RPI/CPI User Group

Is the term bias being misused?

Posted By: Arthur Barnett November 10, 2012 11:38 am
Posted In: RPI/CPI User Group

Description

The reasoning behind moving the RPI from Carli to Jevons to a large extent depends on the concept of bias, but is this term being misused. 

A statistic is biased if it is calculated in such a way that is systematically different from the population parameter of interest.  

The attached note puts the argument that it is not appropriate to refer to any of the methods of aggregating elementary indices as statistically biased.

It also explores the argument that the Time Reversal test is of limited use for choosing between models for aggregating elementary indices. 

Attachment(s)

Be the first person to share this.

Statistics

0 Favorited
13 Views
1 Files
0 Shares
14 Downloads

Related Entries and Links

No Related Resource entered.