Table 35 Paired-person (cheating) agreement |
(controlled by PSELECT=, ISELECT=, PSUBTOTAL=, MAXPAGE=, LINELENGTH=)
In Table 35, the response string for each person (row) is compared with the response string for every other person (row). The underlying details for Table 35 are reported in the AGREEFILE= file.
Sub-samples (groups of persons) can be specified with PSUBTOTAL=. Five plots are displayed for each sub-sample, unless the plot is empty.
When Table 35 is launched from the Output Tables menu, the Table 35 dialog box displays.
Table 35 Table 35.1-5 - plots for the entire sample or for the accumulated sub-samples selected by PSUBTOTAL= Table 35.11-15, 35.21-25, ... - plots for sub-samples selected by PSUBTOTAL= |
x-axis: "Average of two person measures" = average of the ability measures for each pair of two persons. plotted values: 1-9 are counts of pairs at the x,y coordinates. * is more than 9 pairs. |
Table 35.1, 35.11, 35.21, ...
% SAME (PAIRED STUDENT) OBSERVED RESPONSES -4 -2 0 2 4 6 +-------+-------+-------+-------+-------+ 100%| 1 | | | 90%| | | 1 | 80%| 11 1 | | 1 | 70%| 2 2 | | 1 1 21 1 1 | 60%| 1 1 13 1 | | 11 2 4111 1 2 21 2 | 50%| 1 1212 22224 1 1 11 | | 232111 142 1 1 1 | 40%| 23 1121 | | 1 1 11 11 | 30%| 1 21 1 | | 1 1 1 1 11 | 20%| 1 | | | 10%| | | | 0%| 1 | +-------+-------+-------+-------+-------+ -4 -2 0 2 4 6 AVERAGE OF THE TWO STUDENT MEASURES |
Table 35.1, 35.11, 35.21, ... y-axis: "% Same (paired student) observed responses" = the count of items for which both persons have the same response code in CODES= divided by the count of items for which both persons have a non-missing response %.
Cheating detection: shared responses. For cheating-detection, see www.rasch.org/rmt/rmt61d.htm
In the plot, "1" indicates that 1 pair are plotted at this point. "2" indicates 2 pairs. "4" indicates 4 pairs, and so on up to "9". When there are 10 or more pairs at a point, "*" is plotted. |
Table 35.2, 35.12, 35.22, ...
% SAME (PAIRED STUDENT) SCORED RESPONSES -4 -2 0 2 4 6 +-------+-------+-------+-------+-------+ 100%| 1 1 | | | 90%| 1 | | 1 1 1 | 80%| 11 1 | | 1 133 | 70%| 1 1 11441 1 2 | | 1 1 112 2111 2 1 | 60%| 114112121 2 | | 1111 221 1 1 21 2 | 50%| 1 1 34 11114 11 | | 1 1 1 1 1 | 40%| 1 1 | | 1 1 11 | 30%| 1 | | 1 1 11 | 20%| | | | 10%| | | | 0%| 1 | +-------+-------+-------+-------+-------+ -4 -2 0 2 4 6 AVERAGE OF THE TWO STUDENT MEASURES |
Table 35.2, 35.12, 35.22, ... y-axis: "% Same (paired student) scored responses" = the count of items for which both persons have the same score divided by the count of items for which both persons have a non-missing response %. |
Table 35.3, 35.13, 35.23, ...
% SAME (PAIRED STUDENT) OBSERVED HIGHEST (RIGHT) RESPONSES -4 -2 0 2 4 6 +-------+-------+-------+-------+-------+ 100%| 1 1 | | | 90%| | | 1 | 80%| 1 1 | | 1 1 | 70%| 1 1 2 | | 1 2 1 | 60%| 322 2 | | 1 2 231 1 1 11 2 | 50%| 1 21211111 2 1 11 | | 14111121 1 | 40%| 1113 1231 1 1 | | 1 1121 121 2 1 | 30%| 1 1 1 | | 1 11121 | 20%| 1 111 | | 1 | 10%| | | | 0%| 211 | +-------+-------+-------+-------+-------+ -4 -2 0 2 4 6 AVERAGE OF THE TWO STUDENT MEASURES |
Table 35.3, 35.13, 35.23, ... y-axis: "% Same (paired student) observed highest (right) responses" = the count of items for which both persons have the same highest scored response divided by the count of items for which one or both persons have a highest scored response %.
Cheating detection: shared knowledge |
Table 35.4, 35.14, 35.24, ...
% SAME (PAIRED STUDENT) OBSERVED LOWEST (WRONG) RESPONSES -4 -2 0 2 4 6 +-------+-------+-------+-------+-------+ 100%| | | | 90%| | | | 80%| | | | 70%| | | 1 | 60%| 1 1 11 | | | 50%| 1 | | 1 2 1 | 40%| 1 1 1 | | 1 2 1 323 | 30%| 1 11311 | | 1412 41 21 1 | 20%| 1 122121224 | | 1 1 1 151 1 21 4 1 | 10%| 11 11 | | 1 | 0%| 1 1 11 1 111111 11124 2 | +-------+-------+-------+-------+-------+ -4 -2 0 2 4 6 AVERAGE OF THE TWO STUDENT MEASURES |
Table 35.4, 35.14, 35.24, ... y-axis: "% Same (paired student) observed lowest (wrong) responses" = the count of items for which both persons have the same lowest scored response divided by the count of items for which one or both persons have a lowest scored response %.
Cheating detection: shared ignorance - a better indication of cheating than shared knowledge. |
Table 35.5, 35.15, 35.25, ...
% SAME (PAIRED STUDENT) MISSING RESPONSES -4 -2 0 2 4 6 +-------+-------+-------+-------+-------+ 100%| | | | 90%| 1 | | 1 2 2 | 80%| 1 1 | | 1 11 11 1 1 | 70%| 1 11 1 1 2 1 | | 11 3331 421 11 1 21 | 60%| 125 1222 1 11 | | 111 21231 55 1 1 1 | 50%| 1 1 3421 1 | | 1 11 1 1 | 40%| 1 2 | | 11 | 30%| | | 1 | 20%| | | | 10%| | | | 0%| | +-------+-------+-------+-------+-------+ -4 -2 0 2 4 6 AVERAGE OF THE TWO STUDENT MEASURES |
Table 35.5, 35.15, 35.25, ... This Table is only output when there are missing observations in the data.
y-axis: "% Same (paired student) missing responses" = the count of items for which both persons have a missing response divided by the count of items for which one or both persons have a missing response %.
Pairs of students near the top of the plot responded to almost the same items.
CAT testing: to detect test overlap, which we want to minimize in order avoid item over-exposure and "tracking" through the item bank. |
Help for Winsteps Rasch Measurement and Rasch Analysis Software: www.winsteps.com. Author: John Michael Linacre
Facets Rasch measurement software.
Buy for $149. & site licenses.
Freeware student/evaluation Minifac download Winsteps Rasch measurement software. Buy for $149. & site licenses. Freeware student/evaluation Ministep download |
---|
Forum: | Rasch Measurement Forum to discuss any Rasch-related topic |
---|
Questions, Suggestions? Want to update Winsteps or Facets? Please email Mike Linacre, author of Winsteps mike@winsteps.com |
---|
State-of-the-art : single-user and site licenses : free student/evaluation versions : download immediately : instructional PDFs : user forum : assistance by email : bugs fixed fast : free update eligibility : backwards compatible : money back if not satisfied Rasch, Winsteps, Facets online Tutorials |
---|
Our current URL is www.winsteps.com
Winsteps® is a registered trademark