Hi,
no idea, only suggestions to try:
* Have you standardised before factor analyzing and then again before
clustering?
* Could you visualize whether your factors can actually form clusters
before clustering?
* 4 instead of 3 variables?
* 3 other variables?
I tried MXITER, because I suspect that the cluster centers are too
close together and that the remaining data points, as outliers, are no
longer taken into account.
But I no expert in PSPP oder Statistics.
Here my results
QUICK CLUSTER zego2 zcommunity2 zorder2
/CRITERIA=CLUSTERS(3) MXITER(4).
Clusterzentren der Ausgangsklassifikation
╭─────────────────────┬──────────────────╮
│ │ Cluster │
│ ├──────┬─────┬─────┤
│ │ 1 │ 2 │ 3 │
├─────────────────────┼──────┼─────┼─────┤
│Z-Wert von ego2 │ -5,17│-1,16│ ,77│
│Z-Wert von community2│-12,55│ ,26│ -,15│
│Z-Wert von order2 │ -7,34│ 1,62│-1,06│
╰─────────────────────┴──────┴─────┴─────╯
Anzahl der Fälle in jedem Cluster
╭─────────┬──────────────────────╮
│ │Beobachtete Häufigkeit│
├─────────┼──────────────────────┤
│Cluster 1│ 0│
│ 2│ 746│
│ 3│ 1448│
├─────────┼──────────────────────┤
│Gültig │ 2194│
╰─────────┴──────────────────────╯
QUICK CLUSTER zego2 zcommunity2 zorder2
/CRITERIA=CLUSTERS(3) MXITER(3).
Clusterzentren der Ausgangsklassifikation
╭─────────────────────┬─────────────────╮
│ │ Cluster │
│ ├─────┬─────┬─────┤
│ │ 1 │ 2 │ 3 │
├─────────────────────┼─────┼─────┼─────┤
│Z-Wert von ego2 │-2,57│-1,00│ ,83│
│Z-Wert von community2│-7,41│ ,10│ ,07│
│Z-Wert von order2 │-3,67│ 1,56│-1,15│
╰─────────────────────┴─────┴─────┴─────╯
Anzahl der Fälle in jedem Cluster
╭─────────┬──────────────────────╮
│ │Beobachtete Häufigkeit│
├─────────┼──────────────────────┤
│Cluster 1│ 2│
│ 2│ 872│
│ 3│ 1320│
├─────────┼──────────────────────┤
│Gültig │ 2194│
╰─────────┴──────────────────────╯
by the way: you have 2213 case, which ist different to 2194 (my analysis).
I also used the Schwartz's items, but only for Germany (and therefore
fewer cases), therefore I interessted in the solution.
Best
Andreas
Am 29.08.2026 um 16:04 schrieb [email protected]:
Send Pspp-users mailing list submissions to
[email protected]
To subscribe or unsubscribe via the World Wide Web, visit
https://lists.gnu.org/mailman/listinfo/pspp-users
or, via email, send a message with subject or body 'help' to
[email protected]
You can reach the person managing the list at
[email protected]
When replying, please edit your Subject line so it is more specific
than "Re: Contents of Pspp-users digest..."
Today's Topics:
1. Re: new PSPP page (Frans Houweling)
2. again NaN in Quick Cluster result (ftr)
3. Re: again NaN in Quick Cluster result (Frans Houweling)
----------------------------------------------------------------------
Message: 1
Date: Fri, 28 Aug 2026 18:29:44 +0200
From: Frans Houweling<[email protected]>
To:[email protected]
Subject: Re: new PSPP page
Message-ID:<[email protected]>
Content-Type: text/plain; charset="utf-8"; Format="flowed"
Good work. Good site!
On 8/28/26 12:06, ftr wrote:
Hi,
I found a new (?) , at least recently updated website treating PSPP on
https://knassen.github.io/personal-tech/pspp/pspp.html
There are pages on syntax, exploratory analysis, inferential analysis
& modelling, merging, multi-record data sets, and matrix language.
Regards
-ftr
-------------- next part --------------
An HTML attachment was scrubbed...
URL:<https://lists.gnu.org/archive/html/pspp-users/attachments/20260828/3493bc42/attachment.htm>
------------------------------
Message: 2
Date: Fri, 28 Aug 2026 22:10:22 +0200
From: ftr<[email protected]>
To:[email protected]
Subject: again NaN in Quick Cluster result
Message-ID:<[email protected]>
Content-Type: text/plain; charset="utf-8"; Format="flowed"
Hi,
I look for guidance how to understand the following result of a Quick
Cluster analysis. Before the cluster analysis I factor analysed
Schwartz's 21 Human Values item, dropped cases with a response set and
got a KMO of .89 for the factor analysis. The factors are close to the
study hypotheses.
Now I want to use the three factors community, ego, and order to create
a typology and start with k=3 clusters. For this step I took a 10%
sample of the initial more than 50,000 cases to reduce computation time.
The three input factors are standardised before the clustering. All
cases with missing data are excluded (listwise deletion).
The result is incomprehensible to me. Where does the NaN result for one
cluster may come from ? And the sizes of the 3 clusters are so different
that there must be an error somewhere.
Any ideas ?
Thanks in advance
-ftr
Descriptive Statistics
N Mean Std Dev Minimum Maximum
community2 4738,97 ,01 ,89 -3,73 2,38
ego2 4738,97 ,00 ,92 -3,26 2,53
order2 4738,97 -,03 ,85 -3,28 2,24
Valid N (listwise) 5155,35
Missing N (listwise) 416,38
QUICK CLUSTER zcommunity2 zego2 zorder2
/CRITERIA=CLUSTERS(3) NOINITIAL
/MISSING=EXCLUDE
/PRINT=INITIAL CLUSTER
/SAVE=CLUSTER(clus3t) DISTANCE(distclus3t).
Initial Cluster Centers
Cluster
1 2 3
Z-score of community2 ,04 1,06 ,70
Z-score of ego2 ,84 1,10 -,72
Z-score of order2 -,84 1,10 -,40
Final Cluster Centers
Cluster
1 2 3
Z-score of community2 -,05 1,37 NaN
Z-score of ego2 -,10 2,75 NaN
Z-score of order2 -,09 2,50 NaN
Number of Cases in each Cluster
Count
Cluster 1 2132
2 81
3 0
Valid 2213
-------------- next part --------------
An HTML attachment was scrubbed...
URL:<https://lists.gnu.org/archive/html/pspp-users/attachments/20260828/a52bf44a/attachment.htm>
------------------------------
Message: 3
Date: Sat, 29 Aug 2026 16:03:44 +0200
From: Frans Houweling<[email protected]>
To:[email protected]
Subject: Re: again NaN in Quick Cluster result
Message-ID:<[email protected]>
Content-Type: text/plain; charset="utf-8"; Format="flowed"
Hi,
I am by no means an expert.
You get NaN because cluster 3 has no cases. That's because no case is
closer to the 3rd cluster centers than to the other ones. Why do you see
a contradiction with factor analysis? Factor analysis studies variables,
not respondents.
On 8/28/26 22:10, ftr wrote:
Hi,
I look for guidance how to understand the following result of a Quick
Cluster analysis. Before the cluster analysis I factor analysed
Schwartz's 21 Human Values item, dropped cases with a response set and
got a KMO of .89 for the factor analysis. The factors are close to the
study hypotheses.
Now I want to use the three factors community, ego, and order to
create a typology and start with k=3 clusters. For this step I took a
10% sample of the initial more than 50,000 cases to reduce computation
time. The three input factors are standardised before the clustering.
All cases with missing data are excluded (listwise deletion).
The result is incomprehensible to me. Where does the NaN result for
one cluster may come from ? And the sizes of the 3 clusters are so
different that there must be an error somewhere.
Any ideas ?
Thanks in advance
-ftr
Descriptive Statistics
N Mean Std Dev Minimum Maximum
community2 4738,97 ,01 ,89 -3,73 2,38
ego2 4738,97 ,00 ,92 -3,26 2,53
order2 4738,97 -,03 ,85 -3,28 2,24
Valid N (listwise) 5155,35
Missing N (listwise) 416,38
QUICK CLUSTER zcommunity2 zego2 zorder2
/CRITERIA=CLUSTERS(3) NOINITIAL
/MISSING=EXCLUDE
/PRINT=INITIAL CLUSTER
/SAVE=CLUSTER(clus3t) DISTANCE(distclus3t).
Initial Cluster Centers
Cluster
1 2 3
Z-score of community2 ,04 1,06 ,70
Z-score of ego2 ,84 1,10 -,72
Z-score of order2 -,84 1,10 -,40
Final Cluster Centers
Cluster
1 2 3
Z-score of community2 -,05 1,37 NaN
Z-score of ego2 -,10 2,75 NaN
Z-score of order2 -,09 2,50 NaN
Number of Cases in each Cluster
Count
Cluster 1 2132
2 81
3 0
Valid 2213
-------------- next part --------------
An HTML attachment was scrubbed...
URL:<https://lists.gnu.org/archive/html/pspp-users/attachments/20260829/e4104c76/attachment.htm>
------------------------------
Subject: Digest Footer
_______________________________________________
Pspp-users mailing list
[email protected]
https://lists.gnu.org/mailman/listinfo/pspp-users
------------------------------
End of Pspp-users Digest, Vol 235, Issue 13
*******************************************
--
Andreas Hammer M. A.
Beratung & Evaluation
Eppinger Str. 62
D-76684 Östringen
Telefon +49 72 59 - 92 57 29
Mobil +49 170 - 2 82 68 14
Signal +49 170 - 2 82 68 14
WhatsAPP +49 151 - 59 82 01 95
http://www.andreas-hammer.eu/
Bluesky:https://bsky.app/profile/andreashammer.bsky.social
Xing:https://www.xing.com/profile/Andreas_Hammer28
Linked.In:www.linkedin.com/in/andreas-hammer
Mastodon: @[email protected]
Bankverbindung: IBAN DE87 6635 0036 0017 6394 54
Steuer-Nr. 30361/32021 - Gerichtsstand Bruchsal
Evaluationen - Fortbildungen - Vorträge - Konzeptionen - online-Befragungen <<
NEUESTE BLOG-BEITRÄGE aufwww.andreas-hammer.eu/
99.015 Eintritte, 403 Jobcenter: Wie ungleich Arbeitsgelegenheiten in
Deutschland genutzt werden.
Mindestlohn und öffentlich geförderte Beschäftigung in Deutschland. Hat eine
Mindestlohn-Erhöhung Einfluss auf die öffentlich geförderte Beschäftigung?
Verwaltungskosten und Effizienz der Jobcenter. Welchen Einfluss haben
Verwaltungskosten auf die Vermittlungsquote im SGB II?
Hat der Job-Turbo den Übergang geflüchteter SGB-II-Beziehender in Arbeit
beschleunigt? Eine Strukturbruchanalyse von Abgangsraten (outflow rates).
10 JAHRE „SOMMER DER MIGRATION“ UND “FLÜCHTLINGSKRISE”
Eingliederungsleistungen und Effizienz der Jobcenter und Träger. Einfluss der
Ausgaben für Leistungen zur Eingliederung in Arbeit auf die Integrationsquote
§16h SGB II: Jugendliche frühzeitiger fördern, Wirksamkeit erhöhen.
Outreach im Kontext SGB II
Zeitreihenanalyse von Beschäftigungsübergängen. Trends und Prognosen der
Wiedereingliederung in den Arbeitsmarkt am Beispiel von Abgangsraten.
Staatsangehörigkeit und Grundsicherung für Arbeitsuchende: Der wachsende Anteil
nichtdeutscher Leistungsberechtigter im Kontext der Arbeitsmarkt- und
Sozialpolitik.
