How do you find sufficient data points?

Please check out whether there are sufficient data points when the occupation codes are limited to protective service occupations.

I believe you are referring to the NHIS variable OCCUPN204 (Simple occupational classification (2004 - forward)), please correct me if I am wrong. You can determine if the sample size is adequate for your application by looking at the “Case Count” View" option on the codes tab for OCCUPN204 (select the “Case count view” radio button under “Codes and Frequencies”). In general, there is no rule regarding whether a sample size is “too small to study,” although more is always better. If the sample is too small, the sampling error around estimated statistics will be relatively large, thereby limiting any informative interpretation from the data. One way to increase the sample size of your estimates is to pool multiple samples together (e.g., across years if you are using NHIS data). This will increase the number of observations in your data and the statistical precision but will limit the temporal precision of your analysis. Note that if you do pool together multiple samples you will need to adjust the sampling weights so that they properly account for the combined samples. An approximate way to do this is to divide the sampling weight by the number of samples you are pooling together. As always, we recommend consulting the weights tab for each variable for information on weighting, as well as relevant documentation as part of our user guide.

Thank you so much Grace. If I have any more questions, I will reach out to you.

Yvette Evans

Hi Grace, I need help finding the datasets for OCCUPN204. Psychosocial Occupational Exposures.

Yvette Evans

This tutorial on How to create an extract using NHIS provides helpful guidance on how to access NHIS data. It sounds like you are also asking about the availability of variables for measuring psychosocial occupational exposures. To the best of my knowledge, there are limited variables outlining mental health occupational exposures that overlap with the availability of OCCUPN204 (2004 - 2018). Here are a few NHIS mental health variables relating to working conditions that you might find useful:

WORYWORK - Feelings of worry caused by amount and type of work (available for the 2010 sample)
WORJOBSTOP - Worry or anxiety would stop with more money or better job (available for the 2010 sample)
DEPJOBSTOP - Depression would stop with more money or better job (available for the 2010 sample)

Alternatively, it may be possible to gather the information you need through the American Time Use Survey (ATUS) by combining information about occupation (OCC or OCC2) with well-being activity variables such as SCSTRESS, SCHAPPY, or SCSAD. This tutorial provides guidance on how to create an ATUS extract.

I hope this helps!

Hi Grace,

Thank you so much for the information. I created this data and hope to find the survey or data. I also added a specific code 12 to the occupn 204. This is what I have. Not sure if correct.

Yvette Evans

Means - SDA.pdf (330 KB)

It looks like you are using the online analysis tool rather than creating a data extract for analyzing in a statistical software package. The figure you attached appears to be showing the mean of whether or not the sample adult or sample child needed but could not afford mental healthcare in the past 12 months by family income imputation status. I am sharing a few resources and ideas that may be helpful as you move forward with using these data. First, this sample exercise uses the online tool for IPUMS NHIS data that may be helpful as you navigate how to get the information you are interested in out of the tool. Additionally, you might consider a different program than the means program if you are interested in YBARMENTAL as it is a categorical rather than continuous variable. I am not sure if you are intending to control for family income in your results, but want to highlight that you are using the family income imputation flag rather than a measure of family income. Finally, as YBARMENTAL is included on the sample adult and sample child files, the appropriate weight to use is SAMPWEIGHT (as noted on the weights tab of YBARMENTAL); here is some additional information on the available sampling weights in IPUMS NHIS.