Your CIOS file request: Q-METHOD/06089130.903 hotline item

-
Received:  by CIOS Mailer; Monday 8 Jun 2009 13:09:03
Date:         Mon, 8 Jun 2009 18:03:36 +0100
From:         Sam Hopper 
Subject: Re: Analysis?
To:           Q-METHOD@LISTSERV.KENT.EDU
List-Help: ,              
List-Unsubscribe: 
List-Subscribe: 
List-Owner: 
List-Archive: 

--_bdf1e7bd-cf67-41f7-b120-1d9f07813a2f_
Content-Type: text/plain; charset="Windows-1252"
Content-Transfer-Encoding: quoted-printable


Hi All

Just to update you all... as steven suggested I re-ran my analysis this mor=
ning=2C and the numbers are now adding up! With a very strong factor 1=2C a=
s he suspected! Im now glad that I spotted the mistake before the examiners=
!

=20

Thank you everyone for your help!

Sam




=20



=20

> Date: Mon=2C 8 Jun 2009 09:43:59 -0700
> From: daniel.ozer  at UCR.EDU
> Subject: Re: Analysis?
> To: Q-METHOD@LISTSERV.KENT.EDU
>=20
> Regardless of how many are rotated=2C the=20
> cumulative proportion of variance accounted for=20
> by the first k rotated components will never be=20
> greater than the proportion of variance explained=20
> by the first k unrotated components. That's what=20
> makes the components "principal".
>=20
> At 12:06 AM 6/8/2009=2C you wrote:
>=20
> >There seems to be something definitely amiss=20
> >about this situation. It is impossible=2C as=20
> >Peter Schmolck notes=2C to rotate the first four=20
> >unrotated factors and end up explaining more=20
> >variance (or even explaining less variance). If=20
> >only the first four unrotated factors are=20
> >admitted into the varimax phase=2C then the=20
> >rotated factors should explain exactly 72.55% of=20
> >the variance=2C just as the unrotated factors=20
> >did. However=2C I do agree with Bob Braswell that=20
> >if (say) all eight principal components were=20
> >allowed into the varimax rotation=2C that it would=20
> >then be possible that four of those rotated=20
> >factors could account for more variability than=20
> >the first four unrotated factors by virtue of=20
> >gaining some of the variance from those factors=20
> >not retained in the final four. But Sam Hopper=20
> >claims to have kept only four factors for the=20
> >varimax phase. This doesn=92t add up and I would=20
> >be inclined to re-run the analysis.
> >
> >Even without this problem=2C however=2C Sam Hopper=92s=20
> >rotated solution looks problematic. Factors 3=20
> >and 4=2C for example=2C are only defined by a single=20
> >Q sort and should therefore probably not be=20
> >retained unless there is something special about=20
> >those two individuals. (The two sets of factor=20
> >scores for these two factors will be nothing=20
> >more than the Q sorts for those two=20
> >persons.) Moreover=2C the defining Q sort for=20
> >factor 4 carries a negative loading=2C so that=20
> >factor should probably be reflected. In=20
> >addition=2C it very much looks like factors 1 and=20
> >2 are highly correlated with one another. This=20
> >may be one of those rare cases in which the=20
> >unrotated solution might be the best final=20
> >solution. It might be helpful if Sam Hopper=20
> >could provide us with more information about the=20
> >nature of the study and perhaps the Q sample=20
> >that is being used. This might provide a key=20
> >that would help explain these unusual results.
> >
> >As to Sam Hopper=92s desire =93to look at subgroups=20
> >within my data=2C=94 this is generally not a good=20
> >idea. For one thing=2C males-females=2C=20
> >Republicans-Democrats=2C and like divisions are=20
> >mere categories which are supplanted by the=20
> >operant categories represented by the Q=20
> >factors. Conventional categories are not=20
> >accurate guides as to the way nature actually=20
> >operates and ought to be replaced by more=20
> >precise designations (such as Q factors) when=20
> >these reveal themselves. Conventional=20
> >categories are only useful in designing P sets=2C=20
> >and to return to categories once the Q factors=20
> >have been revealed is to place the lever in the=20
> >wrong location. Moreover=2C given that P samples=20
> >are neither large nor randomly selected means=20
> >that the categories that comprise them are ill=20
> >suited for inferential purposes. That said=2C it=20
> >is always possible to keep the Q factors intact=20
> >and then compare subcategories of persons using=20
> >t=2C F=2C or other tests of this kind. For=20
> >instance=2C a t-test could be used to determine=20
> >whether the average factor-1 loadings for males=20
> >is significantly greater than the average=20
> >factor-1 loadings for females. Or quantitative=20
> >variables (such as IQ) could be correlated with=20
> >the loadings for the various factors. Such test=20
> >results would still be on shaky ground given the=20
> >small and probably unrepresentative character of=20
> >the person sample. In Q studies=2C it is best=20
> >(and certainly safest) to focus on the factor=20
> >arrays=ADwhich is where the subjectivity is=ADand to=20
> >play down the matrix of factor loadings and the=20
> >objective demographic characteristics of the=20
> >respondents that are associated with the=20
> >loadings. To focus on the latter is to move=20
> >back toward R methodology and all its logic=2C=20
> >which Q methodology is ill suited to do.
> >___________________________________________
> >* _____ ______ ____ __ __ ____ ___ _ * Steven R. Brown
> >| | ___||_ _|| _ || | || _ || | | | Political Science
> >| |___ | | | | _| | | || _| | | | Kent State University
> >| |_____| |__| |____| \___/ |____||_|___|=20
> >| (sbrown@kent.edu)
> >*___________________________________________*_________________________
> >Economists have forecasted nine out of the past five recessions.
> >
> >
> >
> >
> >On 6/5/09 9:37 AM=2C "Sam Hopper"=20
> ><hopper_sam@HOTMAIL.COM> wrote:
> >
> >Dear all
> >I just have a couple of questions regarding my results and I wondered if
> >
> >anyone could help. The first is regarding eigenvalue's/% of variance
> >explained - the prerotation values are:
> >Factor Eigenvalue As Percentage Cumulative percentage
> >1 20.78 61.12 61.12
> >2 1.74 5.13 66.26
> >3 1.13 3.34 69.60
> >4 1.00 2.95 72.55
> >
> >ect...
> >
> >but the post rotation ones are higher (see below)=2C why is this=2C I'm =
going
> >
> >to have to explain it in a viva potentially.
> >
> > QSORT 1 2 3 4
> >
> > 1 1 0.4356 0.6995X 0.1473 -0.1207
> > 2 2 0.6738X 0.4643 -0.0180 0.1879
> > 3 3 0.7053X 0.5243 0.0358 0.0964
> > 4 4 0.5475 0.6437X -0.1134 -0.1321
> > 5 5 0.1918 0.6030X 0.3802 -0.0802
> > 6 6 0.5815 0.6357X 0.0655 0.0106
> > 7 7 0.8032X 0.3382 0.0457 0.2553
> > 8 8 0.5793X 0.5234 -0.0133 0.0006
> > 9 9 0.7499X 0.3172 -0.0290 0.3484
> > 10 10 0.6242X 0.5898 0.0382 0.0342
> > 11 11 0.6167X 0.4980 0.1298 -0.0137
> > 12 12 0.7740X 0.3658 0.0986 0.2421
> > 13 13 0.3465 0.4923X -0.0391 0.2337
> > 14 14 0.6139X 0.5119 -0.0139 0.0914
> > 15 15 0.5519 0.6386X 0.2492 -0.1189
> > 16 16 0.7346X 0.4022 0.1266 0.2470
> > 17 17 0.8324X 0.2080 0.1408 0.4370
> > 18 18 0.8249X 0.3016 0.1740 0.3439
> > 19 19 0.7487X 0.4959 0.1330 0.0894
> > 20 2800 0.6644X 0.4046 0.1106 0.2713
> > 21 2809 0.0840 0.2934X 0.9208X 0.0424
> > 22 2830 0.8255X 0.2794 0.0717 0.3035
> > 23 2876 0.7728X 0.4232 0.1197 0.1627
> > 24 2878 0.6264X 0.4768 0.1398 0.0909
> > 25 2880 0.2799 0.7442X 0.2099 -0.1633
> > 26 2884 0.6981X 0.5118 0.0937 0.0570
> > 27 29 21 0.3420 0.7810X 0.1600 -0.2195
> > 28 30 74 0.6144X 0.6092 0.0311 0.0211
> > 29 3120 0.7232X 0.4899 0.0517 0.0845
> > 30 3357 0.6375X 0.5772 0.1268 -0.0659
> > 31 3371 0.6214X 0.4536 0.2503 -0.0161
> > 32 3380 -0.5689X 0.4873 0.0069 -0.8105X
> > 33 3382 0.7587X 0.3588 -0.0038 0.2617
> > 34 3383 0.6317X 0.4697 0.2232 0.2220
> >
> > % expl.Var. 41 26 4 5
> >
> >
> >
> >Secondly=2C I would like to look at subgroups within my data=2C but dont=
 want
> >
> >to delete sorts from the file to do this. Is there a way of "ignoring"
> >
> >certain participants sorts or making a new file (with copied data) so I =
c
> >an
> >delete the unwanted sorts?
> >
> >Thank you very much for any help!
> >Sam
>=20
>=20
> Daniel Ozer
> Department of Psychology
> University of California=2C Riverside
> Riverside CA 92521
>=20
> http://www.psych.ucr.edu/faculty/ozer/index.html
>=20
> Voice: (951) 827-5211
> Fax: (951) 827-3985
> e-mail: daniel.ozer@ucr.edu

_________________________________________________________________
With Windows Live=2C you can organise=2C edit=2C and share your photos.
http://clk.atdmt.com/UKM/go/134665338/direct/01/=

--_bdf1e7bd-cf67-41f7-b120-1d9f07813a2f_
Content-Type: text/html; charset="Windows-1252"
Content-Transfer-Encoding: quoted-printable






Hi All

Just to update you all... as steven suggested I re-ran my analysis this mor=
ning=2C and the numbers are now adding up! With a very strong factor 1=2C a=
s he suspected! Im now glad that I spotted the mistake before the examiners=
!

 =3B

Thank you everyone for your help!

Sam




 =3B



 =3B

>=3B Date: Mon=2C 8 Jun 2009 09:43:59 -0700
>=3B From: daniel.oz=  at 
er@UCR.EDU
>=3B Subject: Re: Analysis?
>=3B To: Q-METHOD@LISTSERV=
.KENT.EDU
>=3B 
>=3B Regardless of how many are rotated=2C the >=3B cumulative proportion of variance accounted for 
>=3B by the =
first k rotated components will never be 
>=3B greater than the propor=
tion of variance explained 
>=3B by the first k unrotated components. =
That's what 
>=3B makes the components "principal".
>=3B 
>=
=3B At 12:06 AM 6/8/2009=2C you wrote:
>=3B 
>=3B >=3BThere see=
ms to be something definitely amiss 
>=3B >=3Babout this situation. =
It is impossible=2C as 
>=3B >=3BPeter Schmolck notes=2C to rotate t=
he first four 
>=3B >=3Bunrotated factors and end up explaining more=
 
>=3B >=3Bvariance (or even explaining less variance). If 
>=
=3B >=3Bonly the first four unrotated factors are 
>=3B >=3Badmitt=
ed into the varimax phase=2C then the 
>=3B >=3Brotated factors shou=
ld explain exactly 72.55% of 
>=3B >=3Bthe variance=2C just as the u=
nrotated factors 
>=3B >=3Bdid. However=2C I do agree with Bob Brasw=
ell that 
>=3B >=3Bif (say) all eight principal components were 
=
>=3B >=3Ballowed into the varimax rotation=2C that it would 
>=3B =
>=3Bthen be possible that four of those rotated 
>=3B >=3Bfactors =
could account for more variability than 
>=3B >=3Bthe first four unr=
otated factors by virtue of 
>=3B >=3Bgaining some of the variance f=
rom those factors 
>=3B >=3Bnot retained in the final four. But Sam =
Hopper 
>=3B >=3Bclaims to have kept only four factors for the 
&=
gt=3B >=3Bvarimax phase. This doesn=92t add up and I would 
>=3B >=
=3Bbe inclined to re-run the analysis.
>=3B >=3B
>=3B >=3BEve=
n without this problem=2C however=2C Sam Hopper=92s 
>=3B >=3Brotate=
d solution looks problematic. Factors 3 
>=3B >=3Band 4=2C for examp=
le=2C are only defined by a single 
>=3B >=3BQ sort and should there=
fore probably not be 
>=3B >=3Bretained unless there is something sp=
ecial about 
>=3B >=3Bthose two individuals. (The two sets of factor=
 
>=3B >=3Bscores for these two factors will be nothing 
>=3B &=
gt=3Bmore than the Q sorts for those two 
>=3B >=3Bpersons.) Moreove=
r=2C the defining Q sort for 
>=3B >=3Bfactor 4 carries a negative l=
oading=2C so that 
>=3B >=3Bfactor should probably be reflected. In =

>=3B >=3Baddition=2C it very much looks like factors 1 and 
>=
=3B >=3B2 are highly correlated with one another. This 
>=3B >=3Bm=
ay be one of those rare cases in which the 
>=3B >=3Bunrotated solut=
ion might be the best final 
>=3B >=3Bsolution. It might be helpful =
if Sam Hopper 
>=3B >=3Bcould provide us with more information about=
 the 
>=3B >=3Bnature of the study and perhaps the Q sample 
>=
=3B >=3Bthat is being used. This might provide a key 
>=3B >=3Btha=
t would help explain these unusual results.
>=3B >=3B
>=3B >=
=3BAs to Sam Hopper=92s desire =93to look at subgroups 
>=3B >=3Bwit=
hin my data=2C=94 this is generally not a good 
>=3B >=3Bidea. For o=
ne thing=2C males-females=2C 
>=3B >=3BRepublicans-Democrats=2C and =
like divisions are 
>=3B >=3Bmere categories which are supplanted by=
 the 
>=3B >=3Boperant categories represented by the Q 
>=3B &g=
t=3Bfactors. Conventional categories are not 
>=3B >=3Baccurate guid=
es as to the way nature actually 
>=3B >=3Boperates and ought to be =
replaced by more 
>=3B >=3Bprecise designations (such as Q factors) =
when 
>=3B >=3Bthese reveal themselves. Conventional 
>=3B >=
=3Bcategories are only useful in designing P sets=2C 
>=3B >=3Band t=
o return to categories once the Q factors 
>=3B >=3Bhave been reveal=
ed is to place the lever in the 
>=3B >=3Bwrong location. Moreover=
=2C given that P samples 
>=3B >=3Bare neither large nor randomly se=
lected means 
>=3B >=3Bthat the categories that comprise them are il=
l 
>=3B >=3Bsuited for inferential purposes. That said=2C it 
>=
=3B >=3Bis always possible to keep the Q factors intact 
>=3B >=3B=
and then compare subcategories of persons using 
>=3B >=3Bt=2C F=2C =
or other tests of this kind. For 
>=3B >=3Binstance=2C a t-test coul=
d be used to determine 
>=3B >=3Bwhether the average factor-1 loadin=
gs for males 
>=3B >=3Bis significantly greater than the average >=3B >=3Bfactor-1 loadings for females. Or quantitative 
>=3B >=
=3Bvariables (such as IQ) could be correlated with 
>=3B >=3Bthe loa=
dings for the various factors. Such test 
>=3B >=3Bresults would sti=
ll be on shaky ground given the 
>=3B >=3Bsmall and probably unrepre=
sentative character of 
>=3B >=3Bthe person sample. In Q studies=2C =
it is best 
>=3B >=3B(and certainly safest) to focus on the factor <=
BR>>=3B >=3Barrays­=3Bwhich is where the subjectivity is­=3Band t=
o 
>=3B >=3Bplay down the matrix of factor loadings and the 
>=
=3B >=3Bobjective demographic characteristics of the 
>=3B >=3Bres=
pondents that are associated with the 
>=3B >=3Bloadings. To focus o=
n the latter is to move 
>=3B >=3Bback toward R methodology and all =
its logic=2C 
>=3B >=3Bwhich Q methodology is ill suited to do.
&=
gt=3B >=3B___________________________________________
>=3B >=3B* _=
____ ______ ____ __ __ ____ ___ _ * Steven R. Brown
>=3B >=3B| | ___=
||_ _|| _ || | || _ || | | | Political Science
>=3B >=3B| |___ | | |=
 | _| | | || _| | | | Kent State University
>=3B >=3B| |_____| |__| =
|____| \___/ |____||_|___| 
>=3B >=3B| (<=3Bsbrown@kent.htm>=3Bs=
brown@kent.edu)
>=3B >=3B*__________________________________________=
_*_________________________
>=3B >=3BEconomists have forecasted nine=
 out of the past five recessions.
>=3B >=3B
>=3B >=3B
>=
=3B >=3B
>=3B >=3B
>=3B >=3BOn 6/5/09 9:37 AM=2C "Sam Hoppe=
r" 
>=3B >=3B<=3B<=3Bhopper_sam@HOTMAIL.htm>=3Bhopper_sam@HOTM=
AIL.COM>=3B wrote:
>=3B >=3B
>=3B >=3BDear all
>=3B &g=
t=3BI just have a couple of questions regarding my results and I wondered i=
f
>=3B >=3B
>=3B >=3Banyone could help. The first is regardin=
g eigenvalue's/% of variance
>=3B >=3Bexplained - the prerotation va=
lues are:
>=3B >=3BFactor Eigenvalue As Percentage Cumulative percen=
tage
>=3B >=3B1 20.78 61.12 61.12
>=3B >=3B2 1.74 5.13 66.26<=
BR>>=3B >=3B3 1.13 3.34 69.60
>=3B >=3B4 1.00 2.95 72.55
>=
=3B >=3B
>=3B >=3Bect...
>=3B >=3B
>=3B >=3Bbut the =
post rotation ones are higher (see below)=2C why is this=2C I'm going
&g=
t=3B >=3B
>=3B >=3Bto have to explain it in a viva potentially.>=3B >=3B
>=3B >=3B QSORT 1 2 3 4
>=3B >=3B
>=3B &g=
t=3B 1 1 0.4356 0.6995X 0.1473 -0.1207
>=3B >=3B 2 2 0.6738X 0.4643 =
-0.0180 0.1879
>=3B >=3B 3 3 0.7053X 0.5243 0.0358 0.0964
>=3B =
>=3B 4 4 0.5475 0.6437X -0.1134 -0.1321
>=3B >=3B 5 5 0.1918 0.603=
0X 0.3802 -0.0802
>=3B >=3B 6 6 0.5815 0.6357X 0.0655 0.0106
>=
=3B >=3B 7 7 0.8032X 0.3382 0.0457 0.2553
>=3B >=3B 8 8 0.5793X 0.=
5234 -0.0133 0.0006
>=3B >=3B 9 9 0.7499X 0.3172 -0.0290 0.3484
&=
gt=3B >=3B 10 10 0.6242X 0.5898 0.0382 0.0342
>=3B >=3B 11 11 0.61=
67X 0.4980 0.1298 -0.0137
>=3B >=3B 12 12 0.7740X 0.3658 0.0986 0.24=
21
>=3B >=3B 13 13 0.3465 0.4923X -0.0391 0.2337
>=3B >=3B 14=
 14 0.6139X 0.5119 -0.0139 0.0914
>=3B >=3B 15 15 0.5519 0.6386X 0.2=
492 -0.1189
>=3B >=3B 16 16 0.7346X 0.4022 0.1266 0.2470
>=3B &=
gt=3B 17 17 0.8324X 0.2080 0.1408 0.4370
>=3B >=3B 18 18 0.8249X 0.3=
016 0.1740 0.3439
>=3B >=3B 19 19 0.7487X 0.4959 0.1330 0.0894
&g=
t=3B >=3B 20 2800 0.6644X 0.4046 0.1106 0.2713
>=3B >=3B 21 2809 0=
.0840 0.2934X 0.9208X 0.0424
>=3B >=3B 22 2830 0.8255X 0.2794 0.0717=
 0.3035
>=3B >=3B 23 2876 0.7728X 0.4232 0.1197 0.1627
>=3B >=
=3B 24 2878 0.6264X 0.4768 0.1398 0.0909
>=3B >=3B 25 2880 0.2799 0.=
7442X 0.2099 -0.1633
>=3B >=3B 26 2884 0.6981X 0.5118 0.0937 0.0570<=
BR>>=3B >=3B 27 29 21 0.3420 0.7810X 0.1600 -0.2195
>=3B >=3B 28=
 30 74 0.6144X 0.6092 0.0311 0.0211
>=3B >=3B 29 3120 0.7232X 0.4899=
 0.0517 0.0845
>=3B >=3B 30 3357 0.6375X 0.5772 0.1268 -0.0659
&g=
t=3B >=3B 31 3371 0.6214X 0.4536 0.2503 -0.0161
>=3B >=3B 32 3380 =
-0.5689X 0.4873 0.0069 -0.8105X
>=3B >=3B 33 3382 0.7587X 0.3588 -0.=
0038 0.2617
>=3B >=3B 34 3383 0.6317X 0.4697 0.2232 0.2220
>=3B=
 >=3B
>=3B >=3B % expl.Var. 41 26 4 5
>=3B >=3B
>=3B &=
gt=3B
>=3B >=3B
>=3B >=3BSecondly=2C I would like to look at =
subgroups within my data=2C but dont want
>=3B >=3B
>=3B >=3B=
to delete sorts from the file to do this. Is there a way of "ignoring"
&=
gt=3B >=3B
>=3B >=3Bcertain participants sorts or making a new fil=
e (with copied data) so I c
>=3B >=3Ban
>=3B >=3Bdelete the u=
nwanted sorts?
>=3B >=3B
>=3B >=3BThank you very much for any=
 help!
>=3B >=3BSam
>=3B 
>=3B 
>=3B Daniel Ozer
&=
gt=3B Department of Psychology
>=3B University of California=2C Rivers=
ide
>=3B Riverside CA 92521
>=3B 
>=3B http://www.psych.ucr.=
edu/faculty/ozer/index.html
>=3B 
>=3B Voice: (951) 827-5211
&=
gt=3B Fax: (951) 827-3985
>=3B e-mail: daniel.ozer@ucr.edu

Beyond Hotmail =97 see what else you can do with Windows Live. Find =
out more.
=

--_bdf1e7bd-cf67-41f7-b120-1d9f07813a2f_--