How to find out if subset of data is or ins't greater than an altered mean value

I have a large matrix with each row representing a data sample and the columns the information of that data sample. Columns 14:37 of the data represent different chlorophyll concentrations for the sample. I need to find out which samples have chlorophyll concentrations greater than 1.5 of the mean in the upper quarter of the sample (so at least one column for that sample between columns 14:19 have a chlorophyll concentration greater than 1.5 of that of the mean chlorophyll concentration (mean of rows 14:37)). The data which does have a chlorophyll concentrations greater than 1.5 of that of the mean in this upper quartile needs to be given a 1 (for yes) and those that don't a 0 (for no). How would I go about doing this?

Thanks,

Natalie

[Natalie]

Here is an example of what I mean:

If one of the rows of chlorophyll data was [1,1,2,0,3,4,3,2,1,0,0,0,0,4,0,1,0,2,0,3,3,3,5,2] the mean of chlorophyll data would be 1.6667. I want to know if any of the the first 6 columns of this row have a number that is greater than 1.5 of the mean, so greater than 2.5. There are numbers greater than 2.5 in the first 6 columns and rather than getting back a matrix of [0,0,0,0,1,1], I would like to just get back a matrix of 1, saying that in those 6 columns there is at least one number that is greater than 1.5 times that of the mean.

I hope that is a little clearer as to what I meant

Thanks,

Natalie

Answer 1

[Matt J]

thresh=mean(data(:,14:37),2)*1.5;

data(:,14:19)=bsxfun(@ge, data(:,14:19) , thresh);

[Natalie]

Thank you so much! I had to add in some things. After this I went:

sum_data = sum(data(:,14:19); presence = sum_data>.5;

Thank you again,

Natalie

Answer 2

[Mischa Kim]

Hello Natalie,

does this help?

A = [0 1 2;2 3 0;3 0 2]
A =
     0     1     2
     2     3     0
     3     0     2
>> B = A(2:3,:) > 1.5
B =
     1     1     0
     1     0     1

In the above statement I am comparing all entries in rows 2 and 3 and all columns to 1.5.

[Natalie]

Sorry, my description probably wasn't clear enough. I don't want to know what numbers are greater than 1.5, I want to know what numbers are greater than 1.5 of the mean. So just say one row of chlorophyll data was [1,1,2,0,3,4,3,2,1,0,0,0,0,4,0,1,0,2,0,3,3,3,5,2] the mean of chlorophyll data would be 1.6667. I want to know if any of the the first 6 columns of this row have a number that is greater than 1.5 of the mean, so greater than 2.5. There are numbers greater than 2.5 in the first 6 columns and rather than getting back a matrix of [0,0,0,0,1,1], I would like to just get back a matrix of 1, saying that in those 6 columns there is at least one number that is greater than 1.5 times that of the mean.

I hope that is a little clearer as to what I meant

Thank you,

Natalie

[Mischa Kim]

data = [0 1 2 3 4 5 6;2 3 2 3 0 0 0;0 0 0 0 0 0 0];

for ii = 1:length(data(:,1))
   flag(ii) = double(sum(data(ii,1:6)>1.5*mean(data(ii,:))) > 0);
end

flag_data = [flag' data];