2026-03-09T00:26:25Z https://fra.repo.nii.ac.jp/oai

oai:fra.repo.nii.ac.jp:02002526 2026-02-03T01:06:51Z 12:14:1716951426151

Polymodalな度数分布を正規分布へ分解するBASICプログラムの検討 Consideration of the BASIC Program to Analyse the Polymodal Frequency Distribution into Normal Distributions. Akamine, Tatsuro 2059 赤嶺, 達郎 90371822 アカミネ, タツロウ A Maximum-Likelihood program was compared with a Least-Squares program and its variations. The algorithm for convergence was MARQUARDT's method according to AKAMINE (1984). Elements and eigenvalues . eigenvectors of the inverse of an Hessian matrix in the neighborhood of the solution were calculated for a quadratic approximation to estimate errors. A likelihood ratio test was used to estimate the confidence interval of the maximum eigenvector. The obtained results are summarized as follows : 1) The Maximum-Likelihood method is the most adequate procedure for this problem. 2) The X2 minimum method is more adequate than the Least-Squares method for normal data, but the latter is more adequate than the former for abnormal data which have a few separate parts at the end of a distribution. These methods are easy to apply for a robust estimation. 3) Parameters are stable in the part where an obvious minimal value is recognized between neighboring distributions. On the other hand, the confidence intervals of the parameters are larger than for the parts where it is not recognized. departmental bulletin paper 日本海区水産研究所 Japan Sea Regional Fisheries Research Laboratory 1985-03-10 日本海区水産研究所研究報告 35 129 160 Bulletin of the Japan Sea Regional Fisheries Research Laboratory AN00186380 0021-4620 https://fra.repo.nii.ac.jp/records/2002526 jpn js_k_35_129_160 日本農学文献記事索引(agriknowledge) https://agriknowledge.affrc.go.jp/RN/2010841390 日本海区水産研究所研究報告 34号 正誤表 https://fra.repo.nii.ac.jp/records/2015230 metadata only access