Đang chuẩn bị liên kết để tải về tài liệu:
Statistical Methods for Survival Data Analysis Third Edition phần 9

các dữ liệu đã sẵn sàng cho SAS và phần mềm khác. Bảng 13,11 bảng tương ứng trong sáu bệnh nhân tương tự trong bảng 13,9 lần khoảng cách. Sử dụng các ký hiệu Ví dụ các sản phẩm thứ hai trong cho tầng 2 là B điểm kinh nghiệm"điểm kinh nghiệm | MODELS FOR POLYCHOTOMOUS OUTCOMES 419 model y sbp linsul ml covb contrast Equal coefficients for SBP all_parms 0 0 1 1 0 0 contrast Equal coefficients for LINSUL all_parms 0 0 0 0 1 1 run SPSS code data list file c ex14d2d6.dat free age ageg sex sbp dbp lacr hdl linsul smoke dms dm sn. Compute y 4-dms. nomreg y with sbp linsul print fit history parameter lrt. BMDP PR code input file c ex14d2d6.dat . variables 12. format free. variable names age ageg sex sbp dbp lacr hdl linsul smoke dms dm sn. Use age sex to smoke. transform group y 4-dms. codes y 1 2 3. Names y DM IFG NFG. regress depend y. Level 3. Type nom. Interval age sex to smoke. enter .05 .05. remove .05 .05. print end cell model. 14.3.2 Model for Ordinal Polychotomous Outcomes Ordinal Regression Models If the outcomes involve a rank ordering that is the outcome variable is ordinal several multivalued regression models are available. Readers interested in these models are referred to McCullagh and Nelder 1989 Agresti 1990 Ananth and Kleinbaum 1997 and Hosmer and Lemeshow 2000 . In the following discussion we introduce the most frequently used model the proportional odds model. In this model the probability of an outcome below or equal to a given ordinal level P Y k is compared to the probability that it is higher than the level given P Y k . Let Yị be the outcome of the ith subject. Assume that Yị can be classified into m ordinal levels. Let Y k if Y is classified into the kth level and 420 RISK FACTORS RELATED TO DICHOTOMOUS AND POLYCHOTOMOUS OUTCOMES k 1 2 . m. Suppose that for each of n subjects p independent variables X Xi x 2 . Xp y are measured. These variables can be either qualitative or quantitative. If the logit link function defined in Section 14.2.3 is used similar to the logistic regression model 14.2.3 we consider the following models P Y. k I X z logit P Y k I X log ---- 7 a y bịXịị 1 1 - P Yt k I Xj J j k 1 2 . m 1 14.3.5 or equivalently let Uli a yy bx J Kí K X J 7 PY y k I X PYlìí L -I- 1