Skip to main content

Wind chill, and its pointlessness

Slate has this very interesting little essay about the "wind chill factor." For those not in the U.S. (or not living in the cold parts of the U.S.), you may not know about our obsession with this number. Typically, the weather report says the temperature is 25F but it "feels like" 10F (32 Fahrenheit is 0 Celsius). The "feels like" is temperature adjusted by the so-called "wind chill factor." It conveys the idea that keeping temperature constant, it feels colder when there is wind. The Slate article covers a bunch of general issues related with inventing metrics: People love large numbers, in this case, because we are measuring cold temperatures, they like really small numbers The name of the metric may have little or nothing to do with what is being measured In seeking to make numbers more palatable to the public, people may choose less precise language that sometimes completely loses the original meaning. For example, "feels like" does not indicate that wind is at issue. Other factors like humidity also affect how cold one feels, at constant temperature. That said, the public is hungry for statistical concepts or metrics that can be explained easily and understood instinctively. There is nothing wrong with this desire. After a metric is established, it's not easy to dislodge it. Changing the metric renders the entire history useless. I also made this point in the chapter on obesity metrics in Numbersense (link). How cold one feels is affected by a system of multiple factors, including temperature, wind, humidity, etc. Any definition of the perceived temperature involves the notion of statistical adjustments For more, read the Slate essay.    

from Big Data, Plainly Spoken (aka Numbers Rule Your World) http://bit.ly/2TiluZr
via IFTTT
Labels:

Comments

Post a Comment

Popular posts from this blog

Controlling legend appearance in ggplot2 with override.aes

[This article was first published on Very statisticious on Very statisticious , and kindly contributed to R-bloggers ]. (You can report issue about the content on this page here ) Want to share your content on R-bloggers? click here if you have a blog, or here if you don't. In ggplot2 , aesthetics and their scale_*() functions change both the plot appearance and the plot legend appearance simultaneously. The override.aes argument in guide_legend() allows the user to change only the legend appearance without affecting the rest of the plot. This is useful for making the legend more readable or for creating certain types of combined legends. In this post I’ll first introduce override.aes with a basic example and then go through three additional plotting scenarios to how other instances where override.aes comes in handy. Table of Contents R packages Introducing override.aes Adding a guides() layer Using the guide argument in scale_*() Changing multiple aesthetic par...
Post a Comment
Read more

Using RStudio and LaTeX

(This article was first published on r – Experimental Behaviour , and kindly contributed to R-bloggers) This post will explain how to integrate RStudio and LaTeX, especially the inclusion of well-formatted tables and nice-looking graphs and figures produced in RStudio and imported to LaTeX. To follow along you will need RStudio, MS Excel and LaTeX. Using tikzdevice to insert R Graphs into LaTeX I am a very visual thinker. If I want to understand a concept I usually and subconsciously try to visualise it. Therefore, more my PhD I tried to transport a lot of empirical insights by means of  visualization . These range from histograms, or violin plots to show distributions, over bargraphs including error bars to compare means, to interaction- or conditional effects of regression models. For quite a while it was very tedious to include such graphs in LaTeX documents. I tried several ways, like saving them as pdf and then including them in LaTeX as pdf, or any other file ...
Post a Comment
Read more