* Syntax to format cross sectional data into format required for ESRC archive
http://www.data-archive.ac.uk/create-manage/document/data-level
http://www.data-archive.ac.uk/create-manage/document/data-level?index=1  .



* ALGEBRA ############################################# .
GET  FILE='D:\Documents\Academic\ICCAMS\data\FINAL_DATASETS\1XSection\alg right wrong phase 1 cross sectional.sav'.
DATASET NAME alg WINDOW=FRONT.

* qns 2a & 2b are duplicated in 2ab .
DELETE VARIABLES alg02aa_r alg02bb_r .

DO REPEAT V=alg01aa_r to alg26cc_r  .
recode V (sysmis=-9) .
MISSING VALUES V (-9) .
END REPEAT .
EXECUTE .

VALUE LABELS  alg01aa_r to alg26cc_r  0 'Wrong' 1 'Right' .

variable labels alg01aa_r 'If x? x + 2, 6 ->?' .
variable labels alg01bb_r 'If x? 4x, 3 ->?' .
variable labels alg01cc_r 'If x? x + 2, c ->?' .
variable labels alg02ab_r 'Smallest and largest of n+1, n+4, n-3, n, n-7' .
variable labels alg03ab_r 'Which is larger, 2n or n + 2 ? Explain why' .
variable labels alg04aa_r 'Add 4 to 8' .
variable labels alg04bb_r 'Add 4 to n+5' .
variable labels alg04cc_r 'Add 4 to 3n' .
variable labels alg04dd_r 'Mult 8 by 4' .
variable labels alg04ee_r 'Mult n+5 by 4' .
variable labels alg04ff_r 'Mult 3n by 4' .
variable labels alg05aa_r 'If a+b=43, a+b+2=?' .
variable labels alg05bb_r 'If n-246=761, n-247=?' .
variable labels alg05cc_r 'If e+f=8, e+f+g=?' .
variable labels alg06aa_r 'a, if a+5=8' .
variable labels alg06bb_r 'b, if b+2=2b' .
variable labels alg07aa_r 'Area of rect 3 x 4' .
variable labels alg07bb_r 'Area of rect 6 x 10' .
variable labels alg07cc_r 'Area of rect n x m' .
variable labels alg07dd_r 'Area of rect 5 x (e+2)' .
variable labels alg08@@_r 'Perimeter, if sides 9+1+10+2' .
variable labels alg09aa_r 'Perimeter, if sides e+e+e' .
variable labels alg09bb_r 'Perimeter, if sides h+h+h+h+t' .
variable labels alg09cc_r 'Perimeter, if sides u+u+5+5+6' .
variable labels alg09dd_r 'Perimeter, if n sides of length 2' .
variable labels alg10aa_r 'c=#carrots@8p, t=#turnips@6p, 8c+6t stands for?' .
variable labels alg10bb_r 'c=#carrots@8p, t=#turnips@6p, total no of veg=?' .
variable labels alg11aa_r 'u=v+3, v=1, u=?' .
variable labels alg11bb_r 'm=3n+1, n=4, m=?' .
variable labels alg12@@_r 'John has J marbles, Petra has P marbles, tot no of marbles=?' .
variable labels alg13aa_r 'Simplify 2a+5a' .
variable labels alg13bb_r 'Simplify 2a+5b' .
variable labels alg13cc_r 'Simplify (a+b)+a' .
variable labels alg13dd_r 'Simplify 2a+5b+a' .
variable labels alg13ee_r 'Simplify (a-b)+b' .
variable labels alg13ff_r 'Simplify 3a-(b+a)' .
variable labels alg13gg_r 'Simplify a+4+a-4' .
variable labels alg13hh_r 'Simplify 3a-b-a' .
variable labels alg13ii_r 'Simplify (a+b)+(a-b)' .
variable labels alg14@@_r 'If r=s+t,r+s+t=30, r=?' .
variable labels alg15aa_r 'Diagonals = sides-3, 57 sides ? ?' .
variable labels alg15bb_r 'Diagonals = sides-3, k sides ? ?' .
variable labels alg16@@_r 'If c+d=10, c<d, what can you say about c?' .
variable labels alg17aa_r '£200/day + £20/hr overtime, h=hrs overtime, P=total pay, write equation connecting P and h' .
variable labels alg17bb_r '£200/day + £20/hr overtime, h=hrs overtime, P=total pay, if h=4, P=?' .
variable labels alg18aa_r 'A+B+C=C+A+B: true always, never, sometimes?' .
variable labels alg18bb_r 'L+M+N=L+P+N: true always, never, sometimes (when?)? ' .
variable labels alg19aa_r 'a=b+3, b inc by 2, what happens to a?' .
variable labels alg19bb_r 'f=3g+1, g inc by 2, what happens to f?' .
variable labels alg20@@_r 'Cakes cost c pence each and buns cost b pence each.  If I buy 4 cakes and 3 buns,  what does  4c + 3b stand for?' .
variable labels alg21@@_r 'If (x + 1)^3 + x = 349 when x=6, solve (5x + 1)^3 + 5x = 349' .
variable labels alg22@@_r 'Total cost of b blue pencils @ 5p & r red pencils @ 6p is 90p. Write equation in b & r' .
variable labels alg23ab_r 'Machine does +10 then x5. Equivalent to x?? then +??' .
variable labels alg24@@_r 'a, b, and d are positive whole numbers. When is a/b < a/d?' .
variable labels alg25aa_r 'What does * mean in spreadsheet formula?' .
variable labels alg25bc_r 'Which is larger, "=2+(100*A5)" or "=100+(2*A5)"? Explain why' .
variable labels alg26aa_r 'Value of "=B3+8" if B3=20' .
variable labels alg26bb_r 'Name of spreadsheet cell' .
variable labels alg26cc_r 'Formula to give 5 times value in D4' .





* GENERAL VARIABLES ############################################## .
*change ICCAMS_ID to PUPIL_ID .
RENAME VARIABLES ( ICCAMS_ID = PUPIL_ID ) .
*remove n_qns (these are part questions on original paper, may not correspond with coded qns) .
DELETE VARIABLES n_qns .
DELETE VARIABLES N_levels .

* convert dob to month & year .
compute dob = DATE.MOYR(XDATE.MONTH(dob) , XDATE.YEAR(dob) ) .
formats dob (MOYR8) .
execute .


variable labels test_ID 'Unique test response identifier' .
variable labels test_type 'Type of test' .
variable labels test_year 'Year in which test taken' .
variable labels test_date 'Date test taken (imputed from set/batch if missing)' .
variable labels sch 'School code' .
variable labels phase 'Phase in ICCAMS project' .
variable labels year 'School year group (grade) when test taken' .
variable labels PUPIL_ID 'ICCAMS unique pupil identifier' .
variable labels sex 'Sex (1=m, 2=f)' .
variable labels dob 'Date of birth (date format)' .
variable labels MidYIS_score 'Overall MidYIS score' .
variable labels weight 'Weight applied to give nationally representative sample' .
variable labels alg_total 'Total score on Algebra items' .
variable labels alg_CSMS_total 'Total score on CSMS Algebra items' .
variable labels L1 'CSMS Level 1 achieved' .
variable labels L2 'CSMS Level 2 achieved' .
variable labels L3 'CSMS Level 3 achieved' .
variable labels L4 'CSMS Level 4 achieved' .
variable labels L5 'CSMS Level 5 achieved' .
variable labels L6 'CSMS Level 6 achieved' .
variable labels HiLev 'CSMS level' .


RECODE year (sysmis = -9) .
RECODE sex (sysmis = -9) .
RECODE L1 (sysmis = -9) .
RECODE L2 (sysmis = -9) .
RECODE L3 (sysmis = -9) .
RECODE L4 (sysmis = -9) .
RECODE HiLev (sysmis = -9) .


MISSING VALUES year (-9) .
MISSING VALUES sex (-9) .
MISSING VALUES L1 (-9) .
MISSING VALUES L2 (-9) .
MISSING VALUES L3 (-9) .
MISSING VALUES L4 (-9) .
MISSING VALUES HiLev (-9) .



SAVE OUTFILE='D:\Documents\Academic\ICCAMS\data\FINAL_DATASETS\ESRC archive\algebra.sav'
  /COMPRESSED.

DATASET CLOSE alg .