August 11, 2000
Ottawa



Subject: Re-weighting of the Labour Force Survey (LFS) and its impact on
the Residential Telephone Service Survey (RTSS) 

The Residential Telephone Service Survey (RTSS) is administered to a
sub-sample of the dwellings in the Labour Force Survey (LFS) sample, and
therefore its weighting and population estimates are closely tied to
those of the LFS. 

In the past the LFS calculated its population totals based on population
projections using the 1991 Census. In January 2000, the Labour Force
Survey began calculating its population totals based on population
projections using the 1996 Census. This has resulted in a decrease in
the estimate of the total population. For RTSS, this has resulted in
population totals reported in the May 2000 RTSS to be lower than those
reported in the August 1999 RTSS. 

Because of this, users are cautioned not to make comparisons between the
counts seen in the May 2000 RTSS and any previous RTSS. Users can,
however, continue to compare rates as rates are robust to changes in
totals. 

There are plans to re-weight the May 1998 and May 1999 RTSS microdata
files in the next few months. Once this work has been completed, users
will be able to make comparisons between the counts seen in all three
May collections.