"A May survey of 1,000 U.S. adults showed that 39% would consider quitting if their employers weren’t flexible about remote work."
And towards the end it references a tweet that went semi-viral and got a lot of responses.
https://twitter.com/GenieShinobi/status/1389286585347235847
edit: also here's a non-paywall link. https://archive.is/Yc5UW
Maybe they now have remote work options, or having tasted a year without a brutal commute, they take jobs paying less, but closer to their homes.
A may survey of 1000 people reported that 39% would consider quitting if their work didn’t provide flexibility.
I’m no statistician but the red flags are n=1000 and “would consider”. This is a hugely hit button issue right now, great for clicks.
It's been awhile since I've taken stats, but people semi-frequently overestimate the necessary sample size needed for even a 99% confidence level.
Depends on the standard deviation for sure, but some quick napkin math suggests that a sample size of ~700 people is more than enough to draw inferences about the entire western hemisphere at a 99% confidence level.
Reasons for enlarging samples have less to do with accuracy than with resolution. If you plan on looking at specific cross-tabulations or sub-populations, you need a sufficient sample size (typically n>30 for large-sample statistics) to draw inferences.
Error decreases with the square root of sample size. To halve error you must square the sample. A 1,000-element sample has half the error of a 31-element sample. To halve error again would require a 1,000,000 element sample.
"Would consider" is a fair catch, though here the question is how that compares against previous measures / trend.
I've seen very little dismissal of the trend that cannot be traced to commercial real estate, banking, or investment interests. Interestingly enough, all sectors which can themselves utilise remote office or work-from-home arrangements.
Bloomberg are first and foremost an investment information service.
Archiving is a way around many paywalls.
The article itself was short on substance. A bunch of anecdotes without any hard numbers of the amount that are quitting.