作业七解答.docVIP

作業七解答 作業七：(課本274頁，8.2)調查200位消費者，對20種早餐穀片品牌的口味與益助健康之評等。判別作業_01是最可能與最不可能購買的各四種品牌的平均評等資料。請用SPSS進行判別分析，並說明結果。 解答： 兩群之基本統計量： Group Statistics 整體評等 Mean Std. Deviation Valid N (listwise) Unweighted Weighted 最不可能購買 口味評等 3.75 .957 4 4.000 健康評等 3.50 1.732 4 4.000 最可能購買 口味評等 7.00 .816 4 4.000 健康評等 8.25 .957 4 4.000 Total 口味評等 5.38 1.923 8 8.000 健康評等 5.88 2.850 8 8.000 兩群之平均數比較： Tests of Equality of Group Means Wilks Lambda F df1 df2 Sig. 口味評等 .184 26.684 1 6 .002 健康評等 .207 23.043 1 6 .003 Pooled Within-Groups Matricesa 口味評等 健康評等 Covariance 口味評等 .792 .417 健康評等 .417 1.958 Correlation 口味評等 1.000 .335 健康評等 .335 1.000 a. The covariance matrix has 6 degrees of freedom. Covariance Matricesa 整體評等 口味評等 健康評等 最不可能購買 口味評等 .917 .500 健康評等 .500 3.000 最可能購買 口味評等 .667 .333 健康評等 .333 .917 Total 口味評等 3.696 4.768 健康評等 4.768 8.125 a. The total covariance matrix has 7 degrees of freedom. Boxs?Test?of?Equality?of?Covariance?Matrices Test Results Boxs M 1.249 F Approx. .266 df1 3 df2 6.480E3 Sig. .850 Tests null hypothesis of equal population covariance matrices. 判別分析之實務配適性： Eigenvalues Function Eigenvalue % of Variance Cumulative % Canonical Correlation 1 6.218a 100.0 100.0 .928 a. First 1 canonical discriminant functions were used in the analysis. 判別分析之配適性： Wilks Lambda Test of Function(s) Wilks Lambda Chi-square df Sig. 1 .139 9.883 2 .007 標準化之典型判別函數係數： Standardized Canonical Discriminant Function Coefficients Function 1 口味評等 .656 健康評等 .566 Structure Matrix Function 1 口味評等 .846 健康評等 .786 Pooled within-groups correlations between discriminating variables and standardized canonical discriminant functions Variables ordered by absolute size of correlation within function. Canonical Discriminant Function Coefficients Function 1 口味評等 .738 健康評等 .405 (Constant) -6.342 Unstandardized coefficients Functions at Group Centroids 整體評等 Function 1 最不可能購買 -2.160 最可能購買 2.160 Unstandardized canonical di