Natural fluctuation in the data can lead to constellations in which the clustered data seems to be correlated with external labels, but in fact the correlation has occurred by chance.
Correlation coefficients from the sensitivity analysis were compared to the same statistic from the primary analysis to determine whether any relevant changes in the strength of correlation had occurred with the removal of influential observations.
Typically this probability or "P-value" will be less than 0.05, or 5%, which means the odds are less than one in 20 that the observed genetic correlation could have occurred by chance.
They show that many identical numbers reported in the analysis, which are quoted to two decimal places, are more closely correlated than would be expected from independent measurements although the paper says nothing about how the correlation might have occurred.
It has been speculated that this correlation might have occurred because the amount of chlorpyrifos in maternal blood is in equilibrium with the amount in adipose tissue (Needham 2005) and chlorpyrifos is readily transferred from maternal to cord blood across the placental (Whyatt et al. 2003).
On the other hand, misclassification due to low Spearman's rank correlation coefficient might also have occurred, particularly in women.
For example, when significant damage has occurred, correlations between disc rim loss and decreased field test sensitivity will occur simply because all points are functionally depressed and not necessarily because the two are linked by ganglion cell anatomy.
Correlation between the scales may also have occurred because individuals were aware of the answers they had given for the different scales.
Spearman correlation coefficients were calculated without providing evidence that no systematic change had occurred or with evidence that systematic change did occur.
Lack of correlation between this goal-based measure and QLQ-C30 scales may have occurred for several reasons.
Furthermore, whereas 0.32% of the observed correlations were above 0.75, only 0.000019% would be expected to have occurred by chance.
