I am supposed to find the SD from the SE for the last two main effects. What I have so far is Verbal (M = 36.34, SD =___ ),(M = 44.02, SD = __), score averaged across grades 3 and 5 lower for AC schools (M = 36.25, SD =__ ) than for non AC schools (M = 44.12, SD = __).
The data set is below. i don't know how to find SD from this output.
General Linear Model
Notes
Output Created
2011-09-07T21:03:17.578
Comments
Input
Data
C:\Documents and Settings\User\Local Settings\Temporary Internet Files\Content.Outlook\SK981VS2\ODUNJO Dissertation Data set ITBS Scores AC and Non AC 2003 - 2010.sav
Active Dataset
DataSet1
Filter
<none>
Weight
<none>
Split File
<none>
N of Rows in Working Data File
316
Missing Value Handling
Definition of Missing
User-defined missing values are treated as missing.
Cases Used
Statistics are based on all cases with valid data for all variables in the model.
Syntax
GLM VocPct CompPct BY AC Grade
/WSFACTOR=teat 2 Polynomial
/METHOD=SSTYPE(3)
/EMMEANS=TABLES(AC)
/EMMEANS=TABLES(Grade)
/EMMEANS=TABLES(teat)
/EMMEANS=TABLES(AC*Grade)
/EMMEANS=TABLES(AC*teat)
/EMMEANS=TABLES(Grade*teat)
/EMMEANS=TABLES(AC*Grade*teat)
/CRITERIA=ALPHA(.05)
/WSDESIGN=teat
/DESIGN=AC Grade AC*Grade.
Resources
Processor Time
0:00:00.172
Elapsed Time
0:00:00.109
[DataSet1] C:\Documents and Settings\User\Local Settings\Temporary Internet Files\Content.Outlook\SK981VS2\ODUNJO Dissertation Data set ITBS Scores AC and Non AC 2003 - 2010.sav
Within-Subjects Factors
Measure:MEASURE_1
teat
Dependent Variable
1
VocPct
2
CompPct
Between-Subjects Factors
N
AC
0
204
1
112
Grade
3
160
5
156
Multivariate Testsb
Effect
Value
F
Hypothesis df
Error df
Sig.
teat
Pillai's Trace
.688
6.891E2
1.000
312.000
.000
Wilks' Lambda
.312
6.891E2
1.000
312.000
.000
Hotelling's Trace
2.209
6.891E2
1.000
312.000
.000
Roy's Largest Root
2.209
6.891E2
1.000
312.000
.000
teat * AC
Pillai's Trace
.023
7.415a
1.000
312.000
.007
Wilks' Lambda
.977
7.415a
1.000
312.000
.007
Hotelling's Trace
.024
7.415a
1.000
312.000
.007
Roy's Largest Root
.024
7.415a
1.000
312.000
.007
teat * Grade
Pillai's Trace
.076
25.735a
1.000
312.000
.000
Wilks' Lambda
.924
25.735a
1.000
312.000
.000
Hotelling's Trace
.082
25.735a
1.000
312.000
.000
Roy's Largest Root
.082
25.735a
1.000
312.000
.000
teat * AC * Grade
Pillai's Trace
.039
12.775a
1.000
312.000
.000
Wilks' Lambda
.961
12.775a
1.000
312.000
.000
Hotelling's Trace
.041
12.775a
1.000
312.000
.000
Roy's Largest Root
.041
12.775a
1.000
312.000
.000
a. Exact statistic
b. Design: Intercept + AC + Grade + AC * Grade
Within Subjects Design: teat
Mauchly's Test of Sphericityb
Measure:MEASURE_1
Within Subjects Effect
Mauchly's W
Approx. Chi-Square
df
Sig.
Epsilona
Greenhouse-Geisser
Huynh-Feldt
Lower-bound
teat
1.000
.000
0
.
1.000
1.000
1.000
Tests the null hypothesis that the error covariance matrix of the orthonormalized transformed dependent variables is proportional to an identity matrix.
a. May be used to adjust the degrees of freedom for the averaged tests of significance. Corrected tests are displayed in the Tests of Within-Subjects Effects table.
b. Design: Intercept + AC + Grade + AC * Grade
Within Subjects Design: teat
Tests of Within-Subjects Effects
Measure:MEASURE_1
Source
Type III Sum of Squares
df
Mean Square
F
Sig.
teat
Sphericity Assumed
8519.800
1
8519.800
689.138
.000
Greenhouse-Geisser
8519.800
1.000
8519.800
689.138
.000
Huynh-Feldt
8519.800
1.000
8519.800
689.138
.000
Lower-bound
8519.800
1.000
8519.800
689.138
.000
teat * AC
Sphericity Assumed
91.672
1
91.672
7.415
.007
Greenhouse-Geisser
91.672
1.000
91.672
7.415
.007
Huynh-Feldt
91.672
1.000
91.672
7.415
.007
Lower-bound
91.672
1.000
91.672
7.415
.007
teat * Grade
Sphericity Assumed
318.156
1
318.156
25.735
.000
Greenhouse-Geisser
318.156
1.000
318.156
25.735
.000
Huynh-Feldt
318.156
1.000
318.156
25.735
.000
Lower-bound
318.156
1.000
318.156
25.735
.000
teat * AC * Grade
Sphericity Assumed
157.941
1
157.941
12.775
.000
Greenhouse-Geisser
157.941
1.000
157.941
12.775
.000
Huynh-Feldt
157.941
1.000
157.941
12.775
.000
Lower-bound
157.941
1.000
157.941
12.775
.000
Error(teat)
Sphericity Assumed
3857.247
312
12.363
Greenhouse-Geisser
3857.247
312.000
12.363
Huynh-Feldt
3857.247
312.000
12.363
Lower-bound
3857.247
312.000
12.363
Tests of Within-Subjects Contrasts
Measure:MEASURE_1
Source
teat
Type III Sum of Squares
df
Mean Square
F
Sig.
teat
Linear
8519.800
1
8519.800
689.138
.000
teat * AC
Linear
91.672
1
91.672
7.415
.007
teat * Grade
Linear
318.156
1
318.156
25.735
.000
teat * AC * Grade
Linear
157.941
1
157.941
12.775
.000
Error(teat)
Linear
3857.247
312
12.363
Tests of Between-Subjects Effects
Measure:MEASURE_1
Transformed Variable:Average
Source
Type III Sum of Squares
df
Mean Square
F
Sig.
Intercept
933159.766
1
933159.766
6269.381
.000
AC
8952.167
1
8952.167
60.145
.000
Grade
6.578
1
6.578
.044
.834
AC * Grade
15.832
1
15.832
.106
.745
Error
46439.327
312
148.844
Estimated Marginal Means
1. AC
Measure:MEASURE_1
AC
Mean
Std. Error
95% Confidence Interval
Lower Bound
Upper Bound
0
44.118
.604
42.929
45.306
1
36.246
.816
34.641
37.851
2. Grade
Measure:MEASURE_1
Grade
Mean
Std. Error
95% Confidence Interval
Lower Bound
Upper Bound
3
40.075
.709
38.680
41.471
5
40.289
.726
38.860
41.717
3. teat
Measure:MEASURE_1
teat
Mean
Std. Error
95% Confidence Interval
Lower Bound
Upper Bound
1
36.343
.564
35.233
37.452
2
44.021
.490
43.057
44.986
4. AC * Grade
Measure:MEASURE_1
AC
Grade
Mean
Std. Error
95% Confidence Interval
Lower Bound
Upper Bound
0
3
44.176
.854
42.496
45.857
5
44.059
.854
42.378
45.740
1
3
35.974
1.133
33.745
38.203
5
36.519
1.174
34.209
38.828
5. AC * teat
Measure:MEASURE_1
AC
teat
Mean
Std. Error
95% Confidence Interval
Lower Bound
Upper Bound
0
1
40.676
.671
39.356
41.997
2
47.559
.583
46.411
48.706
1
1
32.009
.906
30.226
33.791
2
40.484
.788
38.934
42.034
6. Grade * teat
Measure:MEASURE_1
Grade
teat
Mean
Std. Error
95% Confidence Interval
Lower Bound
Upper Bound
3
1
35.494
.788
33.944
37.044
2
44.657
.685
43.309
46.004
5
1
37.191
.806
35.605
38.778
2
43.386
.701
42.007
44.765
7. AC * Grade * teat
Measure:MEASURE_1
AC
Grade
teat
Mean
Std. Error
95% Confidence Interval
Lower Bound
Upper Bound
0
3
1
39.471
.949
37.604
41.337
2
48.882
.825
47.260
50.505
5
1
41.882
.949
40.016
43.749
2
46.235
.825
44.612
47.858
1
3
1
31.517
1.258
29.042
33.993
2
40.431
1.094
38.279
42.583
5
1
32.500
1.304
29.934
35.066
2
40.537
1.134
38.307
42.767
From: Tammy Greer
Sent: Wednesday, September 07, 2011 8:57 PM
To: 'Adebimpe Odunjo'
Subject: RE: The Whole Enchilada!
Correlations
TeachingCondition
TeachAutonomy
WritersWkShopPrep
OverallImplement
SameStandards
AllStudLearn
ReadWkShopPrep
TeachingCondition
Pearson Correlation
1.000
-.092
.644*
.099
-.153
.525
.442
Sig. (2-tailed)
.477
.018
.747
.618
.066
.130
N
62.000
62
13
13
13
13
13
TeachAutonomy
Pearson Correlation
-.092
1.000
.125
.206
.301
.192
.174
Sig. (2-tailed)
.477
.685
.499
.318
.531
.570
N
62
62.000
13
13
13
13
13
WritersWkShopPrep
Pearson Correlation
.644*
.125
1.000
.297
-.133
.753**
.762**
Sig. (2-tailed)
.018
.685
.324
.665
.003
.002
N
13
13
13.000
13
13
13
13
OverallImplement
Pearson Correlation
.099
.206
.297
1.000
.156
.154
.126
Sig. (2-tailed)
.747
.499
.324
.611
.616
.683
N
13
13
13
13.000
13
13
13
SameStandards
Pearson Correlation
-.153
.301
-.133
.156
1.000
.151
.169
Sig. (2-tailed)
.618
.318
.665
.611
.622
.580
N
13
13
13
13
13.000
13
13
AllStudLearn
Pearson Correlation
.525
.192
.753**
.154
.151
1.000
.892**
Sig. (2-tailed)
.066
.531
.003
.616
.622
.000
N
13
13
13
13
13
13.000
13
ReadWkShopPrep
Pearson Correlation
.442
.174
.762**
.126
.169
.892**
1.000
Sig. (2-tailed)
.130
.570
.002
.683
.580
.000
N
13
13
13
13
13
13
13.000
*. Correlation is significant at the 0.05 level (2-tailed).
**. Correlation is significant at the 0.01 level (2-tailed).
There is data missing form what you are asking.
To find the standard deviation (SD) from the given output, we need to look at the Estimated Marginal Means section.
For the main effect of Verbal, we have the following information:
- Mean for AC schools: 36.25
- Mean for non AC schools: 44.12
To find the standard deviation for each group, we need additional information which is not provided in the given output. The standard deviation cannot be calculated without the raw data.
If you have access to the raw data, you can calculate