计算平均值，不包括当前观察值

Question

How do I calculate a mean (or any other summary statistic) excluding the current observation?

For example, I have following data:

i - value - category

1 - 5 - 1

2 - 5 - 1

3 - 9 - 1

4 - 2 - 2

5 - 2 - 2

I would like to calculate the mean for each category (egen value_mean = mean(value), by(category)), but exclude the i-th observation: For i=1, for example, the mean value by category 1 would be (5+9)/2. For i=3, it would be (5+5)/2. For i=4, it would be 2/1.

There were various threads online matching my question, the closest one being this one , but I do not understand the explanation and I'd require something in Excel, not whatever language that is.

My range for data is an entire column, formula so far works and looks like this:

=AVERAGEIFS(A:A,D:D,D3,E:E,E3,AP:AP,AP3)

But as you can see it does not exclude the current observation, namely the value in A3.

There ought to be a simple solution, any help is appreciated.

Answer 1

Although you could switch to SUMPRODUCT so as to be able to create an explicit reference to the row in which the formula resides (not possible within SUMIF ), I'd probably prefer the slightly longer:

=(SUMIFS(A:A,D:D,D3,E:E,E3,AP:AP,AP3)-A3)/(COUNTIFS(D:D,D3,E:E,E3,AP:AP,AP3)-1)

which retains the advantage that these functions have over SUMPRODUCT , in that arbitrarily large ranges can be referenced with no detriment to performance.

Regards