1. For the 2002 NYCHVS, a completely new sample was initially selected from the 2000 decennial census and updated by including newly created housing units, while the 1991 NYCHVS sample was selected from the 1990 census and updated for the 1993, 1996, and 1999 NYCHVSs.

2. The 2002 NYCHVS was weighted based on the results from the 2000 decennial census, while the 1991, 1993, 1996, and 1999 NYCHVSs were all weighted based on results from the 1990 decennial census. Since surveys based on different censuses produce different results (2000 versus 1990), it may be difficult to compare various data from the 2002 NYCHVS to the 1999 NYCHVS and earlier years.

1. After reviewing all major issues concerning reweighting earlier data, we have decided not to reweight any prior NYCHVS surveys for the following reasons:
   
   • The NYCHVS surveys from the 1990s and from 2002/2005 are from different samples and are weighted based on different decennial censuses (1990 and 2000). We know that Census 2000 had a better coverage of population and housing in the United States and in New York City than did the 1990 census. Comparing estimates from the 1999 and previous NYCHVSs with the 2002 NYCHVS reflects this improved coverage. Simply reweighting earlier data would likely not solve inconsistencies in housing unit and population estimates between the two survey years.
   • In Census 2000, there was a major change in the way race data was collected in the decennial census. Respondents were allowed to choose more than one race, whereas prior to Census 2000, respondents could only select one race. This was an important difference in the Census 2000 from earlier censuses. All current surveys had to make this change in data collection. So, for the 2002/2005 NYCHVS, respondents were allowed to select more than one race, whereas in the 1999 NYCHVS and earlier surveys, only one race could be selected. Since race is an important part of the weighting process and because of this change in data collection, we don’t believe there is any way to make data for the 2002/2005 NYCHVSs consistent with earlier NYCHVSs.
   • If the 1999 NYCHVS data were reweighted, the 2002 NYCHVS data would also have to be reweighted. Reweighting the 2002 NYCHVS data would necessitate revising estimates of the components of inventory change from 1999 to 2002 and from 2002 to 2005. Therefore, reweighting the 1999 NYCHVS data would cause a chain reaction for three or more NYCHVSs: 1999, 2002, 2005, and probably beyond. In the year following each NYCHVS survey, we release the best data that we have at that time. Once these estimates are officially released, we believe they should be considered final. The NYCHVS survey results are ratio estimated to match independent housing unit estimates by borough AND independent population estimates by borough, age, race, and sex. As time goes on, these independent housing and population estimates may change as more updated data become available. We don’t believe these changes warrant reissuing the NYCHVS data every time this occurs.
2. In comparing data from 1999 and previous NYCHVSs with data from 2002 and 2005 NYCHVSs data users should compare percentages, means, and medians, rather than absolute numbers of housing units, households, and/or persons from survey to survey.

We have corrected/revised the following items on the 2002 NYCHVS microdata file:

Race and Ethnicity Recode (Character position 228): We have revised this item after discovering that Asians were being included in the two or more race category.

Sub borough Areas (Character Positions 315-316): We have revised 16 sample cases where the Sub-borough areas were incorrect.

Type of Schedule Code (Character position 217-218): We corrected 1 sample case that was incorrectly classified.

Wheelchair Accessibility (Character position 30): This has been corrected.

Housing Allocation Flags (Character positions 349-375): Values for sample cases not allocated have been changed from missing to zero.