DOCUMENTATION FOR COLON CANCER DATASET You may get a copy of the dataset by copying from my account thefile /biostat/user0/lman/colon.dat . The dataset has 1296observations and 35 variables with missing values recorded as NA.Variable Variable description Code Code DefinitionName(*)PATNO Patient numberTRNO Treatment 1 Observation 2 Levamisole alone 3 5-FU + LevamisoleDAYREG Day of registration MTHREG Month of registrationYRREG Year of registrationDAYLC Day of last contact or deathMTHLC Month of last contact or deathYRLC Year of last contact or deathSTATUS Survival status 0 Alive 1 DeadDAYPRGREL Day of prog/relapseMTHPRGREL Month of prog/relapseYRPRGREL Year of prog/relapseunknown variable 1SEX Sex 0 Female 1 MalePT1SITE Location of primary 1 Cecumneoplasm 2 Right Colon 3 Hepatic flexure 4 Transverse colon 5 Splenic flexure 6 Left colon 7 Sigmoid colon 8 Rectosigmoid 9 Rectum10 Multiple sitesHISTYPE Histologic type 1 Adenocarcinoma 2 Colloid(mucinous) 3 Signet ring type 4 OtherCDIFINTG Differentiation 1 Well 2 Moderate well (gr 2-3) 3 Poor (grade 4)EXTLOC Extent of local spread 1 Submucosa/not muscle 2 Muscular/not serosa 3 Serosa/not contiguos 4 Contiguos structuresOBSTRC Obstruction 0 No 1 YesPERFOR Perforation 0 No 1 YesADHERE Adherence 0 No 1 YesREGIMP Regional Implants 0 No 1 Yesunknown variable 2NOPOSND Nodal involvement (number of positive nodes)DAYRES Day of tumor resectionMTHRES Month of tumor resectionYRRES Year of tumor resectionDAYRX Day of start of treatmentMTHRX Month of start of treatmentYRRX Year of start of treatmentPRGREL Prog/relapse status 0 No 1 YesAGE Patient age at reg.DAYS Number of days from tumor resection to start of treatment.TIME Number of days from registration to last contact STUDY Study number(*) You can name the variables whatever you want. These names arefrom the original SAS dataset.The following three variables are NOT in the data set.DUKE Dukes Stage 0 Stage B 1 Stage CELOVER Overall elig. status 0 No 1 YesSEROSA Serosal involvement 0 No 1
View Full Document