using quantile regression ，I do know the reason？

[shitong.wang]

SET BASETEXTDIRECTION=AUTOMATIC TABLERENDER=light ROWSBREAK=100 SUMMARY=None TOLERANCE=1 CELLSBREAK=10000 TLook=None Printback=On Locale="Chinese-PRC" MIOUTPUT=[observed imputed pooled diagnostics] OLang=English Unicode=No TFit=Both.
SPSSINC QUANTREG DEPENDENT=NAS_DELAY
  ENTER=DISTANCE WEEK1TO7 WEEK2TO7 WEEK3TO7 WEEK4TO7 WEEK5TO7 WEEK6TO7 SEASON1TO4 SEASON2TO4 SEASON3TO4 TYPE_OF_AIRLINE1TO4 TYPE_OF_AIRLINE2TO4 TYPE_OF_AIRLINE3TO4 TYPE_OF_ARR_TIME1TO6 TYPE_OF_ARR_TIME2TO6 TYPE_OF_ARR_TIME3TO6 TYPE_OF_ARR_TIME4TO6 TYPE_OF_ARR_TIME5TO6 TYPE_OF_DEP_TIME1TO6 TYPE_OF_DEP_TIME2TO6 TYPE_OF_DEP_TIME3TO6 TYPE_OF_DEP_TIME4TO6 TYPE_OF_DEP_TIME5TO6 QUANTILES = .5
  /OPTIONS METHOD = BR STDERR = RANK MISSING=LISTWISE
  /SAVE.
[1] "contrasts can be applied only to factors with 2 or more levels"
Error in quantreg(dep, enter, taus, missing, method, stderr, plot, residualsdataset,  :
  object 'rqres' not found


Y is continuous variable， X1 is continuous variable， X2 is category variable，and the x2 is 1,2,3. X3 is category variable，and the x3 is 1,2,3,4. and so on. I want to use the quantile regression,wheather or not I change the X2,X3 into dummy variable.

[Jon K Peck]

It appears that you have a variable with a categorical measurement level, and it is a constant, possibly due to missing data causing case deletion.  If you can't find the variable, try running a very small problem - just one variable, and adding others one at a time.


Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
phone: [phone]




From:        "shitong.wang" <[hidden email]>
To:        [hidden email]
Date:        10/17/2014 07:53 AM
Subject:        [SPSSX-L] using quantile regression ，I do know the reason？
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

SET BASETEXTDIRECTION=AUTOMATIC TABLERENDER=light ROWSBREAK=100 SUMMARY=None
TOLERANCE=1 CELLSBREAK=10000 TLook=None Printback=On Locale="Chinese-PRC"
MIOUTPUT=[observed imputed pooled diagnostics] OLang=English Unicode=No
TFit=Both.
SPSSINC QUANTREG DEPENDENT=NAS_DELAY
 ENTER=DISTANCE WEEK1TO7 WEEK2TO7 WEEK3TO7 WEEK4TO7 WEEK5TO7 WEEK6TO7
SEASON1TO4 SEASON2TO4 SEASON3TO4 TYPE_OF_AIRLINE1TO4 TYPE_OF_AIRLINE2TO4
TYPE_OF_AIRLINE3TO4 TYPE_OF_ARR_TIME1TO6 TYPE_OF_ARR_TIME2TO6
TYPE_OF_ARR_TIME3TO6 TYPE_OF_ARR_TIME4TO6 TYPE_OF_ARR_TIME5TO6
TYPE_OF_DEP_TIME1TO6 TYPE_OF_DEP_TIME2TO6 TYPE_OF_DEP_TIME3TO6
TYPE_OF_DEP_TIME4TO6 TYPE_OF_DEP_TIME5TO6 QUANTILES = .5
 /OPTIONS METHOD = BR STDERR = RANK MISSING=LISTWISE
 /SAVE.
[1] "contrasts can be applied only to factors with 2 or more levels"
Error in quantreg(dep, enter, taus, missing, method, stderr, plot,
residualsdataset,  :
 object 'rqres' not found




--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/using-quantile-regression-I-do-know-the-reason-tp5727636.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
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

[shitong.wang]

Y is continuous variable， X1 is continuous variable， X2 is category variable，and the x2 is 1,2,3. X3 is category variable，and the x3 is 1,2,3,4. and so on. I want to use the quantile regression,wheather or not I change the X2,X3 into dummy variable.