bug-gnu-pspp
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

PSPP-BUG: [bug #57731] Wrong results of NPAR TEST RUNS for some data


From: Igor Kushnir
Subject: PSPP-BUG: [bug #57731] Wrong results of NPAR TEST RUNS for some data
Date: Mon, 3 Feb 2020 13:04:47 -0500 (EST)
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:72.0) Gecko/20100101 Firefox/72.0

URL:
  <https://savannah.gnu.org/bugs/?57731>

                 Summary: Wrong results of NPAR TEST RUNS for some data
                 Project: PSPP
            Submitted by: vedg
            Submitted on: Mon 03 Feb 2020 06:04:45 PM UTC
                Category: Numerical Errors
                Severity: 5 - Average
                  Status: None
             Assigned to: None
             Open/Closed: Open
         Discussion Lock: Any
                 Release: None
                  Effort: 0.00

    _______________________________________________________

Details:

The wrong results are the same in the two PSPP versions I have tested:
  * 1.2.0-3 on Debian Buster 64-bit;
  * pspp-20200117-daily-32bits-ForTestingOnly on Windows 7 64-bit.

Steps to reproduce:
1. Open the attached files runs-bug.sav and runs-bug.sps in PSPP.
2. Run all of runs-bug.sps.

Actual results:

NPAR TEST
        /RUNS ( MEAN ) =  Var0001 Var0002 Var0003 Var0004.

Runs Test
╔══════════════════════╦═══════╤═══════╤═══════╤═══════╗
║                      ║Var0001│Var0002│Var0003│Var0004║
╠══════════════════════╬═══════╪═══════╪═══════╪═══════╣
║Test Value (mean)     ║    .60│    .60│    .60│    .60║
║Cases < Test Value    ║      2│      2│      2│      2║
║Cases ≥ Test Value    ║      3│      3│      3│      3║
║Total Cases           ║      5│      5│      5│      5║
║Number of Runs        ║      5│      2│      3│      4║
║Z                     ║   1.20│   -.98│    .00│    .11║
║Asymp. Sig. (2-tailed)║   .230│  1.674│  1.000│   .913║
╚══════════════════════╩═══════╧═══════╧═══════╧═══════╝


Expected results:
The results in columns where Z>=0 are correct. When Z<0, the result is
incorrect: it's actually 2-correct_result.
Note that in the second column Asymp. Sig. (2-tailed) is greater than 1, which
is impossible because this is a probability value.



    _______________________________________________________

File Attachments:


-------------------------------------------------------
Date: Mon 03 Feb 2020 06:04:45 PM UTC  Name: runs-bug.sav  Size: 696B   By:
vedg

<http://savannah.gnu.org/bugs/download.php?file_id=48338>
-------------------------------------------------------
Date: Mon 03 Feb 2020 06:04:45 PM UTC  Name: runs-bug.sps  Size: 63B   By:
vedg

<http://savannah.gnu.org/bugs/download.php?file_id=48339>

    _______________________________________________________

Reply to this item at:

  <https://savannah.gnu.org/bugs/?57731>

_______________________________________________
  Message sent via Savannah
  https://savannah.gnu.org/




reply via email to

[Prev in Thread] Current Thread [Next in Thread]