Info

0 0.2 0.4 0.6 0.8 1 Allele frequency

Figure A.3 Two frequency distributions of 100 data points each with nearly identical means (0.498 on the left and 0.506 on the right) but different degrees of variance among the observations (the variance is 0.0293 on the left and 0.0025 on the right). The lines at the top indicate the position of the mean (vertical line) and two standard deviations on either side of the mean (horizontal dashed line) and two standard errors on either side of the mean (horizontal solid line). Like allele frequencies, each distribution is on the interval of 0 to 1.

negative for observations less than the mean but positive for observations greater than the mean. Squaring will make all differences positive so that positive and negative differences will not cancel each other out when summed. Figure A.3 shows two example distributions with variances that differ by more than 10-fold. You should also note that distributions with larger means will have larger variances even if the spread of observations is identical in the two distributions. This makes comparing variance values difficult without reference to the mean.

Variance (a2) The sum of the squared deviations from the mean divided by one less than the sample size.

Standard deviation (a) The square root of the variance; the average deviation from the mean for a single observation. Quantifies the range of values around the mean seen in a sample.

Standard error of an average (SE) The product of the standard deviation and the square root of the sample size divided by the sample size; how far the true population average (a parameter) may be from the sample average (a parameter estimate) by chance.

0 0

Post a comment