Early ICC Definition: Unbiased But Complex Formula
The earliest work on intraclass correlations focused on the case of paired measurements, and the first intraclass correlation (ICC) statistics to be proposed were modifications of the interclass correlation (Pearson correlation).
Consider a data set consisting of N paired data values (xn,1, xn,2), for n = 1, ..., N. The intraclass correlation r originally proposed by Ronald Fisher is
- ,
- ,
- .
Later versions of this statistic used the proper degrees of freedom 2N −1 in the denominator for calculating s2 and N −1 in the denominator for calculating r, so that s2 becomes unbiased, and r becomes unbiased if s is known.
The key difference between this ICC and the interclass (Pearson) correlation is that the data are pooled to estimate the mean and variance. The reason for this is that in the setting where an intraclass correlation is desired, the pairs are considered to be unordered. For example, if we are studying the resemblance of twins, there is usually no meaningful way to order the values for the two individuals within a twin pair. Like the interclass correlation, the intraclass correlation for paired data will be confined to the interval .
The intraclass correlation is also defined for data sets with groups having more than two values. For groups consisting of 3 values, it is defined as
- ,
- ,
- .
As the number of values per groups grows, the number of cross-product terms in this expression grows rapidly. The equivalent form
where K is the number of data values per group, and is the sample mean of the nth group, is simpler to calculate. This form is usually attributed to Harris. The left term is non-negative, consequently the intraclass correlation must satisfy
- .
For large K, this ICC is nearly equal to
which can be interpreted as the fraction of the total variance that is due to variation between groups. Ronald Fisher devotes an entire chapter to Intraclass correlation in his classic book Statistical Methods for Research Workers.
For data from a population that is completely noise, Fisher's formula produces ICC values that are distributed about 0, i.e. sometimes being negative. This is because Fisher designed the formula to be unbiased, and therefore its estimates are sometimes overestimates and sometimes underestimates. For small or 0 underlying values in the population, the ICC calculated from a sample may be negative.
Read more about this topic: Intraclass Correlation
Famous quotes containing the words early, unbiased, complex and/or formula:
“In early times every sort of advantage tends to become a military advantage; such is the best way, then, to keep it alive. But the Jewish advantage never did so; beginning in religion, contrary to a thousand analogies, it remained religious. For that we care for them; from that have issued endless consequences.”
—Walter Bagehot (1826–1877)
“Where there is no exaggeration there is no love, and where there is no love there is no understanding. It is only about things that do not interest one, that one can give a really unbiased opinion; and this is no doubt the reason why an unbiased opinion is always valueless.”
—Oscar Wilde (1854–1900)
“I have met charming people, lots who would be charming if they hadn’t got a complex about the British and everyone has pleasant and cheerful manners and I like most of the American voices. On the other hand I don’t believe they have any God and their hats are frightful. On balance I prefer the Arabs.”
—Freya Stark (1893–1993)
“Given for one instant an intelligence which could comprehend all the forces by which nature is animated and the respective positions of the beings which compose it, if moreover this intelligence were vast enough to submit these data to analysis, it would embrace in the same formula both the movements of the largest bodies in the universe and those of the lightest atom; to it nothing would be uncertain, and the future as the past would be present to its eyes.”
—Pierre Simon De Laplace (1749–1827)