NOTE: FULTON COUNTY= ATLANTA KENT COUNTY= GRAND RAPIDS ALL CONTROLS ACROSS SITES 17:04 Thursday, July 2, 1998 77 Mean (fullwgtd) Child Outcomes for Cs, BY SITE Survey site=FULTON Variable Label N Mean Std Dev Minimum Maximum ---------------------------------------------------------------------------------------------------------------- BRAKNRAW Braken Raw Score 487 46.9323367 10.8727017 0 61.0000000 CTHLTFD2 Maternal rept F Childs Good Health 0/1 505 0.7675978 0.4036028 0 1.0000000 ---------------------------------------------------------------------------------------------------------------- Survey site=KENT Variable Label N Mean Std Dev Minimum Maximum ---------------------------------------------------------------------------------------------------------------- BRAKNRAW Braken Raw Score 212 46.3278392 11.5340409 7.0000000 60.0000000 CTHLTFD2 Maternal rept F Childs Good Health 0/1 216 0.7918566 0.3937959 0 1.0000000 ---------------------------------------------------------------------------------------------------------------- Survey site=RIVERSIDE Variable Label N Mean Std Dev Minimum Maximum ---------------------------------------------------------------------------------------------------------------- BRAKNRAW Braken Raw Score 460 46.4390537 11.0639008 0 61.0000000 CTHLTFD2 Maternal rept F Childs Good Health 0/1 484 0.8149268 0.3525652 0 1.0000000 ---------------------------------------------------------------------------------------------------------------- ALL CONTROLS ACROSS SITES 17:04 Thursday, July 2, 1998 79 Mean (fullwgtd) Child Outcomes for Cs, BY SITE General Linear Models Procedure Class Level Information Class Levels Values SITE 3 FULTON KENT RIVERSIDE Number of observations in data set = 1208 NOTE: Due to missing values, only 1159 observations can be used in this analysis. ALL CONTROLS ACROSS SITES 17:04 Thursday, July 2, 1998 80 Mean (fullwgtd) Child Outcomes for Cs, BY SITE General Linear Models Procedure Dependent Variable: BRAKNRAW Braken Raw Score Weight: FULLWGT Source DF Sum of Squares Mean Square F Value Pr > F Model 3 37457.45293944 12485.81764648 138.23 0.0001 Error 1155 104324.38430795 90.32414226 Corrected Total 1158 141781.83724739 R-Square C.V. Root MSE BRAKNRAW Mean 0.264191 20.38082 9.50390142 46.63160569 Source DF Type I SS Mean Square F Value Pr > F SITE 2 72.69494153 36.34747076 0.40 0.6688 CHAGERAD 1 37384.75799791 37384.75799791 413.90 0.0001 Source DF Type III SS Mean Square F Value Pr > F SITE 2 362.33266838 181.16633419 2.01 0.1350 CHAGERAD 1 37384.75799791 37384.75799791 413.90 0.0001 T for H0: Pr > |T| Std Error of Parameter Estimate Parameter=0 Estimate INTERCEPT 15.46639363 B 9.68 0.0001 1.59828840 SITE FULTON -1.21870002 B -1.82 0.0686 0.66851865 KENT -1.28207632 B -1.54 0.1243 0.83365161 RIVERSIDE 0.00000000 B . . . CHAGERAD 0.62033696 20.34 0.0001 0.03049175 NOTE: The X'X matrix has been found to be singular and a generalized inverse was used to solve the normal equations. Estimates followed by the letter 'B' are biased, and are not unique estimators of the parameters. ALL CONTROLS ACROSS SITES 17:04 Thursday, July 2, 1998 81 Mean (fullwgtd) Child Outcomes for Cs, BY SITE General Linear Models Procedure Least Squares Means SITE BRAKNRAW Std Err Pr > |T| Pr > |T| H0: LSMEAN(i)=LSMEAN(j) LSMEAN LSMEAN H0:LSMEAN=0 i/j 1 2 3 FULTON 46.0845210 0.4525430 0.0001 1 . 0.9378 0.0686 KENT 46.0211447 0.6746203 0.0001 2 0.9378 . 0.1243 RIVERSIDE 47.3032210 0.4884483 0.0001 3 0.0686 0.1243 . NOTE: To ensure overall protection level, only probabilities associated with pre-planned comparisons should be used. ALL CONTROLS ACROSS SITES 17:04 Thursday, July 2, 1998 133 Mean (fullwgtd) Child Outcomes for Cs, BY SITE General Linear Models Procedure Class Level Information Class Levels Values SITE 3 FULTON KENT RIVERSIDE Number of observations in data set = 1208 NOTE: Due to missing values, only 1205 observations can be used in this analysis. ALL CONTROLS ACROSS SITES 17:04 Thursday, July 2, 1998 134 Mean (fullwgtd) Child Outcomes for Cs, BY SITE General Linear Models Procedure Dependent Variable: CTHLTFD2 Maternal rept F Childs Good Health 0/1 Weight: FULLWGT Source DF Sum of Squares Mean Square F Value Pr > F Model 2 0.47900381 0.23950190 1.64 0.1943 Error 1202 175.47831842 0.14598862 Corrected Total 1204 175.95732223 R-Square C.V. Root MSE CTHLTFD2 Mean 0.002722 48.36581 0.38208457 0.78998901 Source DF Type I SS Mean Square F Value Pr > F SITE 2 0.47900381 0.23950190 1.64 0.1943 Source DF Type III SS Mean Square F Value Pr > F SITE 2 0.47900381 0.23950190 1.64 0.1943 T for H0: Pr > |T| Std Error of Parameter Estimate Parameter=0 Estimate INTERCEPT 0.8149267900 B 42.55 0.0001 0.01915039 SITE FULTON -.0473290087 B -1.81 0.0706 0.02615249 KENT -.0230701829 B -0.70 0.4845 0.03299124 RIVERSIDE 0.0000000000 B . . . NOTE: The X'X matrix has been found to be singular and a generalized inverse was used to solve the normal equations. Estimates followed by the letter 'B' are biased, and are not unique estimators of the parameters. ALL CONTROLS ACROSS SITES 17:04 Thursday, July 2, 1998 135 Mean (fullwgtd) Child Outcomes for Cs, BY SITE General Linear Models Procedure Least Squares Means SITE CTHLTFD2 Std Err Pr > |T| Pr > |T| H0: LSMEAN(i)=LSMEAN(j) LSMEAN LSMEAN H0:LSMEAN=0 i/j 1 2 3 FULTON 0.76759778 0.01781054 0.0001 1 . 0.4518 0.0706 KENT 0.79185661 0.02686419 0.0001 2 0.4518 . 0.4845 RIVERSIDE 0.81492679 0.01915039 0.0001 3 0.0706 0.4845 . NOTE: To ensure overall protection level, only probabilities associated with pre-planned comparisons should be used.