.g Variable-directed techniques concerned with relationships that might exist among the response variables being measured. Include correlation matrics, principal components analysis, factor analysis regression analysis, and canonical correlation anal ysis ◇工 ndividual- directed techniques concerned with relationships that might exist among the experimental units and /or individuals being measured. Include discriminant analysis, cluster analysis, and multivariate analysis of variance( MANOva 2021/2/22 16 cxt
2021/2/22 16 cxt ❖ Variable-directed techniques concerned with relationships that might exist among the response variables being measured. Include correlation matrics, principal components analysis, factor analysis, regression analysis, and canonical correlation analysis. ❖ Individual-directed techniques concerned with relationships that might exist among the experimental units and /or individuals being measured. Include discriminant analysis, cluster analysis, and multivariate analysis of variance（MANOVA）
◆1、简化数据结构 如:主成分分析、因子分析、对应分析 ◆2、分类与判别 如:聚类分析、判别分析 3、变量之间的相关关系 如:回归分析、典型相关分析等 ◇4、统计推断 2021/2/22 cxt
2021/2/22 17 cxt ❖ 1、简化数据结构 如：主成分分析、因子分析、对应分析 ❖ 2、分类与判别 如：聚类分析、判别分析 ❖ 3、变量之间的相关关系 如：回归分析、典型相关分析等 ❖ 4、统计推断
Dependence Techniques: 41\ Multiple regression(Mr)-the objective of MR is to predict changes in a single metric dependent variable in response to changes in several metric independent variables. a related technique is multiple correlation. ◆ General forn Y=Ⅹ1+Ⅹ2+X3++Xn where y and the x's are metric variables 2021/2/22 18 cxt
2021/2/22 18 cxt Dependence Techniques: ❖ 1、Multiple Regression(MR) –the objective of MR is to predict changes in a single metric dependent variable in response to changes in several metric independent variables. A related technique is multiple correlation. ❖ General Form Y = X1 + X2 + X3 + …. +Xn , where Y and the X’s are metric variables
例3:肾小球滤过率的影响因素研究 临床观测61例患者的肾小球滤过率y及10种观察指标:年龄X1,糖化血 红蛋白X2,饭后两小时血糖X3,胰岛素X4,胆固醇X5,肌肝X6,平均 动3体里8,肯体状白蛋白排泄率X10 病例X1X2X3X4X5X6X7X8X9X10y 136916315531013043551177 239142417769902531023130 3421429748296242933101 三.,,····■·····■··■ 6145202210310190203101116 ◇试分析这10项指标与肾小球滤过率间的关系。 2021/2/22 19 cxt
2021/2/22 19 cxt 例3： 肾小球滤过率的影响因素研究 临床观测61例患者的肾小球滤过率y,及10种观察指标:年龄X1,糖化血 红蛋白X2, 饭后两小时血糖X3, 胰岛素X4, 胆固醇X5, 肌肝X6, 平均 动脉压X7, 体重X8, 肾脏体积X9, 尿白蛋白排泄率X10。 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 病例 X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 y ────────────────────────────────── 1 36 9 16 31 5 53 101 304 355 1 177 2 39 14 24 17 7 69 90 25 310 23 130 3 42 14 29 7 4 82 96 24 293 3 101 . . . . . . . . . . . . . . . . . . . . . . . . 61 45 20 22 10 3 101 90 20 310 1 116 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ❖ 试分析这10项指标与肾小球滤过率间的关系
◆变量系数标准误t值P值 截距71.0227.662.5670.0133 X10.,140.270.5100.6124 X2-0.620.95-0.6560.5149 X1.010482.0840.0423* X40.060.160.3820.7039 X52.331.861.2550.2153 6-0.640.193.3690.0015 X70020.180.1570.8757 X8-0.240.78-0.3080.7594 X90.230045.0080.0001* X10-0.210.14-1.5240.1337 ◆P值可以看出,在十个变量中,X3饭后两小时血糖X6肌肝t 和X9肾脏体积对肾小球滤过率影响有显著性意义其它的7 2021/2/22 20 cxt
2021/2/22 20 cxt ❖ 变量 系数 标准误 t值 P值 截距 71.02 27.66 2.567 0.0133 X1 0.14 0.27 0.510 0.6124 X2 -0.62 0.95 -0.656 0.5149 X3 1.01 0.48 2.084 0.0423 * X4 0.06 0.16 0.382 0.7039 X5 2.33 1.86 1.255 0.2153 X6 -0.64 0.19 -3.369 0.0015 ** X7 0.02 0.18 0.157 0.8757 X8 -0.24 0.78 -0.308 0.7594 X9 0.23 0.04 5.008 0.0001 ** X10 -0.21 0.14 -1.524 0.1337 ❖ P值可以看出，在十个变量中, X3饭后两小时血糖,X6肌肝 t 和 X9 肾脏体积对肾小球滤过率影响有显著性意义, 其它的7 个变量没有显著性意义