lang/en_utf8/help/quiz/itemanalysis.html

   1 <h1>Item Analysis</h1>
   2
   3 <p>This table presents processed quiz data in a way suitable for anayzing and judging the
   4 performance of each question for the function of assessment. The statistical parameters used are
   5 calculated as explained by classical test theory (ref. 1)</p>
   6
   7 <h2>Facility Index (% Correct)</h2>
   8 <p>This is a measure of how easy or difficult is a question for quiz-takers.
   9 It is calculated as:
  10 <br />
  11 FI = (X<sub>average</sub>) / X<sub>max</sub>
  12 <br />
  13
  14 where X<sub>average</sub> is the mean credit obtained by all users attempting the item, <br/>
  15 and X<sub>max</sub> is the maximum credit achievable for that item.<br/>
  16 If questions can be distributed dicotomically into correct / uncorrect categories,
  17 this parameter coincides with the percentage of users that answer the question correctly. </p>
  18
  19 </p>
  20 <h2>Standard Deviation (SD)</h2>
  21 <p>This parameter measures the spread of answers in the response population. If all users
  22 answers the same, then SD=0. SD is calculated as the statistical stadard deviation for the
  23 sample of fractional scores (achieved/maximum) at each particular question.
  24 </p>
  25
  26 <h2>Discrimination Index (DI)</h2>
  27 <p>This provides a rough indicator of the performance of each item to separate proficient
  28 <i>vs.</i> less-proficient users. This parameter is calculated by first dividing learners into thirds
  29 based on the overall score in the quiz. Then the average score at the analyzed item is calculated for
  30 the groups of top and bottom performers, and the average scored substracted. The matematical expression is:
  31 <br/>
  32 DI = (X<sub>top</sub> - X<sub>bottom</sub>)/ N
  33 <br/>
  34
  35 where X<sub>top</sub> is the sum of the fractional credit (achieved/maximum) obtained at this item by the 1/3 of users having tha highest
  36 grades in the whole quiz (i.e. number of correct responses in this group), <br/>
  37 and X<sub>bottom</sub>) is the analog sum for users with the lower 1/3 grades for the whole quiz.</p>
  38
  39 <p>This parameter can take values between +1 and -1.
  40 If the index goes below 0.0 it means that more of the weaker learners got the item right than the stronger learners.
  41 Such items should be discarded as worthless.  In fact, they reduce the accuracy of the overall score for the quiz. </p>
  42
  43 <h2>Discrimination Coefficient (DC)</h2>
  44 <p>This is another measure of the separating power of the item to distinguish proficient from weak learners.<br/>
  45 The discrimination coefficient is a correlation coefficient between scores at the item and at the whole quiz. Here it is calculated as:
  46
  47 <br/>
  48 DC = Sum(xy)/ (N * s<sub>x</sub> * s<sub>y</sub>)
  49 <br/>
  50 where Sum(xy) is the sum of the products of deviations for item scores and overall quiz scores, <br/>
  51 N is the number of responses given to this question<br/>
  52 s<sub>x</sub> is the standard deviation of fractional scores for this question and, <br/>
  53 s<sub>y</sub> is the standard deviation of scores at the quiz as a whole.
  54 </p>
  55 <p>Again, this parameter can take values between +1 and -1. Positive values indicate items that
  56 do discriminate proficient learners, whereas negative indices mark items that are answered best by
  57 those with lowest grades. Items with negative DC are answered incorrectly by the seasoned learners
  58 and thus they are actually a penalty against the most proficient learners. Those items should be avoided.<br/>
  59 The advantage of Discrimination Coefficient vs. Discrimitation Index is that the former uses information
  60 from the whole population of learners, not just the extreme upper and lower thirds. Thus, this parameter may be
  61 more sensitive to detect item performance.</p>