Setting up data sheet

[Rose, Fred]

I’m having a mental block this morning and can’t figure out how to set up a data sheet for the following study:

In a 2 x 2 repeated measures design, students examined the effect  of glasses (yes/no) and gender (m/f) on perceived intelligence (rated on a 7-point Likert-type scale).  Each participant viewed 8 pictures:  4 Men and 4 Women, half of each gender had glasses and half did not.  Glasses and gender were counterbalanced, such that half of the participants saw, for example, person A with glasses and Person B without, whereas the other half saw person A without glasses and person B with.  

In truth, the questionnaire had 5 dimensions being rated (friendliness, intelligence, shyness, assertiveness, and helpfulness) but they can get by with just analyzing intelligence.

I know this is an incredibly elemental setup, but I’m drawing a blank this morning on how to handle the repeated measures nature of this study when entering data.  Help???

Thanks,

Fred


--
Fredric E. Rose, Ph.D.
Associate Professor of Psychology
Palomar College
760-744-1150 x2344
frose@...
====================To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

[Melissa Ives]

Seems like you would need something like this...where gender/glasses are preassigned by picture group, and the raters provide the values for each person.

Rater	Picture group	Person	Gender	Glasses	Intelligence	Friendly	Shy	Assertive	Helpful
1	I	A	M	1
1	I	B	M	0
1	I	C	M	1
1	I	D	M	0
1	I	E	F	1
1	I	F	F	0
1	I	G	F	1
1	I	H	F	0
2	II	A	M	0
2	II	B	M	1
2	II	C	M	0
2	II	D	M	1
2	II	E	F	0
2	II	F	F	1
2	II	G	F	0
2	II	H	F	1

---

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Rose, Fred
Sent: Thursday, April 15, 2010 1:37 PM
To: [hidden email]
Subject: [SPSSX-L] Setting up data sheet

I’m having a mental block this morning and can’t figure out how to set up a data sheet for the following study:

In a 2 x 2 repeated measures design, students examined the effect  of glasses (yes/no) and gender (m/f) on perceived intelligence (rated on a 7-point Likert-type scale).  Each participant viewed 8 pictures:  4 Men and 4 Women, half of each gender had glasses and half did not.  Glasses and gender were counterbalanced, such that half of the participants saw, for example, person A with glasses and Person B without, whereas the other half saw person A without glasses and person B with.  

In truth, the questionnaire had 5 dimensions being rated (friendliness, intelligence, shyness, assertiveness, and helpfulness) but they can get by with just analyzing intelligence.

I know this is an incredibly elemental setup, but I’m drawing a blank this morning on how to handle the repeated measures nature of this study when entering data.  Help???

Thanks,

Fred


--
Fredric E. Rose, Ph.D.
Associate Professor of Psychology
Palomar College
760-744-1150 x2344
frose@...
======= To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

---

PRIVILEGED AND CONFIDENTIAL INFORMATION
This transmittal and any attachments may contain PRIVILEGED AND
CONFIDENTIAL information and is intended only for the use of the
addressee. If you are not the designated recipient, or an employee
or agent authorized to deliver such transmittals to the designated
recipient, you are hereby notified that any dissemination,
copying or publication of this transmittal is strictly prohibited. If
you have received this transmittal in error, please notify us
immediately by replying to the sender and delete this copy from your
system. You may also call us at [phone] for assistance.

[Rose, Fred]

Yeah, that is what I had in mind but I was concerned about having multiple rows for each participant – seems like that’s a no-no because of the intercorrelations and artificially elevated n.  Or am I not getting it?

Fred


On 4/15/10 12:14 PM, "Melissa Ives" <mives@...> wrote:

Seems like you would need something like this...where gender/glasses are preassigned by picture group, and the raters provide the values for each person.
Rater Picture group Person Gender Glasses Intelligence Friendly Shy Assertive Helpful
1 I A M 1
1 I B M 0
1 I C M 1
1 I D M 0
1 I E F 1
1 I F F 0
1 I G F 1
1 I H F 0
2 II A M 0
2 II B M 1
2 II C M 0
2 II D M 1
2 II E F 0
2 II F F 1
2 II G F 0
2 II H F 1

---

From: SPSSX(r) Discussion [[hidden email]] On Behalf Of Rose, Fred
Sent: Thursday, April 15, 2010 1:37 PM
To: SPSSX-L@...
Subject: [SPSSX-L] Setting up data sheet

I’m having a mental block this morning and can’t figure out how to set up a data sheet for the following study:

In a 2 x 2 repeated measures design, students examined the effect  of glasses (yes/no) and gender (m/f) on perceived intelligence (rated on a 7-point Likert-type scale).  Each participant viewed 8 pictures:  4 Men and 4 Women, half of each gender had glasses and half did not.  Glasses and gender were counterbalanced, such that half of the participants saw, for example, person A with glasses and Person B without, whereas the other half saw person A without glasses and person B with.  

In truth, the questionnaire had 5 dimensions being rated (friendliness, intelligence, shyness, assertiveness, and helpfulness) but they can get by with just analyzing intelligence.

I know this is an incredibly elemental setup, but I’m drawing a blank this morning on how to handle the repeated measures nature of this study when entering data.  Help???

Thanks,

Fred

--
Fredric E. Rose, Ph.D.
Associate Professor of Psychology
Palomar College
760-744-1150 x2344
frose@...
====================To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

[Bruce Weaver]

Whether multiple rows per person is a problem or not depends on what procedure you use to analyze the data.  If you intend to use GLM Repeated Measures, you will indeed have to reduce things to one row per person (with multiple columns for any repeated measures).  But if you use MIXED, it needs to have one row per observation of the DV, as Melissa set it up.

Rose, Fred wrote

Re: Setting up data sheet


Yeah, that is what I had in mind but I was concerned about having multiple rows for each participant – seems like that’s a no-no because of the intercorrelations and artificially elevated n.  Or am I not getting it?

Fred


On 4/15/10 12:14 PM, "Melissa Ives" < [e-mail] > wrote:

Seems like you would need something like this...where gender/glasses are preassigned by picture group, and the raters provide the values for each person.
Rater Picture group Person Gender Glasses Intelligence Friendly Shy Assertive Helpful
1 I A M 1
1 I B M 0
1 I C M 1
1 I D M 0
1 I E F 1
1 I F F 0
1 I G F 1
1 I H F 0
2 II A M 0
2 II B M 1
2 II C M 0
2 II D M 1
2 II E F 0
2 II F F 1
2 II G F 0
2 II H F 1

From: SPSSX(r) Discussion [ mailto:[e-mail] ] On Behalf Of Rose, Fred
Sent: Thursday, April 15, 2010 1:37 PM
To: [e-mail]
Subject: [SPSSX-L] Setting up data sheet

I’m having a mental block this morning and can’t figure out how to set up a data sheet for the following study:

In a 2 x 2 repeated measures design, students examined the effect  of glasses (yes/no) and gender (m/f) on perceived intelligence (rated on a 7-point Likert-type scale).  Each participant viewed 8 pictures:  4 Men and 4 Women, half of each gender had glasses and half did not.  Glasses and gender were counterbalanced, such that half of the participants saw, for example, person A with glasses and Person B without, whereas the other half saw person A without glasses and person B with.  

In truth, the questionnaire had 5 dimensions being rated (friendliness, intelligence, shyness, assertiveness, and helpfulness) but they can get by with just analyzing intelligence.

I know this is an incredibly elemental setup, but I’m drawing a blank this morning on how to handle the repeated measures nature of this study when entering data.  Help???

Thanks,

Fred


--
Fredric E. Rose, Ph.D.
Associate Professor of Psychology
Palomar College
760-744-1150 x2344
[e-mail]




====================To manage your subscription to SPSSX-L, send a message to
[e-mail] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Mike]

Setting up data sheetThe design you are describing below is much more complicated unless you
collapse or summarize across the levels of variables. It seems to me that a
subject/participant was exposed to a series of pictures like the following

Picture_1: Male 1 with glasses
Picture_2: Male 2 with glasses
Picture_3: Male 3 without glasses
Picture_4: Male 4 without glasses
Picture_5: Female 1 with glasses
Picture_6: Female 2 with glasses
Picture_7: Female 3 without glasses
Picture_8: Female 4 without glasses

But if you view this as a 2x2 design, you want 4 variables for each measure
you're using.  Assuming you're just interested in rated intelligence:

Male with glasses (MwithG)
Male without glasses (MwoG)
female with glasses (FwithG)
female without glasses (FwoG)

which would give you a case layout with the following variables:

SubID MwithG MwoG FwithG FwoG.

The question really is how do you get the above 4 variables?
Assume that above "Picture_#" is the name of the measure made
on a subject.  The compute new variables:

compute MwithG=(Picture_1 + Picture_2)/2.
compute MwoG=(Picture_3 + Picture_4)/2.
compute FwithG=(Picture_5 + Picture_6)/2.
compute FwoG=(Picture_7 + Picture_8)/2.

You would then use GLM with the following syntax:

GLM MwithG MwoG FwithG FwoG/
 wsfactors=Gender(2),Glasses(2)/
 measure=rate_Intell/
 METHOD = SSTYPE(3)/
 CRITERIA = ALPHA(.05)/
 print=descriptive/
 WSDESIGN = gender, glasses, gender*glasses.

All this would have to be done for each rated characteristic.

I'm open to correction if I am misunderstanding your design and/or
intent to analyze.

-Mike Palij
New York University
[hidden email]

----- Original Message -----
From: Rose, Fred
To: [hidden email]
Sent: Thursday, April 15, 2010 2:37 PM
Subject: Setting up data sheet


I'm having a mental block this morning and can't figure out how to set up a data sheet for the following study:

In a 2 x 2 repeated measures design, students examined the effect  of glasses (yes/no) and gender (m/f) on perceived intelligence (rated on a 7-point Likert-type scale).  Each participant viewed 8 pictures:  4 Men and 4 Women, half of each gender had glasses and half did not.  Glasses and gender were counterbalanced, such that half of the participants saw, for example, person A with glasses and Person B without, whereas the other half saw person A without glasses and person B with.

In truth, the questionnaire had 5 dimensions being rated (friendliness, intelligence, shyness, assertiveness, and helpfulness) but they can get by with just analyzing intelligence.

I know this is an incredibly elemental setup, but I'm drawing a blank this morning on how to handle the repeated measures nature of this study when entering data.  Help???

Thanks,

Fred


--
Fredric E. Rose, Ph.D.
Associate Professor of Psychology
Palomar College
760-744-1150 x2344
[hidden email]
======= To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD