Hello all, I am having difficulty figuring out the reason for this error message. Currently trying to run a multivariable model for prediction on vaping status. My issue lies in my references. I have found GRAD_T will pull in all levels of 8th, 10th, and 12th grade into the model without difficulty, but only when I exclude AGE_T from the model entirely. I have tried variations on AGE_T including 'first' but it just seems to mess up GRAD_T. Running a cross tabulation of GRAD_T with AGE_T and I do have zeros in the rows, but independently values are present. I have went back in my code and eliminated missing values for both GRAD_T and AGE_T. I have even tried different coded string in the '', including 'first' and '1' without success. *BEGINNING OF CODE*;
libname MTFGR '/home/u52765837/MTFDATA';
*INPUT ALL DATA STARTING WITH GRADE 12, 2019*;
data school12_2019;
set mtfgr.grade1219;
year=2019;
grade=12;
keep GRADE v2150 v2151 v2102 v2106 v2117 v2582 v2102d v2106d v2117d v13 archive_wt RESPONDENT_AGE V2163
V2164 V2179 SEX RACE GRADAVG DAD_EDU MOM_EDU CIG30 MJ30 ALC30 VAPE30 AGE SCHOOL_REGION;
*CREATING SEX LABELS*;
IF V2150= 1 THEN SEX= 'MALE';
ELSE IF V2150= 2 THEN SEX= 'FEMALE';
*CREATING RACE LABELS*;
IF V2151= 1 THEN RACE= 'BLACK/AFRICAN AMERICAN';
ELSE IF V2151= 2 THEN RACE= 'WHITE/CAUCASIAN';
ELSE IF V2151= 3 THEN RACE= 'HISPANIC';
*CREATING AGE LABELS*;
IF RESPONDENT_AGE= 1 THEN AGE= 'UNDER 18';
ELSE IF RESPONDENT_AGE= 2 THEN AGE= '18 OR OLDER';
if RESPONDENT_AGE= -9 THEN delete;
*CREATING LABEL FOR SCHOOL REGION*;
IF V13= 1 THEN SCHOOL_REGION= 'NORTHEAST';
ELSE IF V13= 2 THEN SCHOOL_REGION= 'MIDWEST';
ELSE IF V13= 3 THEN SCHOOL_REGION= 'SOUTH';
ELSE IF V13= 4 THEN SCHOOL_REGION= 'WEST';
*CREATING GRADE AVERAGE INTO NEW VARIABLE*;
IF V2179 IN (9,8) THEN GRADAVG= 'A';
ELSE IF V2179 IN (7,6,5) THEN GRADAVG= 'B';
ELSE IF V2179 IN (4,3,2) THEN GRADAVG= 'C';
ELSE IF V2179= 1 THEN GRADAVG= 'D';
*CREATING FATHER EDUCATION INTO NEW VARIABLE*;
IF V2163 IN (1,2,3) THEN DAD_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V2163
IN (4,5) THEN DAD_EDU= 'UP TO COLLEGE';
ELSE IF V2163
= 6 THEN DAD_EDU= 'GRAD SCHOOL';
ELSE IF V2163
= 9 THEN DAD_EDU= 'DONT KNOW';
*CREATING MOTHER EDUCATION INTO NEW VARIABLE*;
IF V2164 IN (1,2,3) THEN MOM_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V2164 IN (4,5) THEN MOM_EDU= 'UP TO COLLEGE';
ELSE IF V2164 = 6 THEN MOM_EDU= 'GRAD SCHOOL';
ELSE IF V2164= 9 THEN MOM_EDU= 'DONT KNOW';
/* CREATING CIG 30 DAY DICHOTOMOUS VARIABLE */
IF V2102D= 0 THEN CIG30= 'NO ';
ELSE IF V2102D = 1 THEN CIG30= 'YES';
/* CREATING ALCOHOL 30 DAY DICHOTOMOUS VARIABLE */
IF V2106D= 0 THEN ALC30= 'NO ';
ELSE IF V2106D= 1 THEN ALC30= 'YES';
/* CREATING MARIJUANA 30 DAY DICHOTOMOUS VARIABLE */
IF V2117D= 0 THEN MJ30= 'NO ';
ELSE IF V2117D= 1 THEN MJ30= 'YES';
/* CREATING VAPE 30 DAY DICHOTOMOUS VARIABLE */
IF V2582= 1 THEN VAPE30= 'NO ';
ELSE IF V2582 IN (2,3,4,5,6,7) THEN VAPE30= 'YES';
*labeling variables FOR MISSING VALUES*;
if v2150= -9 then v2150= .;
if v2151= -9 then v2151= .;
if v2102= -9 then v2102= .;
if v2106= -9 then v2106= .;
if v2117= -9 then v2117= .;
if v2582= -9 then v2582= .;
if v2102d= -9 then v2102d= .;
if v2106d= -9 then v2106d= .;
if v2117d= -9 then v2117d= .;
if V2163= -9 then V2163= .;
if v2164= -9 then v2164= .;
if v2179= -9 then v2179= .;
label SEX= 'SEX'
RACE= 'RACE'
V2582= '30 DAYS VAPE NICOTINE'
CIG30= '30 DAY CIGARETTE USE- DICHOTOMOUS'
ALC30= '30 DAY ALCOHOL USE- DICHOTOMOUS'
MJ30= '30 DAY MARIJUANA USE- DICHOTOMOUS'
SCHOOL_REGION= 'SCHOOL REGION'
AGE= 'AGE CATEGORIES'
DAD_EDU= 'FATHER EDUCATION LEVEL'
MOM_EDU= 'MOTHER EDUCATION LEVEL'
GRADAVG= 'AVERAGE GRADE'
VAPE30= '30 DAY VAPE USE- DICHOTOMOUS';
*GRADE 12, 2020*;
data school12_2020;
set mtfgr.grade1220;
year=2020;
grade=12;
keep GRADE v2150 v2151 v2102 v2106 v2117 v2582 v2102d v2106d v2117d v13 archive_wt RESPONDENT_AGE V2163
V2164 V2179 SEX RACE GRADAVG DAD_EDU MOM_EDU CIG30 MJ30 ALC30 VAPE30 AGE SCHOOL_REGION;
*CREATING SEX LABELS*;
IF V2150= 1 THEN SEX= 'MALE';
ELSE IF V2150= 2 THEN SEX= 'FEMALE';
*CREATING RACE LABELS*;
IF V2151= 1 THEN RACE= 'BLACK/AFRICAN AMERICAN';
ELSE IF V2151= 2 THEN RACE= 'WHITE/CAUCASIAN';
ELSE IF V2151= 3 THEN RACE= 'HISPANIC';
*CREATING AGE LABELS*;
IF RESPONDENT_AGE= 1 THEN AGE= 'UNDER 18';
ELSE IF RESPONDENT_AGE= 2 THEN AGE= '18 OR OLDER';
if RESPONDENT_AGE= -9 THEN delete;
*CREATING LABEL FOR SCHOOL REGION*;
IF V13= 1 THEN SCHOOL_REGION= 'NORTHEAST';
ELSE IF V13= 2 THEN SCHOOL_REGION= 'MIDWEST';
ELSE IF V13= 3 THEN SCHOOL_REGION= 'SOUTH';
ELSE IF V13= 4 THEN SCHOOL_REGION= 'WEST';
*CREATING GRADE AVERAGE INTO NEW VARIABLE*;
IF V2179 IN (9,8) THEN GRADAVG= 'A';
ELSE IF V2179 IN (7,6,5) THEN GRADAVG= 'B';
ELSE IF V2179 IN (4,3,2) THEN GRADAVG= 'C';
ELSE IF V2179= 1 THEN GRADAVG= 'D';
*CREATING FATHER EDUCATION INTO NEW VARIABLE*;
IF V2163
IN (1,2,3) THEN DAD_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V2163
IN (4,5) THEN DAD_EDU= 'UP TO COLLEGE';
ELSE IF V2163
= 6 THEN DAD_EDU= 'GRAD SCHOOL';
ELSE IF V2163
= 9 THEN DAD_EDU= 'DONT KNOW';
*CREATING MOTHER EDUCATION INTO NEW VARIABLE*;
IF V2164 IN (1,2,3) THEN MOM_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V2164 IN (4,5) THEN MOM_EDU= 'UP TO COLLEGE';
ELSE IF V2164 = 6 THEN MOM_EDU= 'GRAD SCHOOL';
ELSE IF V2164= 9 THEN MOM_EDU= 'DONT KNOW';
/* CREATING CIG 30 DAY DICHOTOMOUS VARIABLE */
IF V2102D= 0 THEN CIG30= 'NO ';
ELSE IF V2102D = 1 THEN CIG30= 'YES';
/* CREATING ALCOHOL 30 DAY DICHOTOMOUS VARIABLE */
IF V2106D= 0 THEN ALC30= 'NO ';
ELSE IF V2106D= 1 THEN ALC30= 'YES';
/* CREATING MARIJUANA 30 DAY DICHOTOMOUS VARIABLE */
IF V2117D= 0 THEN MJ30= 'NO ';
ELSE IF V2117D= 1 THEN MJ30= 'YES';
/* CREATING VAPE 30 DAY DICHOTOMOUS VARIABLE */
IF V2582= 1 THEN VAPE30= 'NO ';
ELSE IF V2582 IN (2,3,4,5,6,7) THEN VAPE30= 'YES';
*labeling variables FOR MISSING VALUES*;
if v2150= -9 then v2150= .;
if v2151= -9 then v2151= .;
if v2102= -9 then v2102= .;
if v2106= -9 then v2106= .;
if v2117= -9 then v2117= .;
if v2582= -9 then v2582= .;
if v2102d= -9 then v2102d= .;
if v2106d= -9 then v2106d= .;
if v2117d= -9 then v2117d= .;
if V2163
= -9 then V2163
= .;
if v2164= -9 then v2164= .;
if v2179= -9 then v2179= .;
label SEX= 'SEX'
RACE= 'RACE'
V2582= '30 DAYS VAPE NICOTINE'
CIG30= '30 DAY CIGARETTE USE- DICHOTOMOUS'
ALC30= '30 DAY ALCOHOL USE- DICHOTOMOUS'
MJ30= '30 DAY MARIJUANA USE- DICHOTOMOUS'
SCHOOL_REGION= 'SCHOOL REGION'
AGE= 'AGE CATEGORIES'
DAD_EDU= 'FATHER EDUCATION LEVEL'
MOM_EDU= 'MOTHER EDUCATION LEVEL'
GRADAVG= 'AVERAGE GRADE'
VAPE30= '30 DAY VAPE USE- DICHOTOMOUS';
/* 2021 */
data school12_2021;
set mtfgr.grade1221;
year=2021;
grade=12;
keep GRADE v2150 v2151 v2102 v2106 v2117 v7782 v2102d v2106d v2117d v13 archive_wt RESPONDENT_AGE V2163
V2164 V2179 SEX RACE GRADAVG DAD_EDU MOM_EDU CIG30 MJ30 ALC30 VAPE30 AGE SCHOOL_REGION;
*CREATING SEX LABELS*;
IF V2150= 1 THEN SEX= 'MALE';
ELSE IF V2150= 2 THEN SEX= 'FEMALE';
*CREATING RACE LABELS*;
IF V2151= 1 THEN RACE= 'BLACK/AFRICAN AMERICAN';
ELSE IF V2151= 2 THEN RACE= 'WHITE/CAUCASIAN';
ELSE IF V2151= 3 THEN RACE= 'HISPANIC';
*CREATING AGE LABELS*;
IF RESPONDENT_AGE= 1 THEN AGE= 'UNDER 18';
ELSE IF RESPONDENT_AGE= 2 THEN AGE= '18 OR OLDER';
if RESPONDENT_AGE= -9 THEN delete;
*CREATING LABEL FOR SCHOOL REGION*;
IF V13= 1 THEN SCHOOL_REGION= 'NORTHEAST';
ELSE IF V13= 2 THEN SCHOOL_REGION= 'MIDWEST';
ELSE IF V13= 3 THEN SCHOOL_REGION= 'SOUTH';
ELSE IF V13= 4 THEN SCHOOL_REGION= 'WEST';
*CREATING GRADE AVERAGE INTO NEW VARIABLE*;
IF V2179 IN (9,8) THEN GRADAVG= 'A';
ELSE IF V2179 IN (7,6,5) THEN GRADAVG= 'B';
ELSE IF V2179 IN (4,3,2) THEN GRADAVG= 'C';
ELSE IF V2179= 1 THEN GRADAVG= 'D';
*CREATING FATHER EDUCATION INTO NEW VARIABLE*;
IF V2163
IN (1,2,3) THEN DAD_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V2163
IN (4,5) THEN DAD_EDU= 'UP TO COLLEGE';
ELSE IF V2163
= 6 THEN DAD_EDU= 'GRAD SCHOOL';
ELSE IF V2163
= 9 THEN DAD_EDU= 'DONT KNOW';
*CREATING MOTHER EDUCATION INTO NEW VARIABLE*;
IF V2164 IN (1,2,3) THEN MOM_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V2164 IN (4,5) THEN MOM_EDU= 'UP TO COLLEGE';
ELSE IF V2164 = 6 THEN MOM_EDU= 'GRAD SCHOOL';
ELSE IF V2164= 9 THEN MOM_EDU= 'DONT KNOW';
/* CREATING CIG 30 DAY DICHOTOMOUS VARIABLE */
IF V2102D= 0 THEN CIG30= 'NO ';
ELSE IF V2102D = 1 THEN CIG30= 'YES';
/* CREATING ALCOHOL 30 DAY DICHOTOMOUS VARIABLE */
IF V2106D= 0 THEN ALC30= 'NO ';
ELSE IF V2106D= 1 THEN ALC30= 'YES';
/* CREATING MARIJUANA 30 DAY DICHOTOMOUS VARIABLE */
IF V2117D= 0 THEN MJ30= 'NO ';
ELSE IF V2117D= 1 THEN MJ30= 'YES';
/* CREATING VAPE 30 DAY DICHOTOMOUS VARIABLE */
IF V7782= 1 THEN VAPE30= 'NO ';
ELSE IF V7782 IN (2,3,4,5,6,7) THEN VAPE30= 'YES';
*labeling variables FOR MISSING VALUES*;
if v2150= -9 then v2150= .;
if v2151= -9 then v2151= .;
if v2102= -9 then v2102= .;
if v2106= -9 then v2106= .;
if v2117= -9 then v2117= .;
if v2102d= -9 then v2102d= .;
if v2106d= -9 then v2106d= .;
if v2117d= -9 then v2117d= .;
if V2163= -9 then V2163= .;
if v2164= -9 then v2164= .;
if v2179= -9 then v2179= .;
label SEX= 'SEX'
RACE= 'RACE'
V2582= '30 DAYS VAPE NICOTINE'
CIG30= '30 DAY CIGARETTE USE- DICHOTOMOUS'
ALC30= '30 DAY ALCOHOL USE- DICHOTOMOUS'
MJ30= '30 DAY MARIJUANA USE- DICHOTOMOUS'
SCHOOL_REGION= 'SCHOOL REGION'
AGE= 'AGE CATEGORIES'
DAD_EDU= 'FATHER EDUCATION LEVEL'
MOM_EDU= 'MOTHER EDUCATION LEVEL'
GRADAVG= 'AVERAGE GRADE'
VAPE30= '30 DAY VAPE USE- DICHOTOMOUS';
*CONCATENATED DATASET FOR 12 GRADE ALL YEARS*;
DATA SCHOOL123;
SET SCHOOL12_2019 SCHOOL12_2020 SCHOOL12_2021;
rename archive_wt=weight;
RUN;
*INPUT DATA STARTING WITH GRADE 8, 2019-2021*;
data school8_2019;
set mtfgr.grade819;
year=2019;
grade=8;
keep v7301 v7202 V1252 v1070 v7102 v7107 v7114 V7763 v7102d v7107d v7114d v507 v5 V7215 V7216 V7221 GRADLVL SEX RACE GRADAVG DAD_EDU MOM_EDU CIG30 MJ30 ALC30 VAPE30 AGE SCHOOL_REGION;
*CREATING GRADE LEVEL DISTINCTION*;
IF V7301 = 2 THEN GRADLVL= '8TH ';
ELSE IF V7301= 4 THEN GRADLVL= '10TH';
ELSE IF V7301 IN (1,3,5,6, -9) THEN DELETE;
*CREATING SEX LABELS*;
IF V7202= 1 THEN SEX= 'MALE';
ELSE IF V7202= 2 THEN SEX= 'FEMALE';
*CREATING RACE LABELS*;
IF V1070= 1 THEN RACE= 'BLACK/AFRICAN AMERICAN';
ELSE IF V1070= 2 THEN RACE= 'WHITE/CAUCASIAN';
ELSE IF V1070= 3 THEN RACE= 'HISPANIC';
*CREATING AGE LABELS*;
IF V1252= 1 THEN AGE= 'UNDER 16';
ELSE IF V1252= 2 THEN AGE= '16 OR OLDER';
IF V1252= (-9 -8) THEN delete;
*CREATING LABEL FOR SCHOOL REGION*;
IF V507= 1 THEN SCHOOL_REGION= 'NORTHEAST';
ELSE IF V507= 2 THEN SCHOOL_REGION= 'MIDWEST';
ELSE IF V507= 3 THEN SCHOOL_REGION= 'SOUTH';
ELSE IF V507= 4 THEN SCHOOL_REGION= 'WEST';
*CREATING GRADE AVERAGE INTO NEW VARIABLE*;
IF V7221 IN (9,8) THEN GRADAVG= 'A';
ELSE IF V7221 IN (7,6,5) THEN GRADAVG= 'B';
ELSE IF V7221 IN (4,3,2) THEN GRADAVG= 'C';
ELSE IF V7221= 1 THEN GRADAVG= 'D';
*CREATING FATHER EDUCATION INTO NEW VARIABLE*;
IF V7215 IN (1,2,3) THEN DAD_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V7215 IN (4,5) THEN DAD_EDU= 'UP TO COLLEGE';
ELSE IF V7215= 6 THEN DAD_EDU= 'GRAD SCHOOL';
ELSE IF V7215= 7 THEN DAD_EDU= 'DONT KNOW';
*CREATING MOTHER EDUCATION INTO NEW VARIABLE*;
IF V7216 IN (1,2,3) THEN MOM_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V7216 IN (4,5) THEN MOM_EDU= 'UP TO COLLEGE';
ELSE IF V7216 = 6 THEN MOM_EDU= 'GRAD SCHOOL';
ELSE IF V7216= 7 THEN MOM_EDU= 'DONT KNOW';
/* CREATING CIG 30 DAY DICHOTOMOUS VARIABLE */
IF V7102D= 0 THEN CIG30= 'NO ';
ELSE IF V7102D = 1 THEN CIG30= 'YES';
/* CREATING ALCOHOL 30 DAY DICHOTOMOUS VARIABLE */
IF V7107D= 0 THEN ALC30= 'NO ';
ELSE IF V7107D= 1 THEN ALC30= 'YES';
/* CREATING MARIJUANA 30 DAY DICHOTOMOUS VARIABLE */
IF V7114D= 0 THEN MJ30= 'NO ';
ELSE IF V7114D= 1 THEN MJ30= 'YES';
/* CREATING VAPE 30 DAY DICHOTOMOUS VARIABLE */
IF V7763= 1 THEN VAPE30= 'NO ';
ELSE IF V7763 IN (2,3,4,5,6,7) THEN VAPE30= 'YES';
*labeling variables FOR MISSING VALUES*;
if v7202= -9 then v2150= .;
if v1070= -9 then vV1070= .;
/* if v2102= -9 then v2102= .; */
/* if v2106= -9 then v2106= .; */
/* if v2117= -9 then v2117= .; */
if v7221= -9 then v7221= .;
IF V7215= -9 THEN V7215= .;
IF V7216= -9 THEN V7216= .;
if V7102D= -9 then vV7102D= .;
if v7107D= -9 then v7107D= .;
if V7114D= -9 then V7114D= .;
label SEX= 'SEX'
RACE= 'RACE'
CIG30= '30 DAY CIGARETTE USE- DICHOTOMOUS'
ALC30= '30 DAY ALCOHOL USE- DICHOTOMOUS'
MJ30= '30 DAY MARIJUANA USE- DICHOTOMOUS'
SCHOOL_REGION= 'SCHOOL REGION'
AGE= 'AGE CATEGORIES'
DAD_EDU= 'FATHER EDUCATION LEVEL'
MOM_EDU= 'MOTHER EDUCATION LEVEL'
GRADAVG= 'AVERAGE GRADE'
VAPE30= '30 DAY VAPE USE- DICHOTOMOUS'
GRADLVL= 'GRADE LEVEL';
*2020*;
data school8_2020;
set mtfgr.grade820;
year=2020;
grade=8;
keep V7301 v7202 V1252 v1070 v7102 v7107 v7114 V7763 v7102d v7107d v7114d v507 v5 V7215 V7216 V7221 GRADLVL SEX RACE GRADAVG DAD_EDU MOM_EDU CIG30 MJ30 ALC30 VAPE30 AGE SCHOOL_REGION;
*CREATING GRADE LEVEL DISTINCTION*;
IF V7301 = 2 THEN GRADLVL= '8TH ';
ELSE IF V7301= 4 THEN GRADLVL= '10TH';
ELSE IF V7301 IN (1,3,5,6, -9) THEN DELETE;
*CREATING SEX LABELS*;
IF V7202= 1 THEN SEX= 'MALE';
ELSE IF V7202= 2 THEN SEX= 'FEMALE';
*CREATING RACE LABELS*;
IF V1070= 1 THEN RACE= 'BLACK/AFRICAN AMERICAN';
ELSE IF V1070= 2 THEN RACE= 'WHITE/CAUCASIAN';
ELSE IF V1070= 3 THEN RACE= 'HISPANIC';
*CREATING AGE LABELS*;
IF V1252= 1 THEN AGE= 'UNDER 16';
ELSE IF V1252= 2 THEN AGE= '16 OR OLDER';
ELSE IF V1252= (-8 -9) THEN delete;
*CREATING LABEL FOR SCHOOL REGION*;
IF V507= 1 THEN SCHOOL_REGION= 'NORTHEAST';
ELSE IF V507= 2 THEN SCHOOL_REGION= 'MIDWEST';
ELSE IF V507= 3 THEN SCHOOL_REGION= 'SOUTH';
ELSE IF V507= 4 THEN SCHOOL_REGION= 'WEST';
*CREATING GRADE AVERAGE INTO NEW VARIABLE*;
IF V7221 IN (9,8) THEN GRADAVG= 'A';
ELSE IF V7221 IN (7,6,5) THEN GRADAVG= 'B';
ELSE IF V7221 IN (4,3,2) THEN GRADAVG= 'C';
ELSE IF V7221= 1 THEN GRADAVG= 'D';
*CREATING FATHER EDUCATION INTO NEW VARIABLE*;
IF V7215 IN (1,2,3) THEN DAD_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V7215 IN (4,5) THEN DAD_EDU= 'UP TO COLLEGE';
ELSE IF V7215= 6 THEN DAD_EDU= 'GRAD SCHOOL';
ELSE IF V7215= 7 THEN DAD_EDU= 'DONT KNOW';
*CREATING MOTHER EDUCATION INTO NEW VARIABLE*;
IF V7216 IN (1,2,3) THEN MOM_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V7216 IN (4,5) THEN MOM_EDU= 'UP TO COLLEGE';
ELSE IF V7216 = 6 THEN MOM_EDU= 'GRAD SCHOOL';
ELSE IF V7216= 7 THEN MOM_EDU= 'DONT KNOW';
/* CREATING CIG 30 DAY DICHOTOMOUS VARIABLE */
IF V7102D= 0 THEN CIG30= 'NO ';
ELSE IF V7102D = 1 THEN CIG30= 'YES';
/* CREATING ALCOHOL 30 DAY DICHOTOMOUS VARIABLE */
IF V7107D= 0 THEN ALC30= 'NO ';
ELSE IF V7107D= 1 THEN ALC30= 'YES';
/* CREATING MARIJUANA 30 DAY DICHOTOMOUS VARIABLE */
IF V7114D= 0 THEN MJ30= 'NO ';
ELSE IF V7114D= 1 THEN MJ30= 'YES';
/* CREATING VAPE 30 DAY DICHOTOMOUS VARIABLE */
IF V7763= 1 THEN VAPE30= 'NO ';
ELSE IF V7763 IN (2,3,4,5,6,7) THEN VAPE30= 'YES';
*labeling variables FOR MISSING VALUES*;
if v7202= -9 then v2150= .;
if v1070= -9 then vV1070= .;
/* if v2102= -9 then v2102= .; */
/* if v2106= -9 then v2106= .; */
/* if v2117= -9 then v2117= .; */
if v7221= -9 then v7221= .;
IF V7215= -9 THEN V7215= .;
IF V7216= -9 THEN V7216= .;
if V7102D= -9 then vV7102D= .;
if v7107D= -9 then v7107D= .;
if V7114D= -9 then V7114D= .;
label SEX= 'SEX'
RACE= 'RACE'
CIG30= '30 DAY CIGARETTE USE- DICHOTOMOUS'
ALC30= '30 DAY ALCOHOL USE- DICHOTOMOUS'
MJ30= '30 DAY MARIJUANA USE- DICHOTOMOUS'
SCHOOL_REGION= 'SCHOOL REGION'
AGE= 'AGE CATEGORIES'
DAD_EDU= 'FATHER EDUCATION LEVEL'
MOM_EDU= 'MOTHER EDUCATION LEVEL'
GRADAVG= 'AVERAGE GRADE'
VAPE30= '30 DAY VAPE USE- DICHOTOMOUS';
*2021*;
data school8_2021;
set mtfgr.grade821;
year=2021;
grade=8;
keep V7301 v7202 V1252 v1070 v7102 v7107 v7114 V7782 v7102d v7107d v7114d v507 v5 V7215 V7216 V7221 GRADLVL SEX RACE GRADAVG DAD_EDU MOM_EDU CIG30 MJ30 ALC30 VAPE30 AGE SCHOOL_REGION;
*CREATING GRADE LEVEL DISTINCTION*;
IF V7301 = 2 THEN GRADLVL= '8TH ';
ELSE IF V7301= 4 THEN GRADLVL= '10TH';
ELSE IF V7301 IN (1,3,5,6, -9) THEN DELETE;
*CREATING SEX LABELS*;
IF V7202= 1 THEN SEX= 'MALE';
ELSE IF V7202= 2 THEN SEX= 'FEMALE';
/* ELSE IF V7202= 3 THEN SEX= 'OTHER'; */
*CREATING RACE LABELS*;
IF V1070= 1 THEN RACE= 'BLACK/AFRICAN AMERICAN';
ELSE IF V1070= 2 THEN RACE= 'WHITE/CAUCASIAN';
ELSE IF V1070= 3 THEN RACE= 'HISPANIC';
*CREATING AGE LABELS*;
IF V1252= 1 THEN AGE= 'UNDER 16';
ELSE IF V1252= 2 THEN AGE= '16 OR OLDER';
ELSE IF V1252= (-9 -8) THEN delete;
*CREATING LABEL FOR SCHOOL REGION*;
IF V507= 1 THEN SCHOOL_REGION= 'NORTHEAST';
ELSE IF V507= 2 THEN SCHOOL_REGION= 'MIDWEST';
ELSE IF V507= 3 THEN SCHOOL_REGION= 'SOUTH';
ELSE IF V507= 4 THEN SCHOOL_REGION= 'WEST';
*CREATING GRADE AVERAGE INTO NEW VARIABLE*;
IF V7221 IN (9,8) THEN GRADAVG= 'A';
ELSE IF V7221 IN (7,6,5) THEN GRADAVG= 'B';
ELSE IF V7221 IN (4,3,2) THEN GRADAVG= 'C';
ELSE IF V7221= 1 THEN GRADAVG= 'D';
*CREATING FATHER EDUCATION INTO NEW VARIABLE*;
IF V7215 IN (1,2,3) THEN DAD_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V7215 IN (4,5) THEN DAD_EDU= 'UP TO COLLEGE';
ELSE IF V7215= 6 THEN DAD_EDU= 'GRAD SCHOOL';
ELSE IF V7215= 7 THEN DAD_EDU= 'DONT KNOW';
*CREATING MOTHER EDUCATION INTO NEW VARIABLE*;
IF V7216 IN (1,2,3) THEN MOM_EDU= 'UP TO HIGH SCHOOL';
ELSE IF V7216 IN (4,5) THEN MOM_EDU= 'UP TO COLLEGE';
ELSE IF V7216 = 6 THEN MOM_EDU= 'GRAD SCHOOL';
ELSE IF V7216= 7 THEN MOM_EDU= 'DONT KNOW';
/* CREATING CIG 30 DAY DICHOTOMOUS VARIABLE */
IF V7102D= 0 THEN CIG30= 'NO ';
ELSE IF V7102D = 1 THEN CIG30= 'YES';
/* CREATING ALCOHOL 30 DAY DICHOTOMOUS VARIABLE */
IF V7107D= 0 THEN ALC30= 'NO ';
ELSE IF V7107D= 1 THEN ALC30= 'YES';
/* CREATING MARIJUANA 30 DAY DICHOTOMOUS VARIABLE */
IF V7114D= 0 THEN MJ30= 'NO ';
ELSE IF V7114D= 1 THEN MJ30= 'YES';
/* CREATING VAPE 30 DAY DICHOTOMOUS VARIABLE */
IF V7782= 1 THEN VAPE30= 'NO ';
ELSE IF V7782 IN (2,3,4,5,6,7) THEN VAPE30= 'YES';
*labeling variables FOR MISSING VALUES*;
if v7202= -9 then v2150= .;
if v1070= -9 then vV1070= .;
/* if v2102= -9 then v2102= .; */
/* if v2106= -9 then v2106= .; */
/* if v2117= -9 then v2117= .; */
if v7221= -9 then v7221= .;
IF V7215= -9 THEN V7215= .;
IF V7216= -9 THEN V7216= .;
if V7102D= -9 then vV7102D= .;
if v7107D= -9 then v7107D= .;
if V7114D= -9 then V7114D= .;
IF V7782= -9 THEN V7782= .;
label SEX= 'SEX'
RACE= 'RACE'
CIG30= '30 DAY CIGARETTE USE- DICHOTOMOUS'
ALC30= '30 DAY ALCOHOL USE- DICHOTOMOUS'
MJ30= '30 DAY MARIJUANA USE- DICHOTOMOUS'
SCHOOL_REGION= 'SCHOOL REGION'
DAD_EDU= 'FATHER EDUCATION LEVEL'
MOM_EDU= 'MOTHER EDUCATION LEVEL'
GRADAVG= 'AVERAGE GRADE'
VAPE30= '30 DAY VAPE USE- DICHOTOMOUS';
*CONCATENATED DATA SETS 2019-2021 FOR 8TH AND 10TH GRADE*;
DATA SCHOOL1234;
SET SCHOOL8_2019 SCHOOL8_2020 SCHOOL8_2021;
rename v5=weight;
RUN;
*FORMATTING FOR CHARACTER STRINGS*;
PROC FORMAT; *FOR CHARACTER STRINGS*;
VALUE AGE_T 1= 'UNDER 16' 2= '16 AND OLDER/UNDER 18' 3= 'OVER 18';
VALUE GRAD_T 1= '8TH GRADE' 2= '10TH GRADE' 3= '12TH GRADE';
*complete data set w all grades after concatenating*;
DATA SCHOOL12345;
SET SCHOOL123 SCHOOL1234;
keep vape30 gradlvl SEX RACE SCHOOL_REGION AGE GRADAVG DAD_EDU MOM_EDU CIG30 ALC30 MJ30 AGE_T GRAD_T WEIGHT;
*creating GROUPINGS/ FORMATTING ALL VARIABLES FOR MULTIVARIABLE ANALYSIS*;
if AGE= 'UNDER 16' then AGE_T= 1;
ELSE IF AGE='16 OR OL' or AGE= 'UNDER 18' THEN AGE_T= 2;
ELSE IF AGE='18 OR OL' THEN AGE_T= 3;
IF GRADLVL ='8TH' THEN GRAD_T= 1;
else if grade =12 THEN GRAD_T= 3;
else IF GRADLVL='10TH' THEN GRAD_T= 2;
FORMAT AGE_T AGE_T. GRAD_T GRAD_T.;
RUN;
PROC CONTENTS DATA= SCHOOL12345;
*frequnecy count with procsurvey no strata, all grades*;
proc surveyfreq data=school12345;
TABLES (SEX RACE SCHOOL_REGION GRADAVG DAD_EDU MOM_EDU CIG30 ALC30 MJ30 GRAD_T AGE_T)*vape30/chisq;
where vape30 is not missing;
weight WEIGHT;
title "procsurveyfreq ALL GRADES, NO STRATIFICATION, 2019-2021";
RUN;
*multivariable logistic analysis*;
proc surveylogistic data=school12345;
class AGE_T(REF='UNDER 16') GRAD_T(REF='8TH GRADE') sex(ref='MALE') RACE(REF='WHITE/CAUCASIAN') SCHOOL_REGION(REF='NORTHEAST')
GRADAVG(REF='A') DAD_EDU(REF='UP TO COLLEGE') MOM_EDU(REF='UP TO COLLEGE') CIG30(REF='YES') ALC30(REF='YES') MJ30(REF='YES')/ PARAM=REF;
weight weight;
model vape30(EVENT='YES') = AGE_T GRAD_T SEX RACE SCHOOL_REGION GRADAVG DAD_EDU MOM_EDU alc30 cig30 mj30;
run;
... View more