Ignore anomalies in collection of datasets

I want to ignore anomalies in datasets contained within a for loop. However, I'm not sure how to do this where:

• i = number of rows, and my code will step through it to produce an animation made up of >1000 frames. For example:

RPtoT = [RASIS(i,:); RT2(i,:); RT3(i,:)];
LPtoT = [LASIS(i,:); LT0(i,:); LT1(i,:)];

I want to exlude anomolies that cause my markers to jump around. For example, half way through the moving figure, a few markers will suddenly jump from an x position of 2000 to 0 - I want to be able to ignore these, so almost filter the data, but I don't know how to do this and apply it to a lot more data similar to the code displayed above.

for i = 1:1033
    if i<10
        i = [NaN]; % I want the values contained within i to be neglected if they randomly bounce towards zero
    else
        i = i;
    end

I don't want to have to go through 50+ datasets with a matrices of 1000+ by 3 and set anomalies to NaN, so is there an easier way to do this?

Answer 1

[Steven Lord]

Preprocess your data to identify, fill, and/or remove outliers. Use the functions in the "Missing Data and Outliers" section on that page or use the Live Editor Task "Clean Outlier Data" also described on that page.

[MADRobot]

I've tried to integrate this into my current code, but it doesn't seem to be working.

An example of how I've done this:

[cleanedData,outlierIndices] = rmoutliers([L5MT LLMal LMMal LAnkle R5MT RLMal RMMal RAnkle], 'ThresholdFactor',6);

I've also tried applying it as:

[cleanedData,outlierIndices] = rmoutliers(R5MT, 'ThresholdFactor',6);
[cleanedData,outlierIndices] = rmoutliers(RLMal, 'ThresholdFactor',6);
[cleanedData,outlierIndices] = rmoutliers(RMMal, 'ThresholdFactor',6);
[cleanedData,outlierIndices] = rmoutliers(RAnkle, 'ThresholdFactor',6);

It doesn't seem to be making any difference for some reason, I'm pretty sure I'm doing something wrong but I don't know what I'm doing wrong.