Zur Schätzung des Inkonsistenz-Index als Maßzahl zur Fehlermessung bei klassierten Erhebungsergebnissen / On the Estimation of the Index of Inconsistency as Special Statistic to Measure Errors in Classified Survey Results
The index of inconsistency is outlined as a special statistic for judging the reliability of survey data classified by size classes. The index estimates take on, as a rule, values between 0 and 1 according to a previously definded restriction for dichotomized proportions in the estimation formula (estimates should be ≤ 1). If the results of a main survey and a repetition show no variability of the individual responses regarding the assignment of units i to specified size classes the index value is 0, in case of total unreliability (random differences) it is, as a rule, 1. The extreme values 0 and 1 are demonstrated by means of simulated examples and their data show that the restriction required is fulfilled.
Volume (Year): 220 (2000)
Issue (Month): 6 (December)
|Contact details of provider:|| Web page: http://www.degruyter.com|
|Order Information:||Web: http://www.degruyter.com/view/j/jbnst|
When requesting a correction, please mention this item's handle: RePEc:jns:jbstat:v:220:y:2000:i:6:p:777-792. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Peter Golla)
If references are entirely missing, you can add them using this form.