LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (October 2002)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Wed, 2 Oct 2002 02:41:41 -0500
Reply-To:     Ben Earnhart <bearnhar@blue.weeg.uiowa.edu>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Ben Earnhart <bearnhar@blue.weeg.uiowa.edu>
Subject:      Re: your mail
Comments: To: rangarajan <b.rangarajan@pgrad.unimelb.edu.au>
In-Reply-To:  <4.1.20021002155634.009833f0@cassius.its.unimelb.edu.au>
Content-Type: TEXT/PLAIN; charset=US-ASCII

Get to know your data. Odds are the median value for the tenth percentile really *is* 0, especially becuase judging by your variable names, it looks like you're getting frequencies on wages. Read up on "truncation" "censored data" and "floor effects" and it will make a lot of sense; basic idea is that since the value of the variable can't go below 0, you'll have a bunch of people clustered there.

On Wed, 2 Oct 2002, rangarajan wrote:

> Hi: > When i ran following syntax, i always get the median value as zero at the tenth percentile. How could i f fix this. Hope > somebody can guide me. > > FREQUENCIES > VARIABLES=hwage85 hwage86 hwage87 hwage88 hwage89 /FORMAT=NOTABLE > /NTILES= 10 > /STATISTICS=STDDEV MEAN MEDIAN > /ORDER ANALYSIS . > > > Frequencies > > >

*==========================================================*; * Ben Earnhart *; * Department of Management Information Sciences (student), *; * Department of Sociology (work) *; * University of Iowa *; * (319) 335-2887 *; *==========================================================*;


Back to: Top of message | Previous page | Main SPSSX-L page