Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one hospital inpatient stay are represented on this data file. In this case, the Full Year Consolidated File, which has data for all sampled persons, must be used to estimate the total number of persons (i.e., those with use and those without use). For example, the proportion of the civilian noninstitutionalized population of the U.S. with at least one hospital inpatient stay of four or more days would be estimated as: (∑ Wi Zi)/(∑Wi) across all unique persons i on the person-level file (6) where Wi is the sampling weight (PERWT04F) for person i and Zi = 1 if NUMNIGHXj GE 4 for any stay of person i = 0 otherwise.
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one other medical expense event are represented on this data file. In this case, the person level file, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with use and those without use). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one other medical expense event for ambulance services received in 1998, the numerator would be derived from data on this event file, and the denominator would be derived from data on the person-level file. That is, (∑ Wi Zi)/(∑Wi) across all unique persons i on the 1998 MEPS Full Year (6) Consolidated Data File where Wi is the sampling weight (WTDPER98) for person i and Zi = 1 if OMTYPEXj = 4 for any other medical expense record of person i. = 0 otherwise.
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one emergency room visit are represented on this data file. In this case a person level file, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with use and those without use). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one emergency room visit where s/he saw a doctor, the numerator would be derived from data on this event file, and the denominator would be derived from data on the person level file. That is, (∑ Wi Zi)/(∑Wi) across all unique persons i on the person level file (6) where Wi is the sampling weight (PERWT99F) for person i and Zi = 1 if SEEDOCj = 1 for any emergency room visit of person i. = 0 otherwise.
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one emergency room visit are represented on this data file. In this case MEPS File HC-011, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with use and those without use). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one emergency room visit where s/he saw a doctor, the numerator would be derived from data on the current file, and the denominator should be derived from data on the MEPS HC-011, the person-level file. That is, (∑ W iZ i ) (∑ W i ) across all unique persons i on the MEPS HC-011 file, (6) where Wi is the sampling weight(WTDPER96) for person i and Zi = 1 if SEEDOCj EQ 1 for any visit of person i on the emergency room visit file = 0 otherwise for all remaining persons on the MEPS HC-011 file. Prior to estimation users will need to correct the 75 records with a missing value for SEEDOC.
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one emergency room visit are represented on this data file. In this case 1997 MEPS Person Level Use and Expenditure File, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with use and those without use). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one emergency room visit where s/he saw a doctor, the numerator would be derived from data on the current file, and the denominator should be derived from data on the 1997 MEPS Person Level Use and Expenditure File. That is, (∑ WiZi ) (∑ Wi ) across all unique persons i on the person level file, (6) where and Wi is the sampling weight(WTDPER97) for person i Zi = 1 if SEEDOCj EQ 1 for any visit of person i on the emergency room visit file = 0 otherwise for all remaining persons on the MEPS HC-020: Person Level Use and Expenditure File.
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one home health provider event are represented on this data file. In this case MEPS File HC-011, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with events and those without events). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one home health event by an independent provider, the numerator would be derived from data on the current file, and the denominator should be derived from data on the MEPS HC-011 person-level file. That is, (∑ W iZ i ) (∑ W i ) across all unique persons i on the MEPS HC-011 file, (6) where and Wi is the sampling weight(WTDPER96) for person i Zi = 1 if SELFAGENj EQ 2 for any events of person i on the home health provider events file = 0 otherwise for all remaining persons on the MEPS HC-011 file. Prior to estimation users will need to take into consideration that 704 records have a missing value for SELFAGEN.
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one hospital inpatient stay are represented on this data file. In this case the person level file, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with use and those without use). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one hospital inpatient stay of four or more days would be estimated as:
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one office-based medical provider visits are represented on this data file. In this case, a 1997 person level file, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with visits and those without visits). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one in person office-based medical provider visit, the numerator would be derived from data on the current file, and the denominator should be derived from data on the 1997 person-level file. That is, (∑ WiZi ) (∑ Wi ) across all unique persons i on the 1997 person-level file, (6) where and Wi is the sampling weight(WTDPER97) for person i Zi = 1 if SEETLKPVj EQ 1 for any visits of person i on the office-based medical provider event-level file = 0 otherwise for all remaining persons on the 1997 person-level file. Prior to estimation users will need to take into consideration that 71 records have a missing value for SEETLKPV.
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one office-based medical provider visits are represented on this data file. In this case MEPS File HC-011, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with visits and those without visits). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one in person office-based medical provider visit, the numerator would be derived from data on the current file, and the denominator should be derived from data on the MEPS HC-011 person-level file. That is, (∑ W iZ i ) (∑ W i ) across all unique persons i on the MEPS HC-011 file, (6) where and Wi is the sampling weight(WTDPER96) for person i Zi = 1 if SEETLKPVj EQ 1 for any visits of person i on the office-based medical provider visits file = 0 otherwise for all remaining persons on the MEPS HC-011 file. Prior to estimation users will need to take into consideration that 149 records have a missing value for SEETLKPV.
Person-Based Ratio Estimates Relative to the Entire Population. If the ratio relates to the entire population, this file cannot be used to calculate the denominator, as only those persons with at least one prescribed medicine event are represented on this data file. In this case the person level file, which has data for all sampled persons, must be used to estimate the total number of persons (i.e. those with use and those without use). For example, to estimate the proportion of civilian non-institutionalized population of the U.S. with at least one prescribed medicine event with RXNDC = “00093310905” (Amoxicillin) in 2000, the numerator would be derived from data on this event file, and the denominator would be derived from data on the person-level file. That is, (∑Wi Zi)/(∑Wi) across all unique persons i on the MEPS HC-050 file (6) where and Wi is the sampling weight (PERWT00F) for person i Zi = 1 if RXNDCj = “00093310905” for any event of person i. = 0 otherwise.
