| |
In a panel design,
participants are followed over multiple survey rounds for a specified
period of time. New panels are created at designated intervals.
Although the MEPS and MCBS both use a panel design, there are,
again, important design differences that need to be considered.
The Household Component of MEPS uses an overlapping panel design
in which data are collected through an initial round of contact
followed by a series of four rounds of interviews over a 2 1/2-year
period, and data for 2 calendar years are collected from each
household. This series of data collection rounds is launched on
a new sample of households each year to provide overlapping panels
of survey data. Therefore, in any given year one panel is in the
first year of data collection and another in the second year.
These panels can be combined to increase sample size and power.
MCBS uses a rotating panel design in which subjects agree to participate
in twelve equally-spaced interviews over a period of four years.
Newly sampled subjects remain in the panel for no more than four
years at which time they are rotated out and replaced by newly
sampled subjects. Approximately one fourth of the panel is replaced
each year. Using a cohort model, it is possible to follow the
experience of 12,000 persons for one year, 8,000 persons for two
years, and 4,000 persons for four years.
The MCBS interviewing
schedules mean that a subject's four-year enlistment generates
three year's worth of utilization and cost data, and four years
of health status, coverage, and other survey data.
|