Filter
Top Products
472
Example 31
To obtain a standard error for the combined parameter estimate, go through the
following steps:
E Compute the average within-imputation variance.
E Compute the between-imputation variance.
E Compute the total variance.
The multiple-group standard error is then
A test of the null hypothesis that the regression weight is 0 in the population can be
based on the statistic
which, if the regression weight is 0, has a t distribution with degrees of freedom given
by
A calculator that implements these formulas and also provides multiple-imputation
confidence intervals can be downloaded from
http://www.amosdevelopment.com/bayes/calculator.
Joseph Schafer’s NORM program also performs these calculations. NORM can be
downloaded from http://www.stat.psu.edu/~jls/misoftwa.html#win.
U
1
m
----
U
t()
t 1=
m
∑
0.0233==
B
1
m 1–
-------------
Q
ˆ
t()
Q–()
t 1=
m
∑
=
2
0.0085=
TU= 1
1
m
----+
⎝⎠
⎛⎞
B+ 0.0233= 1
1
10
------+
⎝⎠
⎛⎞
0.0085+ 0.0326=
T 0.0326 0.1807==
Q
T
-------
1.172
0.1807
---------------- 6.49==
vm1–()= 1
U
1
1
m
----+
⎝⎠
⎛⎞
B
-----------------------+
2
10 1–()= 1
0.0233
1
1
10
------+
⎝⎠
⎛⎞
0.0085
-------------------------------------+
2
109=