You are using an unsupported browser. Please update your browser to the latest version on or before July 31, 2020.
close
You are viewing the article in preview mode. It is not live at the moment.
Home > RAW > Support > RAW Data FAQs > Non Farm Payroll Methodology
Non Farm Payroll Methodology
print icon

In this article, you will read how to build your own NFP forecast with LinkUp data. Please be aware that because of drift, the NFP forecast may not be an exact match.

 

The model that is used for the blog is taking an active percent change, and our created percent change, blending those 2 numbers together evenly to get a blended average. This blended average is then used to look up the value that should be applied to the previous month's released BLS NFP number.

 

If the duration is above 47 days for that month, we will use the previous month's blended average for the lookup value. As such this model is based on the initial BLS data points, not the revised series. Below Is the table that is used to determine the amount to be added or subtracted from the prior month's BLS released number.

 

It should be noted that if you try to historically recreate these values they will not match exactly with what is found in the historical_NFP_forecasts.csv. This is due to our active values changing over time. Active values can increase as we move through time due to job postings being reposted after they were deleted, we refer to this as drift. This can cause differences between what was released on the blog, and what the same methodology will produce today. Additionally, the model that is used for our blog is run manually, and manual adjustments are made to that model, which can also account for differences.

 

Feedback
0 out of 0 found this helpful

scroll to top icon