## Gender and BW gap changes over time in the GSS Wordsum (SPSS syntax)

GSS data for SPSS format available here (select cumulative data set). Unfortunately, it wasn’t possible to exclude “hispanic” in the white or even in the black sample in the analysis of gap over time. For one reason : HISPANIC variable has not been created before the year 2000. We will see it just by using the simple and quick GSS crosstabulation SDA program. We can however look at the gender or racial gap using hispanic variable starting from the year 2000.

RECODE hispanic (1=1) (2 thru highest=2) INTO HISPANIC_RACE.

IF race=2 and HISPANIC_RACE=1 BHW_startingfrom2000=1.
IF HISPANIC_RACE=2 BHW_startingfrom2000=2.
IF race=1 and HISPANIC_RACE=1 BHW_startingfrom2000=3.

RECODE childs (0=1) (1=2) (2=3) (3 thru highest=4) INTO NumberChildren.
RECODE race (1=2) (2=1) (ELSE=SYSMIS) INTO BW.
RECODE age (20 thru 29=1) (30 thru 39=2) (40 thru 49=3) (50 thru 65=4) INTO AGE4.

RECODE AGE4 (1=1) INTO age4Cat0.
RECODE AGE4 (2=1) (3,4,1=0) INTO age4Cat1.
RECODE AGE4 (3=1) (2,4,1=0) INTO age4Cat2.
RECODE AGE4 (4=1) (2,3,1=0) INTO age4Cat3.

RECODE year (1972 thru 1982=1) (1983 thru 1990=2) (1991 thru 2000=3) (2001 thru 2012=4) INTO year4.

RECODE year4 (1=1) INTO Year4Cat0.
RECODE year4 (2=1) (3,4,1=0) INTO Year4Cat1.
RECODE year4 (3=1) (2,4,1=0) INTO Year4Cat2.
RECODE year4 (4=1) (2,3,1=0) INTO Year4Cat3.

COMPUTE sex_Year4Cat1=sex*Year4Cat1.
COMPUTE sex_Year4Cat2=sex*Year4Cat2.
COMPUTE sex_Year4Cat3=sex*Year4Cat3.

COMPUTE BW_Year4Cat1=BW*Year4Cat1.
COMPUTE BW_Year4Cat2=BW*Year4Cat2.
COMPUTE BW_Year4Cat3=BW*Year4Cat3.

RECODE cohort (1915 thru 1930=1) (1931 thru 1943=2) (1944 thru 1953=3) (1954 thru 1962=4) (1963 thru 1971=5) (1972 thru 1988=6) (ELSE=SYSMIS) INTO Cohort6.

RECODE Cohort6 (1=1) INTO Cohort6C0.
RECODE Cohort6 (2=1) (3,4,5,6,1=0) INTO Cohort6C1.
RECODE Cohort6 (3=1) (2,4,5,6,1=0) INTO Cohort6C2.
RECODE Cohort6 (4=1) (2,3,5,6,1=0) INTO Cohort6C3.
RECODE Cohort6 (5=1) (2,3,4,6,1=0) INTO Cohort6C4.
RECODE Cohort6 (6=1) (2,3,4,5,1=0) INTO Cohort6C5.

COMPUTE BW_Cohort6C1=BW*Cohort6C1.
COMPUTE BW_Cohort6C2=BW*Cohort6C2.
COMPUTE BW_Cohort6C3=BW*Cohort6C3.
COMPUTE BW_Cohort6C4=BW*Cohort6C4.
COMPUTE BW_Cohort6C5=BW*Cohort6C5.

COMPUTE sex_Cohort6C1=sex*Cohort6C1.
COMPUTE sex_Cohort6C2=sex*Cohort6C2.
COMPUTE sex_Cohort6C3=sex*Cohort6C3.
COMPUTE sex_Cohort6C4=sex*Cohort6C4.
COMPUTE sex_Cohort6C5=sex*Cohort6C5.

RECODE year (1972 thru 1975=1) (1976 thru 1979=2) (1980 thru 1983=3) (1984 thru 1987=4) (1988 thru 1991=5) (1992 thru 1995=6) (1996 thru 1999=7) (2000 thru 2003=8) (2004 thru 2007=9) (2008 thru 2012=10) INTO Year10.

COMPUTE BW_Year4=BW*year4.
COMPUTE BW_Year10=BW*year10.
COMPUTE BW_Cohort6=BW*cohort6.
COMPUTE sex_Year4=sex*year4.
COMPUTE sex_Year10=sex*year10.
COMPUTE sex_cohort6=sex*cohort6.

RECODE cohort (1909 thru 1919=1) (1920 thru 1929=2) (1930 thru 1939=3) (1940 thru 1949=4) (1950 thru 1959=5) (1960 thru 1969=6) (1970 thru 1976=7) (1977 thru 1990=8) (ELSE=SYSMIS) INTO GSScohort8.

RECODE GSScohort8 (1=1) INTO Cohort8Cat0.
RECODE GSScohort8 (2=1) (3,4,5,6,7,8,1=0) INTO Cohort8Cat1.
RECODE GSScohort8 (3=1) (2,4,5,6,7,8,1=0) INTO Cohort8Cat2.
RECODE GSScohort8 (4=1) (2,3,5,6,7,8,1=0) INTO Cohort8Cat3.
RECODE GSScohort8 (5=1) (2,3,4,6,7,8,1=0) INTO Cohort8Cat4.
RECODE GSScohort8 (6=1) (2,3,4,5,7,8,1=0) INTO Cohort8Cat5.
RECODE GSScohort8 (7=1) (2,3,4,5,6,8,1=0) INTO Cohort8Cat6.
RECODE GSScohort8 (8=1) (2,3,4,5,6,7,1=0) INTO Cohort8Cat7.

COMPUTE BW_Cohort8Cat1=BW*Cohort8Cat1.
COMPUTE BW_Cohort8Cat2=BW*Cohort8Cat2.
COMPUTE BW_Cohort8Cat3=BW*Cohort8Cat3.
COMPUTE BW_Cohort8Cat4=BW*Cohort8Cat4.
COMPUTE BW_Cohort8Cat5=BW*Cohort8Cat5.
COMPUTE BW_Cohort8Cat6=BW*Cohort8Cat6.
COMPUTE BW_Cohort8Cat7=BW*Cohort8Cat7.

RECODE cohort (1920 thru 1929=1) (1930 thru 1939=2) (1940 thru 1949=3) (1950 thru 1959=4) (1960 thru 1969=5) (1970 thru 1976=6) (1977 thru 1990=7) (ELSE=SYSMIS) INTO GSScohort7.

RECODE GSScohort7 (1=1) INTO Cohort7Cat0.
RECODE GSScohort7 (2=1) (3,4,5,6,7,1=0) INTO Cohort7Cat1.
RECODE GSScohort7 (3=1) (2,4,5,6,7,1=0) INTO Cohort7Cat2.
RECODE GSScohort7 (4=1) (2,3,5,6,7,1=0) INTO Cohort7Cat3.
RECODE GSScohort7 (5=1) (2,3,4,6,7,1=0) INTO Cohort7Cat4.
RECODE GSScohort7 (6=1) (2,3,4,5,7,1=0) INTO Cohort7Cat5.
RECODE GSScohort7 (7=1) (2,3,4,5,6,1=0) INTO Cohort7Cat6.

COMPUTE BW_Cohort7Cat1=BW*Cohort7Cat1.
COMPUTE BW_Cohort7Cat2=BW*Cohort7Cat2.
COMPUTE BW_Cohort7Cat3=BW*Cohort7Cat3.
COMPUTE BW_Cohort7Cat4=BW*Cohort7Cat4.
COMPUTE BW_Cohort7Cat5=BW*Cohort7Cat5.
COMPUTE BW_Cohort7Cat6=BW*Cohort7Cat6.

RECODE cohort (1930 thru 1939=1) (1940 thru 1949=2) (1950 thru 1959=3) (1960 thru 1969=4) (1970 thru 1976=5) (1977 thru 1990=6) (ELSE=SYSMIS) INTO GSScohort6.

RECODE GSScohort6 (1=1) INTO Cohort6Cat0.
RECODE GSScohort6 (2=1) (3,4,5,6,1=0) INTO Cohort6Cat1.
RECODE GSScohort6 (3=1) (2,4,5,6,1=0) INTO Cohort6Cat2.
RECODE GSScohort6 (4=1) (2,3,5,6,1=0) INTO Cohort6Cat3.
RECODE GSScohort6 (5=1) (2,3,4,6,1=0) INTO Cohort6Cat4.
RECODE GSScohort6 (6=1) (2,3,4,5,1=0) INTO Cohort6Cat5.

COMPUTE BW_Cohort6Cat1=BW*Cohort6Cat1.
COMPUTE BW_Cohort6Cat2=BW*Cohort6Cat2.
COMPUTE BW_Cohort6Cat3=BW*Cohort6Cat3.
COMPUTE BW_Cohort6Cat4=BW*Cohort6Cat4.
COMPUTE BW_Cohort6Cat5=BW*Cohort6Cat5.

COMPUTE sex_Cohort6Cat1=sex*Cohort6Cat1.
COMPUTE sex_Cohort6Cat2=sex*Cohort6Cat2.
COMPUTE sex_Cohort6Cat3=sex*Cohort6Cat3.
COMPUTE sex_Cohort6Cat4=sex*Cohort6Cat4.
COMPUTE sex_Cohort6Cat5=sex*Cohort6Cat5.

REGRESSION
/MISSING LISTWISE
/STATISTICS COEFF OUTS R ANOVA
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER age
/SAVE ZRESID.

RECODE ZRE_1 (lowest thru highest=COPY) INTO zWordsum_Age.

DESCRIPTIVES VARIABLES=wordsum
/SAVE
/STATISTICS=MEAN STDDEV MIN MAX.

COMPUTE wtssall_oversamp=wtssall*oversamp.

WEIGHT BY wtssall_oversamp.

USE ALL.
COMPUTE filter_\$=(Zwordsum>-3).
VARIABLE LABELS filter_\$ ‘Zwordsum>-3 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

SET MXCELLS=9000.

MEANS TABLES=zWordsum_Age Wordsum age BY sex BY BW BY year4
/CELLS MEAN COUNT STDDEV.

MEANS TABLES=zWordsum_Age Wordsum age BY sex BY BW BY cohort6
/CELLS MEAN COUNT STDDEV.

SORT CASES BY sex year4.
SPLIT FILE LAYERED BY sex year4.

T-TEST GROUPS=BW(1 2)
/MISSING=ANALYSIS
/VARIABLES=zWordsum_Age wordsum
/CRITERIA=CI(.95).

SORT CASES BY sex cohort6.
SPLIT FILE LAYERED BY sex cohort6.

T-TEST GROUPS=BW(1 2)
/MISSING=ANALYSIS
/VARIABLES=zWordsum_Age wordsum
/CRITERIA=CI(.95).

SORT CASES BY BW year4.
SPLIT FILE LAYERED BY BW year4.

T-TEST GROUPS=sex(1 2)
/MISSING=ANALYSIS
/VARIABLES=zWordsum_Age wordsum
/CRITERIA=CI(.95).

SORT CASES BY BW cohort6.
SPLIT FILE LAYERED BY BW cohort6.

T-TEST GROUPS=sex(1 2)
/MISSING=ANALYSIS
/VARIABLES=zWordsum_Age wordsum
/CRITERIA=CI(.95).

SPLIT FILE OFF.

USE ALL.
COMPUTE filter_\$=(Zwordsum_Age>-3 and Zwordsum_Age<0).
VARIABLE LABELS filter_\$ ‘Zwordsum_Age>-3 and Zwordsum_Age<0 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

MEANS TABLES=zWordsum_Age Wordsum age BY sex BY BHW_startingfrom2000
/CELLS MEAN COUNT STDDEV.

MEANS TABLES=zWordsum_Age Wordsum age childs BY BW BY cohort6
/CELLS MEAN COUNT STDDEV.

MEANS TABLES=zWordsum_Age Wordsum age BY sex BY BW BY cohort6
/CELLS MEAN COUNT STDDEV.

SORT CASES BY cohort6.
SPLIT FILE LAYERED BY cohort6.

T-TEST GROUPS=BW(1 2)
/MISSING=ANALYSIS
/VARIABLES=zWordsum_Age wordsum
/CRITERIA=CI(.95).

SPLIT FILE OFF.

USE ALL.
COMPUTE filter_\$=(Zwordsum_Age>=0).
VARIABLE LABELS filter_\$ ‘Zwordsum_Age>=0 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

MEANS TABLES=zWordsum_Age Wordsum age BY sex BY BHW_startingfrom2000
/CELLS MEAN COUNT STDDEV.

MEANS TABLES=zWordsum_Age Wordsum age childs BY BW BY cohort6
/CELLS MEAN COUNT STDDEV.

MEANS TABLES=zWordsum_Age Wordsum age BY sex BY BW BY cohort6
/CELLS MEAN COUNT STDDEV.

SORT CASES BY cohort6.
SPLIT FILE LAYERED BY cohort6.

T-TEST GROUPS=BW(1 2)
/MISSING=ANALYSIS
/VARIABLES=zWordsum_Age wordsum
/CRITERIA=CI(.95).

SPLIT FILE OFF.

USE ALL.
COMPUTE filter_\$=(Zwordsum>-3 and BW=1).
VARIABLE LABELS filter_\$ ‘Zwordsum>-3 and BW=1 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

MEANS TABLES=wordsum BY Cohort6C0 Cohort6C1 Cohort6C2 Cohort6C3 Cohort6C4 Cohort6C5
Year4Cat0 Year4Cat1 Year4Cat2 Year4Cat3 BY sex
/CELLS MEAN COUNT STDDEV.

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age cohort6
/METHOD=ENTER sex_cohort6
/PARTIALPLOT ALL
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age year4
/METHOD=ENTER sex_year4
/PARTIALPLOT ALL
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age Cohort6C1 to Cohort6C5
/METHOD=ENTER sex_Cohort6C1 to sex_Cohort6C5
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age Year4Cat1 to Year4Cat3
/METHOD=ENTER sex_Year4Cat1 to sex_Year4Cat3
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

WEIGHT BY wtssall.

USE ALL.
COMPUTE filter_\$=(Zwordsum>-3 and BW=2).
VARIABLE LABELS filter_\$ ‘Zwordsum>-3 and BW=2 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

MEANS TABLES=wordsum BY Cohort6C0 Cohort6C1 Cohort6C2 Cohort6C3 Cohort6C4 Cohort6C5
Year4Cat0 Year4Cat1 Year4Cat2 Year4Cat3 BY sex
/CELLS MEAN COUNT STDDEV.

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age cohort6
/METHOD=ENTER sex_cohort6
/PARTIALPLOT ALL
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age year4
/METHOD=ENTER sex_year4
/PARTIALPLOT ALL
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age Cohort6C1 to Cohort6C5
/METHOD=ENTER sex_Cohort6C1 to sex_Cohort6C5
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age Year4Cat1 to Year4Cat3
/METHOD=ENTER sex_Year4Cat1 to sex_Year4Cat3
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

WEIGHT BY wtssall_oversamp.

USE ALL.
COMPUTE filter_\$=(Zwordsum>-3).
VARIABLE LABELS filter_\$ ‘Zwordsum>-3 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age BW year10
/METHOD=ENTER BW_YEAR10
/PARTIALPLOT ALL
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER sex age BW cohort6
/METHOD=ENTER BW_COHORT6
/PARTIALPLOT ALL
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

UNIANOVA wordsum BY BW Cohort6 WITH age sex
/METHOD=SSTYPE(3)
/INTERCEPT=INCLUDE
/PLOT=PROFILE(Cohort6*BW)
/EMMEANS=TABLES(BW) WITH(age=MEAN sex=MEAN)
/EMMEANS=TABLES(Cohort6) WITH(age=MEAN sex=MEAN)
/EMMEANS=TABLES(BW*Cohort6) WITH(age=MEAN sex=MEAN)
/PRINT=LOF OPOWER ETASQ HOMOGENEITY DESCRIPTIVE
/CRITERIA=ALPHA(.05)
/DESIGN=age sex BW Cohort6 BW*Cohort6.

UNIANOVA wordsum BY BW Year4 WITH age sex
/METHOD=SSTYPE(3)
/INTERCEPT=INCLUDE
/PLOT=PROFILE(Year4*BW)
/EMMEANS=TABLES(BW) WITH(age=MEAN sex=MEAN)
/EMMEANS=TABLES(Year4) WITH(age=MEAN sex=MEAN)
/EMMEANS=TABLES(BW*Year4) WITH(age=MEAN sex=MEAN)
/PRINT=LOF OPOWER ETASQ HOMOGENEITY DESCRIPTIVE
/CRITERIA=ALPHA(.05)
/DESIGN=age sex BW Year4 BW*Year4.

USE ALL.
COMPUTE filter_\$=(Zwordsum>-3).
VARIABLE LABELS filter_\$ ‘Zwordsum>-3 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

MEANS TABLES=wordsum BY Cohort6Cat0 Cohort6Cat1 Cohort6Cat2 Cohort6Cat3 Cohort6Cat4 Cohort6Cat5
Year4Cat0 Year4Cat1 Year4Cat2 Year4Cat3 BY sex
/CELLS MEAN COUNT STDDEV.

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER age sex BW Cohort8Cat1 to Cohort8Cat7
/METHOD=ENTER BW_Cohort8Cat1 to BW_Cohort8Cat7
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER age sex BW Cohort7Cat1 to Cohort7Cat6
/METHOD=ENTER BW_Cohort7Cat1 to BW_Cohort7Cat6
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER age sex BW Cohort6C1 to Cohort6C5
/METHOD=ENTER BW_Cohort6C1 to BW_Cohort6C5
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

REGRESSION
/DESCRIPTIVES MEAN STDDEV CORR SIG N
/MISSING LISTWISE
/STATISTICS COEFF OUTS CI(95) R ANOVA COLLIN TOL CHANGE ZPP
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT wordsum
/METHOD=ENTER age sex BW Year4Cat1 to Year4Cat3
/METHOD=ENTER BW_Year4Cat1 to BW_Year4Cat3
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS HISTOGRAM(ZRESID) NORMPROB(ZRESID).

MEANS TABLES=zWordsum_Age Wordsum BY BW BY year4
/CELLS MEAN COUNT STDDEV.

WEIGHT BY wtssall_oversamp.

USE ALL.
COMPUTE filter_\$=(Zwordsum>-3).
VARIABLE LABELS filter_\$ ‘Zwordsum>-3 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

MEANS TABLES=zWordsum_Age Wordsum BY sex BY BHW_startingfrom2000 by year
/CELLS MEAN COUNT STDDEV.

MEANS TABLES=zWordsum_Age Wordsum BY BHW_startingfrom2000 by year
/CELLS MEAN COUNT STDDEV.

USE ALL.
COMPUTE filter_\$=(Zwordsum>-3 and wordsum<=5).
VARIABLE LABELS filter_\$ ‘Zwordsum>-3 and wordsum<=5 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

UNIANOVA wordsum BY BW Cohort6 WITH age sex
/METHOD=SSTYPE(3)
/INTERCEPT=INCLUDE
/PLOT=PROFILE(Cohort6*BW)
/EMMEANS=TABLES(BW) WITH(age=MEAN sex=MEAN)
/EMMEANS=TABLES(Cohort6) WITH(age=MEAN sex=MEAN)
/EMMEANS=TABLES(BW*Cohort6) WITH(age=MEAN sex=MEAN)
/PRINT=LOF OPOWER ETASQ HOMOGENEITY DESCRIPTIVE
/CRITERIA=ALPHA(.05)
/DESIGN=age sex BW Cohort6 BW*Cohort6.

USE ALL.
COMPUTE filter_\$=(wordsum>=6).
VARIABLE LABELS filter_\$ ‘wordsum>=6 (FILTER)’.
VALUE LABELS filter_\$ 0 ‘Not Selected’ 1 ‘Selected’.
FORMATS filter_\$ (f1.0).
FILTER BY filter_\$.
EXECUTE.

UNIANOVA wordsum BY BW Cohort6 WITH age sex
/METHOD=SSTYPE(3)
/INTERCEPT=INCLUDE
/PLOT=PROFILE(Cohort6*BW)
/EMMEANS=TABLES(BW) WITH(age=MEAN sex=MEAN)
/EMMEANS=TABLES(Cohort6) WITH(age=MEAN sex=MEAN)
/EMMEANS=TABLES(BW*Cohort6) WITH(age=MEAN sex=MEAN)
/PRINT=LOF OPOWER ETASQ HOMOGENEITY DESCRIPTIVE