Font Size:
|
||||||
MEPS HC-225
|
Type of Variable | Full-Year Consolidated File Variable Name Suffix | Longitudinal File Variable Name Suffix | Specific cases or examples |
---|---|---|---|
Constant (i.e., not round or year specific) |
No suffixes |
No suffixes |
All variables: BORNUSA=BORNUSA DOBMM=DOBMM DOBYY=DOBYY DUID=DUID PID=PID DUPERSID=DUPERSID EDUCYR=EDUCYR HIDEG=HIDEG HISPANX=HISPANX HISPNCAT=HISPNCAT HWELLSPK=HWELLSPK INTVLANG=INTVLANG OTHLGSPK=OTHLGSPK PANEL=PANEL PID=PID RACEAX=RACEAX RACEBX=RACEBX RACEWX=RACEWX RACEV1X=RACEV1X RACEV2X=RACEV2X RACETHX=RACETHX SEX=SEX VARPSU=VARPSU VARSTR=VARSTR WHTLGSPK=WHTLGSPK YRSINUS=YRSINUS |
Annual, family related variables |
YR |
Y1 or YR1 Y2 or YR2 |
All variables: FAMIDYR=FAMIDYR1 (2019 file) FAMRFPYR=FAMRFPY1 (2019 file) FAMSZEYR=FAMSZYR1 (2019 file) FAMIDYR=FAMIDYR2 (2020 file) FAMRFPYR=FAMRFPY2 (2020 file) FAMSZEYR=FAMSZYR2 (2020 file) |
Annual, CPS family identifiers |
No suffix |
Y1 Y2 |
All variables: CPSFAMID= CPSFAMY1 (2019 file) CPSFAMID= CPSFAMY2 (2020 file) |
Annual, health insurance eligibility units |
No suffix |
Y1 Y2 |
All variables: HIEUIDX=HIEUIDY1 (2019 file) HIEUIDX=HIEUIDY2 (2020 file) |
Annual, inscope variables |
No suffixes |
YR1 YR2 |
All variables: INSCOPE=INSCPYR1 (2019 file) INSCOPE=INSCPYR2 (2020 file) |
12/31 status variables |
1231 in 2019 file 1231 in 2020 file |
Y1 Y2 |
All variables: FAMS1231=FAMSY1 (2019 file) FCRP1231=FCRPY1 (2019 file) FCSZ1231=FCSZY1 (2019 file) FMRS1231=FMRSY1 (2019 file) INSC1231=INSCY1 (2019 file) FAMS1231=FAMSY2 (2020 file) FCRP1231=FCRPY2 (2020 file) FCSZ1231=FCSZY2 (2020 file) FMRS1231=FMRSY2 (2020 file) INSC1231=INSCY2 (2020 file) |
Annual |
19, 19X, 19F, or 19C 20, 20X, 20F, or 20C |
Y1, Y1X, Y1F, or Y1C Y2, Y2X, Y2F, or Y2C |
Examples: TOTEXP19=TOTEXPY1 AGE19X=AGEY1X TOTEXP20=TOTEXPY2 AGE20X=AGEY2X |
Variables for health insurance prior to January 1, 2019 (data collected in Round 1 only) |
No suffixes |
No suffixes |
All variables: PREVCOVR=PREVCOVR MORECOVR=MORECOVR |
Annual |
No suffixes3 |
Y1 Y2 |
Examples: KEYNESS=KEYNESY1 (2019 file) SAQELIG=SAQELIY1 (2019 file) EVRWRK=EVRWRKY1 (2019 file) EVRETIRE=EVRETIY1 (2019 file) AGELAST=AGELSTY1 (2019 file) DIABDX_M18=DIABDXY1_M18 (2019 file) KEYNESS=KEYNESY2 (2020 file) SAQELIG=SAQELIY2 (2020 file) EVRWRK=EVRWRKY2 (2020 file) EVRETIRE=EVRETIY2 (2020 file) AGELAST=AGELSTY2 (2020 file) DIABDX_M18=DIABDXY2_M18 (2020 file) |
Monthly |
2-character month + 19 2-character month + 20 |
2-character month + Y1 2-character month + Y2 |
Example: PRIJA19=PRIJAY1 (2019 file) PRIJA20=PRIJAY2 (2020 file) |
Round Specific |
31, 31X, or 31H in 2019 file 42, 42X, or 42H in 2019 file 53, 53X, or 53H in 2019 file 31_M18 in 2019 file 42_M18 in 2019 file 31, 31X, or 31H in 2020 file 42, 42X, or 42H in 2020 file 53, 53X, or 53H in 2020 file 31_M18 in 2020 file 42_M18 in 2020 file |
1, 1X, or 1H for 2019 2, 2X, or 2H for 2019 3, 3X, or 3H for 2019 1_M18 for 2019 2_M18 for 2019 3, 3X, 3H for 2020 4, 4X, 4H for 2020 5, 5X, 5H for 2020 3_M18 for 2020 4_M18 for 2020 |
Example: RTHLTH31=RTHLTH1 (2019 file) RTHLTH42=RTHLTH2 (2019 file) RTHLTH53=RTHLTH3 (2019 file if YEARIND=2) JTPAIN31_M18=JTPAIN1_M18 PROVTY42_M18=PROVTY2_M18 RTHLTH31= RTHLTH3 (2020 file if YEARIND=1 or 3) RTHLTH42=RTHLTH4 (2020 file) RTHLTH53=RTHLTH5 (2020 file) JTPAIN31_M18=JTPAIN3_M18 PROVTY42_M18=PROVTY4_M18 |
Diabetes preventive care |
1853, 1953, and 2053 in 2019 file 1953, 2053, and 2153 in 2020 file |
Y0R3 for 2018 Y1R3 for 2019 Y2R3 for 2020 Y1R5 for 2019 Y2R5 for 2020 Y3R5 for 2021 |
Example: DSEB1753=DSEBY0R3 (2019 file) DSEY1753=DSEYY0R3 (2019 file) DSEY1853=DSEYY1R3 (2019 file) DSEY1953=DSEYY2R3 (2019 file) DSEB1853=DSEBY1R5 (2020 file) DSEY1853=DSEYY1R5 (2020 file) DSEY1953=DSEYY2R5 (2020 file) DSEY2053=DSEYY3R5 (2020 file) |
Job Change |
3142 or 4253 |
12 for 2019 23 for 2019 34 for 2020 45 for 2020 |
All cases: CHGJ3142=CHGJ12(2019 file) CHGJ4253=CHGJ23(2019 file) YCHJ3142=YCHJ12(2019 file) YCHJ4253=YCHJ23(2019 file) CHGJ3142=CHGJ34 (2020 file) CHGJ4253=CHGJ45 (2020 file) YCHJ3142=YCHJ34 (2020 file) YCHJ4253=YCHJ45 (2020 file) |
Cancer/ Cancer in remission4 |
No suffixes5 |
Y1 for 2019 Y2 for 2020 |
Example: CALUNG=CALUNGY1 (2019 file) CALUNG=CALUNGY2 (2020 file) |
Age of Diagnosis |
No suffixes5 |
Y1 for 2019 Y2 for 2020 |
Example: CHDAGED=CHDAGY1 (2019 file) CHOLAGED=CHOLAGY1(2019 file) CHDAGED=CHDAGY2 (2020 file) CHOLAGED=CHOLAGY2(2020 file) |
[3] To maintain a previously-implemented 8-character naming convention, some variable names had the last character or two dropped in the renaming process. A few variables have names longer than 8 characters because they were modified in 2018 and tagged with an '_M18' suffix. These variables were altered in the same fashion they would have been without the _M18 suffix, and the _M18 suffix was retained.
[4] Starting in 2010, variables were added to indicate whether each reported cancer was in remission.
[5]To maintain a previously implemented 8-character naming convention, some variable names had the last character or two dropped in the renaming process.
YEARIND | 1=both years, 2=in 2019 only, and 3=in 2020 only |
ALL5RDS | In scope and data collected in all 5 rounds (0=no, 1=yes) |
DIED | Died during the two-year survey period (0=no, 1=yes) |
INST | Institutionalized for some time during the two-year survey period (0=no, 1=yes) |
MILITARY | Active duty military for some time during the two-year survey period (0=no, 1=yes) |
ENTRSRVY | Entered survey after beginning of panel (mainly births; also includes persons who had no initial chance of selection who moved into a MEPS sample household) (0=no, 1=yes) |
LEFTUS | Moved out of the country after beginning of panel (0=no, 1=yes) |
OTHER | Not identified in any of the above analytic groups (0=no, 1=yes) |
Table 2. Frequencies and Percentage for Constructed Variables
Variable |
Number of Records |
Percentage of Records (N=9,797) |
---|---|---|
YEARIND=1 (i.e., person in both years) |
9,569 |
97.7 |
ALL5RDS=1 (yes) |
9,120 |
93.1 |
DIED=1 (yes) |
211 |
2.2 |
INST=1 (yes) |
29 |
0.3 |
MILITARY=1 (yes) |
27 |
0.3 |
ENTRSRVY=1 (yes) |
362 |
3.7 |
LEFTUS=1 (yes) |
25 |
0.3 |
OTHER=1 (yes) |
34 |
0.4 |
Following are examples of situations where these variables would be useful in selecting records for analysis:
The file contains a weight variable (LONGWT) and variance estimation variables (VARSTR, VARPSU) that should be applied when producing national estimates for longitudinal analyses. For example, LONGWT applied to the 9,120 cases where ALL5RDS=1 produces a weighted population estimate of 307.0 million. This represents an estimate of the number of persons in the civilian noninstitutionalized population for the entire two-year period from 2019-2020. To obtain estimates of variability (such as the standard error of sample estimates or corresponding confidence intervals) for estimates based on MEPS survey data, one needs to take into account the complex sample design of MEPS by specifying the estimation variables including stratum of sample selection (VARSTR), primary sampling unit (VARPSU) and longitudinal weight (LONGWT).
This longitudinal file also contains a longitudinal SAQ weight variable (LSAQWT). This weight variable should be used to perform longitudinal analyses involving any variables from the self-administered questionnaire (SAQ) which was administered to persons age 18 and older in both rounds 2 and 4 of the survey. The variable SAQRDS24 can be used to identify which persons have SAQ data for both versus only one of the two rounds. Table 3 below provides the estimated population size (i.e., the sum of LSAQWT values) for cases with only one round of SAQ data (i.e., SAQRDS24=0) and for cases with both rounds of SAQ data (i.e., SAQRDS24=1). The estimated population size for analyses based on the 4,737 cases with SAQ data for both rounds (i.e., SAQRDS24=1) is 229.34 million.
Table 3. Number of Respondents and Estimated Population Size for SAQ Analyses
Value of |
Description |
Number of |
Estimated Population |
---|---|---|---|
0 |
Persons with one round of SAQ data |
5,060 |
23,602,504 |
1 |
Persons with both rounds of SAQ data |
4,737 |
229,285,551 |
Total |
All SAQ respondents |
9,797 |
252,888,055 |
When analyzing subpopulations and/or low prevalence events, it may be desirable to pool together more than one panel of MEPS-HC data to yield sample sizes large enough to generate reliable estimates. If only data from Panels 7 and beyond are being pooled, then simply use the strata and PSU variables (VARSTR, VARPSU)[6] provided on the longitudinal files for pooled estimation. However, because Panels 1-6 MEPS longitudinal weight files were released with panel-specific variance structures, it is necessary to obtain the set of appropriate variance estimation variables from the HC-036 Pooled Estimation File when pooling involves these panels.
The reference period for Panel 24 Round 5 is longer than the Round 5 reference period for previous panels. The extension of Panel 24 to nine rounds led to the fielding of Round 5 as a cross-year round where respondents were asked to provide information about the reference period between the Round 4 interview in 2020 and the Round 5 interview date in 2021. Thus, the Round 5 reference period generally ended in 2021.[7] In previous panels, the Round 5 reference period ended on or before December 31 during respondents' second year of participation (for example, the Panel 23 Round 5 reference period generally ended on December 31, 2019).
The extension of Round 5 for Panel 24 may affect certain survey administration variables (e.g., PSTATS5), demographic variables (e.g., AGE5X), person-level condition variables, disability days indicator variables, access to care variables, employment variables, and health insurance variables with names ending in 5 or 5X. Variables in these categories may include transitions, events, or information that occurred in 2021. Users should be aware of this distinction when pooling and/or comparing data across panels. Income and tax filing variables, other health insurance variables, and utilization, expenditures, and sources of payment variables are not affected by the Round 5 extension and include data from 2020 only, consistent with previous longitudinal files. Please refer to the documentation for HC-224, the 2020 Full Year Consolidated File, for additional details about variable construction.
[6] Note that variable names for strata and PSU are VARSTR and VARPSU, respectively, in longitudinal files for panel 9 and beyond. These variables were named differently in the longitudinal files for panel 7 (VARSTRP7, VARPSUP7) and panel 8 (VARSTRP8, VARPSUP8) and need to be standardized when pooling with subsequent panels.
[7] The end date of the reference period for a person is prior to the date of the interview if the person was deceased during the round, left the reporting unit (RU), was institutionalized prior to that round's interview, or left the RU to join the military.