How to create dummy variable?
2 ビュー (過去 30 日間)
古いコメントを表示
Hi all, I have a data matrix of dimension 100x5(time series) I have an outlier for the 75th value of the 4th column so I decide to construct a dummy variable for this outlier.
How can I do this?
Thanks in advance for your consideration and any help
1 件のコメント
Muthu Annamalai
2013 年 7 月 17 日
Your question is not clear enough.
Do you want to find NaN values from your data? isnan maybe something you are interested in, to help pick NaN from data.
What is a 'dummy variable' ? Do you want to replace,
A(75,4) = 0 ; %eliminate the outlier ?
採用された回答
Iain
2013 年 7 月 17 日
Use the mean of the two "surrounding" points
A(75,4) = A(74,4) + A(76,4);
Fit a curve to the known points, and then evaluate it at that point: (or interpolate...)
p = polyfit(times([1:74 76:end]),A([1:74 76:end],4),4); A(75,4) = polyval(p,times(75)); & That uses a 4th order polynomial
0 件のコメント
その他の回答 (0 件)
参考
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!