Stories
Slash Boxes
Comments

SoylentNews is people

posted by martyb on Sunday July 30 2017, @06:41AM   Printer-friendly
from the Lies,-Damned-Lies,-and-Statistics dept.

"In what has become a running joke amongst those skeptical of the claim that minimum wage increases have no effect on unemployment, a recent report by the Employment Policies Institute showed that 174 of the 184 co-sponsors of a bill to raise the federal minimum wage to $15 an hour hired unpaid interns."

"In a review of over 100 studies, economists David Neumark and William Wascher found that,A sizable majority of the studies surveyed ... give a relatively consistent (although not always statistically significant) indication of negative employment effects of minimum wages. In addition, among the papers we view as providing the most credible evidence, almost all point to negative employment effects, both for the United States as well as for many other countries." http://www.nber.org/papers/w12663.pdf

"Yes, minimum wages still do increase unemployment."

https://mises.org/blog/seattles-minimum-wage-supporters-ignore-facts


Original Submission

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 0) by Anonymous Coward on Sunday July 30 2017, @01:24PM

    by Anonymous Coward on Sunday July 30 2017, @01:24PM (#546667)

    Statistical signficance is based on an arbitrary threshold. Meta-analysis can be performed with statistcally insignificant or signficant results or any combination thereof. There are many examples, where meta-analysis allows to accrue enough statistical power when individual studies weren't, thus: overall significance but not individually per study.
    Also when the the larger studies show larger effects, that is rather worrysome and not a sign that 'something is going on'. Effect sizes of smaller studies should be larger as sampling variation is bigger. As it is, I would be worried about biased studies.