Survey Weights

Weights in the CAHPS Survey data

One of the features of the SEER-CAHPS database is the availability of data on both Medicare fee-for-service (FFS) and Medicare Advantage (MA) enrollees. However, each MA plan has to survey a representative sample of its insurees, so the MA population is over-sampled relative to those with FFS Medicare. In order to produce estimates that better represent the distribution of FFS and MA enrollees in the Medicare population, the SEER-CAHPS data provides two different weight variables.

There are two types of weights found in the CAHPS survey files.

WGT_SIMPLE is a base weight calculated to make the sample representative of the beneficiary populations in the units in the original design. All years and survey types have this type of weight. Using the base weight variable (wgt_simple) allows the analyst to produce estimates that are representative of the beneficiary populations in the units of the original design. For the MA and standalone PDP sample, these units were contracts; for the FFS sample, these were states.

WGT_RAKED was constructed after, using a raking weighting procedure (loglinear weights calculated by iterative proportional fitting) to weight the respondents to match the control distributions estimated from the first round sample (with base weights). In some cases small cells were collapsed with adjacent cells, to avoid extreme weights. This corrected for biases due to differential non-response associated with beneficiary characteristics as well as reducing the effects of random variation in non-response. MA and FFS 2000-2004 does not have this type of weight as the group calculating the weights were unable to get data on non-respondents from that period. Using the raked weight variable (wgt_raked) allows the analyst to correct for biases arising from differential nonresponse associated with beneficiary characteristics as well as reducing the effects of random variation in nonresponse. Currently, raked weights are only available for respondents with surveys in 2011 or later.

Additional information can be found in the yearly Medicare CAHPS Technical Reports, in the Appendix related to Weighting. Some examples of recent reports are referenced here:

  • 2008 Medicare CAHPS Technical Report, Appendix 2.01: Weighting of CAHPS-Medicare data, 2008, version 1.0
  • 2010 MCAHPS Tech Report, Appendix 2.04: Individual-Level Weight Construction
  • 2012 Medicare CAHPS Technical Report, Appendix 2.04: Individual-Level Weight Construction

The following text may be used in describing the weights briefly in manuscripts:

“Data were weighted to represent the enrolled population of contract by county combinations, followed by applying a raking procedure (loglinear weights by iterative proportional fitting) to respondents to match weighted sample distributions within each contract (or state, for FFS beneficiaries unenrolled in a PDP) of gender, age, race/ethnicity, Medicaid and low income supplement eligibility, Special Needs Plan status, PD enrollment, and zip-code level distributions of income, education, and race/ethnicity.”