It’s not the heat, it’s the heat index

August 15, 2018

(This article was first published on R – Decision Science News, and kindly contributed to R-bloggers)


Click to enlarge

(We got a request for a Celsius version of this post and since we are a full service website we created one and put it here).

So, we were wondering, what’s this heat index we hear about? We went to the Wikipedia article on it. It is an index that combines air temperature and relative humidity to convert a (hot) temperature into something like perceived temperature, how hot it feels. It formalizes the adage “it’s not the heat, it’s the humidity.”

The equation to get heat index from temperature and relative humidity is big:

Click to enlarge

This heat index chart is also complicated, but it allows one to look up the heat index rather easily.

Click to enlarge

We wanted a better way to see what the heat index is doing. So we made this plot:

Click to enlarge

When it’s 90 degrees outside with 90% relative humidity, it feels 30 degrees hotter. That’s a lot of degrees.

It turns out there is another heat index formula. This one’s even more complicated.

Click to enlarge

We wanted to see how it compared to the first, so we plotted both together:

Click to enlarge

We like averaging, so we plotted the average of the two outputs:

Click to enlarge

We thought it looks not so far from linear so we fit a regression model to the average and plotted that:

Click to enlarge

Then we couldn’t resist coming up with a simple heuristic (shown in dots):

Click to enlarge

The heuristic comes pretty close to the regression model.

Click to enlarge

The error (mean absolute deviation) of the heuristic to the average model is about 3 degrees. The error of the regression model to the average model is about 2 degrees, so it’s not bad, considering that the two different heat index formulae can differ by over 5 degrees.

So what’s the heuristic?

  • Relative Humidity of 50%: Add 10 degrees for every 10 degrees above 80
  • Relative Humidity of 70%: Add 20 degrees for every 10 degrees above 80
  • Relative Humidity of 90%: Add 30 degrees for every 10 degrees above 80 + 5

It’s quite a bit simpler than the 9 and 16 term equations above and should be good enough for everyday use.

For those who want it

The post It’s not the heat, it’s the heat index appeared first on Decision Science News.

To leave a comment for the author, please follow the link and comment on their blog: R – Decision Science News. offers daily e-mail updates about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...

If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.

Search R-bloggers


Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)