Include Missings in Cluster analysis

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

Johannes67
Posts: 4
Joined: Thu Jun 14, 2012 10:42 am

Include Missings in Cluster analysis

Postby Johannes67 » Thu Jun 21, 2012 7:00 pm

Hello everyone,

i trying to cluster variables at their country ID, but my data has some missing values.
all in all i´m working with N=36 Countries.

my syntax for my cluster analysis is:

CLUSTER POLITY DemocracyScore DemocOwnCountry RealtionDOWDemocScore DEMOPERF DEMOGOV ELEC SECULAR GENDER DemocTaxes DemocRelAuth DemocFreeElec DemocStatAid DemocArmy DemocCivilRights DemocEconom DemocCriminals DemocChangeLaw DemocWomenRights MuslimShare
WestMuslim LaborPartFemale UnemployYouth GiniIndex YearsInSchool15to44Total YearsInSchool15to44Female YearsInSchool15to44Male StartBusiness BIP_perCapita BIPoil BIPagrar BIPserviceIndustries
/METHOD WAVERAGE
/MEASURE=SEUCLID
/ID=countryname
/PRINT SCHEDULE CLUSTER(2,6)
/PLOT DENDROGRAM HICICLE.

if i rum this syntax, spss kicks out like 24 countries because within that 24 countries i have at a minimum one missing value, maximum is 3 (of 24 total variables). How can i indluce cases that have missing values? anyone knows some syntax?
how many missings can i accept?


thanks a lot,

best greetz!
statman
Administrator
Posts: 2757
Joined: Tue Jun 12, 2007 12:08 pm
Location: Florida, USA

Re: Include Missings in Cluster analysis

Postby statman » Mon Jun 25, 2012 12:41 am

Many models filter out missing to 'balance the response base' but there is a missing values module for SPSS (extra $) or perhaps even imputation
See the note below

NOTE: Please read the Posting Guidelines and always tell us your OS, the SPSS version and information about your study and data!

Statman
Statistical Services
Johannes67
Posts: 4
Joined: Thu Jun 14, 2012 10:42 am

Re: Include Missings in Cluster analysis

Postby Johannes67 » Wed Jun 27, 2012 4:11 pm

statman wrote: (...) or perhaps even imputation
thanks for your answer!

If i use imputation, how do i implement this?

do i use linear Regression to estimate the value for the missing? and do i use highly correlated
sample characteristics for the regression?

Who is online

Users browsing this forum: No registered users and 3 guests

cron