Native Hawaiian and Pacific Islander National Health Interview Survey Frequently Asked Questions

Basics

What is the 2014 NHPI NHIS?

The 2014 Native Hawaiian and Pacific Islander National Health Interview Survey (NHPI NHIS) is the first federal survey designed exclusively to measure the health of the civilian noninstitutionalized Native Hawaiian and Pacific Islander population of the United States. It was conducted by the National Center for Health Statistics, which conducts the annual National Health Interview Survey (NHIS).

Is the 2014 NHPI NHIS an oversample within the 2014 NHIS?

No. The 2014 NHPI NHIS was a separate survey, with an entirely separate sample design.

How were the 2014 NHPI NHIS data collected?

The U.S. Census Bureau is the data collection agent for the NHIS.  In order to maintain comparability with the annual NHIS, the procedures for collecting information for the 2014 NHPI NHIS paralleled those of the annual NHIS. Specifically, the data were collected by the Census Bureau’s trained NHIS field interviewers, using the standard 2014 NHIS survey instrument. As in the annual NHIS, the interviews were conducted face-to-face in respondents’ homes, though telephone follow-ups were permitted to complete interviews.

Where can I find more information about the 2014 NHPI NHIS sample and data collection?

For detailed information about the NHPI NHIS survey sample and data collection methods, please see the NHPI NHIS Survey Description document (NCHS, 2017).

Documentation

Where can I find the answers to most of my questions about the 2014 NHPI NHIS?

For detailed information about the NHPI NHIS survey and data sets, please see the NHPI NHIS Survey Description document (NCHS, 2017). Other valuable resources include the ReadMe file and the other documentation accompanying the data release, which can be found here.

How did the 2014 NHPI NHIS survey instrument differ from the 2014 NHIS survey instrument? 

The goal of the NHPI NHIS was to maintain as much consistency as possible with the 2014 NHIS. The instrument used for the NHPI NHIS was thus identical to the 2014 NHIS survey instrument, with the exception of the following two differences:

1. The sample control logic was modified to implement the screening process described in the Sample Design and Allocation section of the NHPI NHIS Survey Description document (NCHS, 2017).
2. Medicare numbers and the last four digits of the Social Security number—data used to link to other Department of Health and Human Services datasets—were not collected because such linking is not permitted under the legislative authority governing the NHPI NHIS.

In all other ways, the instruments were identical. Please note that although the instruments were otherwise identical, the variables available on the public use files are not identical, due to data disclosure prevention requirements.  For more information, see the NHPI NHIS Survey Description document (NCHS, 2017) and the NHPI NHIS documentation.

Where can I get a copy of the 2014 NHPI NHIS questionnaire?

The 2014 NHPI NHIS used the 2014 NHIS questionnaire, with only a couple minor changes. You can find it here:  

Where can I find documentation about the variables that are available on the 2014 NHPI NHIS public use data file?

You can find the 2014 NHPI NHIS data release, including variable summaries, layouts, and frequencies here.

Racial Identity

Do all people in the 2014 NHPI NHIS Person data file have an NHPI racial identity?

No. Of the 11,085 persons in the NHPI NHIS Person data file, 8,697 are NHPI alone or in combination with one or more other races. Of these 8,697 persons, 8,661 persons have a non-zero value for the person weight variable (wtfa). The 36 NHPI persons with a zero value for the wtfa weight variable were on full-time active duty with the armed forces at the time of the interview. These 36 NHPI persons, along with the 2,388 non-NHPI persons, are retained in the person file to enable family-level calculations.

How can I identify which people in the 2014 NHPI NHIS Person data file are NHPI? 

Use the NHPI_ANY variable to identify which people have an NHPI racial identity.

How can I identify which people in the 2014 NHPI NHIS Person data file are NHPI only vs NHPI in combination with one or more other races?

Use the NHPI_ANY variable in combination with the RACERPI2 variable to distinguish persons who are NHPI only and those who are NHPI and one or more other races.

How can I identify what race was chosen as the main race for people in the 2014 NHPI NHIS Person data file who are NHPI in combination with one or more other races?

Use the MRACRPI2 variable to identify the main or primary race named for multiple race people.

How can I identify which people in the 2014 NHPI NHIS Person file are Native Hawaiian? How can I identify which people in the 2014 NHPI NHIS Person file are Samoan, Guamanian/Chamorro, or another detailed Pacific Islander race?

It is not possible to determine detailed NHPI racial identity using the public use data files. To reduce the risk of inadvertent disclosure of confidential information regarding individual respondents, the Disclosure Review Boards of both NCHS and the U.S. Census Bureau restricted all race variables that could be used to disaggregate NHPI persons into detailed NHPI race groups. Therefore, such variables are not available on the NHPI NHIS public use data file. However, over 40 detailed NHPI race variables have been created and are available on the restricted NHPI NHIS data files.

To conduct analyses using variables that could not be released on the public use data file such as detailed race variables, you must apply to use the restricted NHPI NHIS data file. For more information, please visit the Federal Statistic Research Data Center website and the Census Bureau’s “How to Apply Page”.

Geography

Why is there no state variable on the public use 2014 NHPI NHIS data set? 

The risk of inadvertent disclosure of confidential information regarding individual respondents is higher when there exists a publicly released data set having detailed geography variables and a detailed and extensive set of survey observations. For this reason, neither the NHIS nor the NHPI NHIS publicly releases state identifiers or other geographic variables.

To conduct analyses using variables that could not be released on the public use file such as geographic variables, you must apply to use the restricted NHPI NHIS data file. For more information, please visit the Federal Statistic Research Data Center website and the Census Bureau’s “How to Apply Page”.

Variable Detail

The level of detailed provided for a particular variable is not adequate for my analysis. How can I access a more detailed, less aggregated version of that variable?

As is the case for all NHIS data sets, some NHPI NHIS survey variables were suppressed to prevent disclosure of the identity of the survey subjects.  In some cases, multiple variables were collapsed into one variable, while in other cases response categories were collapsed. For example, very extreme values of height and weight are masked by being recoded into broad interval categories.

To conduct analyses using the suppressed variables from the NHPI NHIS, you must apply to use the restricted NHPI NHIS data file. For more information, please visit the Federal Statistic Research Data Center website and the Census Bureau’s “How to Apply Page”.

Linking Data Sets

Can I link the 2014 NHPI NHIS data to other Department of Health and Human Services datasets?

No. Although it is possible to link records from the annual NHIS to other Department of Health and Human Services datasets, such linking is not permitted under the legislative authority governing the NHPI NHIS. For this reason the data needed to conduct this linking (Medicare numbers and the last four digits of the Social Security number), which are collected in the annual NHIS, were not collected in the NHPI NHIS

Can I append the 2014 NHPI NHIS data to the 2014 NHIS data?

It is not appropriate to combine the NHPI NHIS sample with the regular NHIS sample, as the two samples come from different sample designs. For more information about the NHIS area frame-based sample design, see the NHIS Survey Description (NCHS, 2015).  For more information about the ACS frame used as the basis for the NHPI NHIS sample design, see the NHPI NHIS Survey Description (NCHS, 2017).

Comparisons

How can I compare estimates for the U.S. NHPI population calculated using the 2014 NHPI NHIS dataset to estimates for other U.S. race populations calculated using the 2014 NHIS?

First calculate the percentages and standard errors separately for each population using the appropriate analytical dataset. Then use those percentages and standard errors to calculate z-scores.

To calculate the percentages and standard errors, be sure to use the appropriate weights and variance estimation variables, and a statistical software package designed to analyze complex samples. For more information on how to do this, see the Variance Estimation Method for Public Use Data appendix in both the NHPI NHIS Survey Description document (NCHS, 2017) and the 2014 NHIS Survey Description document (NCHS, 2015).

Contact Information

I’ve read this document and the survey documentation and I still have a question. What should I do?

For more information, please e-mail us. Please include “NHPI NHIS” in the email subject line.

References

National Center for Health Statistics. Survey Description, National Health Interview Survey, 2014 [PDF - 1 MB]. Hyattsville, Maryland. 2015. 

National Center for Health Statistics. Survey Description, Native Hawaiian and Pacific Islander National Health Interview Survey, 2014 [PDF - 975 KB]. Hyattsville, Maryland. 2017.