An important statistic in classical item analysis is the item proportion-correct (item-analysis p-value), the proportion of the sample succeeding on a dichotomous item. In Winsteps, this value is interpreted as the average of the responses to the item for both dichotomous and polytomous items.
This proportion-correct-value is not a hypothesis test probability-value (statistical p-value). For hypothesis tests of fit, use the ZSTD values, which are probability-values expressed as unit-normal deviates.
PVALUE = NO Do not report the item observed proportion-correct-value.
PVALUE=YES Report item obsered proportion-correct-values in Tables 6, 10, etc. and IFILE= (over-riding the existing default setting.)
Example: To parallel a classical analysis of an MCQ data set, it is desired to report the raw scores (including extreme persons and items), the point-biserials and the proportion-correct-values or average ratings.
TOTALSCORE= YES ; report original total raw scores
PTBISERIAL = YES ; report point-biserial, not point-measure correlations
PVALUE = YES ; report proportion-correct-values
+----------------------------------------------------------------------------------------+
|ENTRY TOTAL | INFIT | OUTFIT |PTBSE|PROP-| |
|NUMBER SCORE COUNT MEASURE ERROR|MNSQ ZSTD|MNSQ ZSTD|CORR.|VALUE| ITEM |
|------------------------------------+----------+----------+-----+-----+-----------------|
| 1 35 35 -6.59 1.85| MINIMUM ESTIMATED MEASURE | 1.00| 1= 1-4 |
| 4 32 35 -4.40 .81| .90 .0| .35 .8| .48| .91| 4= 1-3-4 |
| 12 6 35 2.24 .55|1.16 .6|1.06 .5| .26| .17| 12=1-3-2-4-3 |
| 18 0 35 6.13 1.84| MAXIMUM ESTIMATED MEASURE | .00| 18=4-1-3-4-2-1-4|
