Zusammenfassung: The growth curves of von Bertalanffy, logistic and Gompertz models were expanded using a periodic function, f (t + 1) = f (t). Each model was expanded into l = l infinity (1-exph sub(1)), l = l infinity /(1 + exph sub(1)) and l = l infinity exp(-exph sub(1)) where h sub(1) = -K(F(t)-F(t sub(0))), F' = f, f = (1 + a)/2 + (1-a)/2 multiplied by cos 2 pi (t-t sub(1)) : a less than or equal to f less than or equal to 1. BASIC programs for each model were written by Marquardt's method. The following subjects were also considered : an expansion into another type, a parameter-error analysis, a comparison with the original model and with Walford's graphical method, and a calculation to determine the extreme points of the growth rate. This expansion of the growth curves is useful and the programs are easily applied to other curves.

Zusammenfassung: When histograms are used instead of raw data to estimate parameters by the maximum likelihood method, data has an error distributed according to a regular distribution among the width of the histogram. This influence on the estimation of parameters is evaluated by the linearized error propagation rule. Covariance is in proportion to the width squared and in inverse proportion to the number of data. Even if the number of data is large, the precision is low for small normal distributions. In practice, an adequate width will be given by the shapes of the histograms.

Zusammenfassung: The statistical model for extraction is a binomial distribution. The conventional method for employing this binomial model is based on approximation to a normal distribution. The Bayesian statistical method, which assumes that the prior distribution of parameters is uniform, is preferable to the conventional method, and two theorems demonstrate that this model corresponds well with the conventional method. Furthermore, this model is simpler to understand and easier to calculate by micro-computer than the conventional method.