Flaws in Polling Data Exposed as U.S. Campaign Season Heats Up

by Steven Yaccino, Robert Hutton & Margaret Talev | Bloomberg  |  published on October 4, 2015

  • Colleen Gill Rotter

    We’d better get it right or we’re in BIG trouble !

  • Pam

    Never, ever put ANY faith in “polling data”.
    1. Samplings are ridiculously small.
    2. You never know, for sure, exactly who was polled. Meaning, is the sample truly representative.
    3. Data are “statistics” and they can ALWAYS be skewed to get the desired result. In polling, it is all about HOW THE QUESTIONS ARE WORDED.

    • PC Bob

      Not only that, but you can design a poll to ‘prove’ anything you want to! It’s been done, far too man y times!

Google Analytics Alternative