bugPSPP - Bugs: bug #22419, REGRESSION reports erroneous...

 
 

bug #22419: REGRESSION reports erroneous predicted values

Submitter:  Jason H Stover <jstover>
Submitted:  Tue 26 Feb 2008 04:44:41 AM UTC
   
 
Category:  Numerical Errors Severity:  7 - Major
Status:  Fixed Assigned to:  jstover
Open/Closed:  Closed Release:  Before 0.6.0
Effort:  0.00
* Mandatory Fields

Add a New Comment Rich Markup
   

Tue 11 Mar 2008 08:49:33 AM UTC, comment #4: 

Seems to be fine now.

John Darrington <jmd>
Group administrator
Tue 11 Mar 2008 03:36:19 AM UTC, comment #3: 

I checked in a cleanup of REGRESSION and added a test for the SAVE subcommand. This has fixed the valgrind warnings I was getting. John, can you check this and let me know if it's fixed? If so, I will close this bug.

Jason H Stover <jstover>
Group Member
Fri 29 Feb 2008 10:34:28 PM UTC, comment #2: 

Also, I suggest that you add a test which exercises the /SAVE subcommand of REGRESSION

John Darrington <jmd>
Group administrator
Fri 29 Feb 2008 08:12:48 AM UTC, comment #1: 

Valgrind shows that there is still a potential problem:

 Invalid read of size 4
==4317==    at 0x80E6DC4: pspp_linreg_get_vars (linreg.c:116)
==4317==    by 0x80902A4: regression_trns_pred_proc (regression.q:570)
==4317==    by 0x810E7FF: trns_chain_execute (transformations.c:196)
==4317==    by 0x81005F6: proc_casereader_read (procedure.c:232)
==4317==    by 0x80ECFB4: casereader_read (casereader.c:74)
==4317==    by 0x80ED998: prime_buffer (casereader.c:611)
==4317==    by 0x80ED9FB: shim_read (casereader.c:626)
==4317==    by 0x80ED88E: random_reader_peek (casereader.c:539)
==4317==    by 0x80ED289: casereader_peek (casereader.c:175)
==4317==    by 0x80ED304: casereader_is_empty (casereader.c:195)
==4317==    by 0x80EC1D7: casegrouper_get_next_group (casegrouper.c:113)
==4317==    by 0x80A49FD: cmd_list (list.q:236)
==4317==  Address 0x4B34370 is 0 bytes after a block of size 8 alloc'd
==4317==    at 0x4024765: malloc (vg_replace_malloc.c:149)
==4317==    by 0x8127311: xmalloc (xmalloc.c:49)
==4317==    by 0x80903B6: xnmalloc (xalloc.h:116)
==4317==    by 0x80919BC: coeff_init (regression.q:1097)
==4317==    by 0x8091F73: run_regression (regression.q:1247)
==4317==    by 0x80915A6: cmd_regression (regression.q:976)
==4317==    by 0x804FD2D: do_parse_command (command.c:235)
==4317==    by 0x804FA7E: cmd_parse_in_state (command.c:148)
==4317==    by 0x804FB62: cmd_parse (command.c:165)
==4317==    by 0x804E2BD: main (main.c:124)

John Darrington <jmd>
Group administrator
Tue 26 Feb 2008 04:44:41 AM UTC, original submission:  

The following syntax causes the REGRESSION procedure to report incorrect predicted values:

DATA LIST LIST /x * y.
BEGIN DATA.
    1.00     2.00
    2.00     3.00
    3.00     4.00
    4.00     5.00
    5.00     6.00
    6.00     7.00
    7.00     8.00
    8.00     9.00
    9.00     9.00
     .00     2.00
END DATA.
REGRESSION
/VARIABLES= x
/DEPENDENT= y
/SAVE= PRED.
LIST.

Jason H Stover <jstover>
Group Member

 

(Note: upload size limit is set to 16384 kB, after insertion of the required escape characters.)

Attach Files:
   
   
Comment:
   

No files currently attached

 

Depends on the following items: None found

Items that depend on this one: None found

 

Carbon-Copy List
  • -email is unavailable- added by jmd (Posted a comment)
  • -email is unavailable- added by jstover (Submitted the item)
  •  

    There are 0 votes so far. Votes easily highlight which items people would like to see resolved in priority, independently of the priority of the item set by tracker managers.

    Only logged-in users can vote.

     

    Follow 7 latest changes.

    Date Changed by Updated Field Previous Value => Replaced by
    2008-03-11 jstover StatusIn Progress Fixed
        Open/ClosedOpen Closed
    2008-02-29 jmd StatusFixed In Progress
        ReleaseNone Before 0.6.0
    2008-02-29 jmd Open/ClosedClosed Open
    2008-02-29 jstover StatusNone Fixed
        Open/ClosedOpen Closed

    Back to the top

    Powered by Savane 3.13-caa5.
    Corresponding source code