The usual delta method of statistics uses a second-order Taylor series approximation for the mean.
Survival data were analyzed using a Kaplan Meier survival analysis with a log-rank method of statistics (*** P<0.001, ** P<0.01 and * P<0.05).
No matter what method of statistics is used, when the input data have been selected from a larger set, any outcome will be biased and flawed by default.
We use simulation studies to demonstrate that our approach, based on the delta method of statistics, outperforms the standard and Gaussian diffusion approximations when selection is strong, while all three methods perform comparably when selection is weak.
Like Norman (1975), we approximate the transition distribution with a Gaussian density, but use the delta method of statistics to derive a set of recurrence equations for the mean and variance of this distribution without making any assumptions about the strength of selection and mutation.
Experimental results were statistically processed by the methods of variation statistics with the use of STATGRAPH statistic program kit.
For the study of statistical population we used methods of descriptive statistics, in particular measure of central tendency: (min, max, mean, median, mode) and measure of variability (interquartile range, standard deviation, coefficient of variation).
Experimental results were statistically processed by the methods of variation statistics and multifactor analysis of variance (MANOVA) with the use of STATGRAPH statistic program kit.
Basic statistical analysis of results was conducted using usual methods of descriptive statistics with assessment of arithmetic mean, minimum and maximum values, geometric mean, median, and standard deviation.
