Date: Tue, 9 Aug 2005 09:28:04 +0200
Reply-To: Marta García-Granero
<biostatistics@terra.es>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Marta García-Granero
<biostatistics@terra.es>
Organization: Asesoría Bioestadística
Subject: Re: SPSS: Factorial design enquiry
In-Reply-To: <200508090629.j796TYRW010747@listserv.cc.uga.edu>
Content-Type: text/plain; charset=ISO-8859-15
Hi David,
Using your data layout with simulated data, I got this dataset:
DATA LIST FREE/ subject repet wordproc task depvar.
BEGIN DATA
1 1 1 1 2 1 2 2 2 8 1 3 3 3 12 1 4 4 4 5
2 1 2 1 3 2 2 3 2 13 2 3 4 3 6 2 4 1 4 8
3 1 3 1 1 3 2 4 2 2 3 3 1 3 2 3 4 2 4 0
4 1 4 1 12 4 2 1 2 3 4 3 2 3 14 4 4 3 4 18
5 1 1 2 11 5 2 2 3 5 5 3 3 4 14 5 4 4 1 1
6 1 2 2 2 6 2 3 3 14 6 3 4 4 4 6 4 1 1 4
7 1 3 2 12 7 2 4 3 19 7 3 1 4 4 7 4 2 1 6
8 1 4 2 1 8 2 1 3 14 8 3 2 4 2 8 4 3 1 1
9 1 1 3 3 9 2 2 4 1 9 3 3 1 13 9 4 4 2 13
10 1 2 3 17 10 2 3 4 7 10 3 4 1 9 10 4 1 2 14
11 1 3 3 4 11 2 4 4 15 11 3 1 1 1 11 4 2 2 10
12 1 4 3 13 12 2 1 4 18 12 3 2 1 6 12 4 3 2 10
13 1 1 4 15 13 2 2 1 2 13 3 3 2 11 13 4 4 3 19
14 1 2 4 6 14 2 3 1 10 14 3 4 2 10 14 4 1 3 5
15 1 3 4 6 15 2 4 1 18 15 3 1 2 8 15 4 2 3 1
16 1 4 4 6 16 2 1 1 12 16 3 2 2 12 16 4 3 3 15
END DATA.
VAR LABEL wordproc 1'A' 2'B' 3'C' 4'D'.
VAR LABEL task 1'Task 1' 2'Task 2' 3'Task 3' 4'Task 4'.
* The following statistical analysis takes care of all the potential
sources of heterogeneity and all the interesting factors *.
UNIANOVA
depvar BY wordproc task subject repet
/RANDOM = subject repet
/METHOD = SSTYPE(3)
/INTERCEPT = EXCLUDE
/SAVE = RESID
/EMMEANS = TABLES(wordproc) COMPARE ADJ(BONFERRONI)
/EMMEANS = TABLES(task) COMPARE ADJ(BONFERRONI)
/PLOT = RESIDUALS
/CRITERIA = ALPHA(.05)
/DESIGN = wordproc task task*wordproc subject repet .
You could also try SPSS procedure MIXED.
HTH
Marta
D> I'm interested to conduct an experiment study. The first goal is to
D> investigate the effect of four different word processors (independent
D> variable) on the time completion (dependent variable). The second goal is
D> to investigate the effect of task difficulties (independent variable) on
D> the time completion (dependent variable).
D> Sixteen subjects are required to use four different word processors (A, B,
D> C and D). To avoid learning effect, the subjects are given four different
D> tasks (1,2,3 and 4). A randomized block design is created as follow.
D> ---------------------------------------------
D> | | Task 1 | Task 2 | Task 3 | Task 4 |
D> ---------------------------------------------
D> | S1 | A | B | C | D |
D> ---------------------------------------------
D> | S2 | B | C | D | A |
D> ---------------------------------------------
D> | S3 | C | D | A | B |
D> ---------------------------------------------
D> | S4 | D | A | B | C |
D> ---------------------------------------------
D> ---------------------------------------------
D> | | Task 2 | Task 3 | Task 4 | Task 1 |
D> ---------------------------------------------
D> | S5 | A | B | C | D |
D> ---------------------------------------------
D> | S6 | B | C | D | A |
D> ---------------------------------------------
D> | S7 | C | D | A | B |
D> ---------------------------------------------
D> | S8 | D | A | B | C |
D> ---------------------------------------------
D> ---------------------------------------------
D> | | Task 3 | Task 4 | Task 1 | Task 2 |
D> ---------------------------------------------
D> | S9 | A | B | C | D |
D> ---------------------------------------------
D> | S10 | B | C | D | A |
D> ---------------------------------------------
D> | S11 | C | D | A | B |
D> ---------------------------------------------
D> | S12 | D | A | B | C |
D> ---------------------------------------------
D> ---------------------------------------------
D> | | Task 4 | Task 1 | Task 2 | Task 3 |
D> ---------------------------------------------
D> | S13 | A | B | C | D |
D> ---------------------------------------------
D> | S14 | B | C | D | A |
D> ---------------------------------------------
D> | S15 | C | D | A | B |
D> ---------------------------------------------
D> | S16 | D | A | B | C |
D> ---------------------------------------------
D> 1. Can SPSS analyze the above design even though there are many empty
D> cells?
D> 2. Or is there any other softwares that can analyze the factorial design?
