Examples of Testing for Significant Differences Between Regression Coefficients Using the Afifi & Clark (1984) Data

>USE "D:\mydocs\ys209\survey2.syd"

SYSTAT Rectangular file D:\mydocs\ys209\survey2.syd,

created Mon Feb 25, 2002 at 09:34:47, contains variables:

 ID           SEX          AGE          MARITAL      EDUCATN      EMPLOY
 INCOME       RELIGION     BLUE         DEPRESS      LONELY       CRY
 SAD          FEARFUL      FAILURE      AS_GOOD      HOPEFUL      HAPPY
 ENJOY        BOTHERED     NO_EAT       EFFORT       BADSLEEP     GETGOING
 MIND         TALKLESS     UNFRNDLY     DISLIKE      TOTAL        CASECONT
 DRINK        HEALTHY      DOCTOR       MEDS         BED_DAYS     ILLNESS
 CHRONIC      MARITAL$     SEX$         AGE$         EDUC$

>rem this is command file m803.syc
>mglh
>let female=0
>if sex=2 then let female=1
>let hsdro=0
>if educatn=1 or educatn=2 then let hsdro=1
>let hsgra=0
>if educatn=3 then let hsgra=1
>let somco=0
>if educatn=4 then let somco=1
>let cogra=0
>if educatn=5 then let cogra=1
>let grade=0
>if educatn=6 or educatn=7 then let grade=1
>rem select males only, as results are more straightforward
>select female=0
>model income=constant+hsgra+somco+cogra+grade
>estimate

Data for the following results were selected according to:
      female=0

Dep Var: INCOME   N: 104   Multiple R: 0.476   Squared multiple R: 0.227
Adjusted squared multiple R: 0.196   Standard error of estimate: 14.723

Effect         Coefficient    Std Error     Std Coef Tolerance     t   P(2 Tail)

CONSTANT            13.389        3.470        0.000      .       3.858    0.000
HSGRA                7.842        4.195        0.232     0.505    1.869    0.065
SOMCO               15.905        4.979        0.360     0.615    3.194    0.002
COGRA               17.549        5.059        0.388     0.626    3.469    0.001
GRADE               24.825        5.247        0.519     0.650    4.732    0.000

                             Analysis of Variance

Source             Sum-of-Squares   df  Mean-Square     F-ratio       P
Regression              6302.889     4     1575.722       7.269       0.000
Residual               21460.025    99      216.768

----------------------------------------------------------------------------------
Durbin-Watson D Statistic     1.933
First Order Autocorrelation   0.028

>hypothesis
>specify somco=cogra
>test

Hypothesis.

A Matrix

                         1           2           3           4           5
                         0.000       0.000      -1.000       1.000       0.000

Null hypothesis value for D

                         0.000

Test of Hypothesis

       Source       SS        df       MS              F              P

  Hypothesis       22.260     1       22.260          0.103          0.749
  Error         21460.025    99      216.768

--------------------------------------------------------------------------------

>hypothesis
>specify grade=cogra
>test

Hypothesis.

A Matrix

                         1           2           3           4           5
                         0.000       0.000       0.000       1.000      -1.000

Null hypothesis value for D

                         0.000

Test of Hypothesis

       Source       SS        df       MS              F              P

  Hypothesis      395.372     1      395.372          1.824          0.180
  Error         21460.025    99      216.768

---------------------------------------------------------------------------------

>hypothesis
>specify cogra=hsgra
>test

Hypothesis.

A Matrix

                         1           2           3           4           5
                         0.000       1.000       0.000      -1.000       0.000

Null hypothesis value for D

                         0.000

Test of Hypothesis

       Source       SS        df       MS              F              P

  Hypothesis     1068.976     1     1068.976          4.931          0.029
  Error         21460.025    99      216.768

--------------------------------------------------------------------------------
>select



Last Modified 22 Mar 2002