« Fantastic visual, but the Google data need some pre-processing | Main | Light entertainment: I am a pen and I object »

Comments

conchis

"A wide range here could mean that ... very few survey responders held that job title."

I don't think this makes sense: more responses will (weakly) increase the range; they can't possibly reduce it.

jlbriggs

@conchis - I don't think that's the point. The point that I take from it is that a wide range could be wide because there are a large number of diverse data points, or it could be wide simply because there are two very different data points - without sample size on the category level, we don't know.

We want to know.

mbab

@conchis @jlbriggs
I believe it's possible that there have been confusion between the range (the obvious minimum and maximum of each category) and a measurement related to standard deviation.
If few people answered, the range can be really wide, and so would the standard deviation be. But with more answers the standard deviation (or any measurement linked to it) can decrease, while as you well said, it cannot reduce the range... (It should really be obvious that adding values between the minimum and the maximum doesn't change said minimum and maximum...)

The comments to this entry are closed.

BOOTCAMP SUMMER '19



Link to Principal Analytics Prep

See our curriculum, instructors. Apply.
Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR.

See my Youtube and Flickr.

Book Blog



Link to junkcharts

Graphics design by Amanda Lee

The Read



Keep in Touch

follow me on Twitter

Residues