@article{oai:niigata-u.repo.nii.ac.jp:00028258, author = {平泉, 光一}, journal = {新潟大学農学部研究報告, 新潟大学農学部研究報告}, month = {Feb}, note = {ケース数が少なく説明変数が多数ある多次元極小標本は、自由度不足で通常は重回帰分析ができない。しかしながら、多くの説明変数を集約して一つの合成変量をつくることで、多次元極小標本であっても単回帰分析を行うことはできる。この方法による回帰分析を本稿では擬似重回帰分析と呼ぶ。本稿では環境保全型農業のコスト規定要因の分析に擬似重回帰分析を適用した。用いたデータは、農林水産省が行った稲作の環境保全型農業に対する調査結果である。標本は、ケース数が5個で、説明変数の数が7個である。回帰分析の結果は、決定係数が0.9899で、回帰係数のp値が0.000428であり、説明力も信頼性も高いものであった。得られた回帰方程式の解釈は、常識的理解と一致した。擬似重回帰分析は、多次元極小標本になりやすい事例研究のデータの分析に向いているといえる。, In general, multidimensional very small sample,which has few cases and many explanatory variables, usually can not\nperform multiple regression analysis due to lack of degrees of freedom. However, it is possible to perform single regression analysis even for multidimensional very small sample by summarizing many explanatory variables to create one synthetic variable. Regression analysis by this method is called pseudo multiple regression analysis in this paper. In this paper, pseudo multiple regression analysis was applied to analysis of cost determinants of sustainable agriculture. The data are the results of the survey on rice cultivation in sustainable agriculture conducted by the Ministry of Agriculture, Forestry and Fisheries. In the sample, the number of cases is five and the number of explanatory variables is seven. Regression analysis results showed that the coefficient of determination was 0.9899, the P-value of the regression coefficient was 0.000428, and the interpretability and reliability were high. Interpretation of the obtained regression equation was consistent with commonsense understanding. It can be said that pseudo multiple regression analysis is suitable for analysis of data of case studies which tend to be multidimensional very small sample.}, pages = {21--24}, title = {多次元極小標本に対する回帰分析の手法開発 : 環境保全型農業のコスト規定要因の分析への適用}, volume = {69}, year = {2017} }