KSSV I already scale them at same interval one observation per month.
KSSV 2023 年 5 月 29 日
Then try crosscorr

サインインしてコメントする。

### カテゴリ

Help Center および File ExchangeCurve Fitting Toolbox についてさらに検索

### Community Treasure Hunt

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

Start Hunting!

Translated by