Easy way to remove outliers on a graph and tell me what the values deleted are?

I am working on some correlations with some data and seeing if there is a linear correlation, however, I am trying to remove some outliers and I don't know what the best way to go about it is. I have seen some functions like the deleteoutliers code (<http://www.mathworks.com/matlabcentral/fileexchange/3961-deleteoutliers>) However, I am trying to find the outliers in the correlation, not just a set of numbers. I need a code that will tell me what the outliers are and then help me remove them so I can have a new set of data without outliers. Is there an easy way to do this having an x and y value?

I have been using cook's distance to determine my outliers but I don't know how to remove those outliers and make a new table of values.

%Cooks distance%
X=x;
Y=y;
% Use regstats to calculate Cook's Distance
stats = regstats(Y,X,'linear');
% if Cook's Distance > n/4 is a typical treshold that is used to suggest
% the presence of an outlier
potential_outlier = stats.cookd > 4/length(X);
% Display the index of potential outliers and graph the results
X(potential_outlier)
plot(X,Y, 'b.')
hold on
plot(X(potential_outlier),Y(potential_outlier), 'r.')
pause

Answer 1

[John Knollmeyer]

If you just need to take your X & Y points and use potential_outliers to filter out outliers, then indexing with inverse of potential_outliers would give you the non-outlying points:

non_outlier_x = X(~potential_outlier);
non_outlier_y = Y(~potential_outlier);
plot(non_outlier_x, non_outlier_y, 'b*');

[Karla Haiat]

Thank you so much!