Pollster.com

Articles and Analysis

 

Re: Day-of-Week Effect in Gallup Daily?

Topics: 2008 , Barack Obama , Gallup , Hillary Clinton , Sampling

A quick note to regular readers that I updated my original post on the Gallup Daily tracking below with some second thoughts about the statistical significance of the apparent day-of-week effect. While some pattern may exist, the evidence available is not strong enough rule the role of random chance as an explanation. See "Update 2" in the original post for the details.

One point that is also worth clarifying: Others have read my observations on this and related subjects as evidence of a "flaw" in the Gallup Daily survey or as an argument that we ignore the Gallup Daily data altogether. I would not go that far, though I have been consistent in recommending (here, here and here) that we make less out of the day-to-day variation than we typically do. Any day-of-week effect, for example, would disappear if we compared weekly averages rather than looking for day-to-day change.

Update: Gallup's Jeff Jones responds with data since January broken out by day-of-week.

 

MAP - US, AL, AK, AZ, AR, CA, CO, CT, DE, FL, GA, HI, ID, IL, IN, IA, KS, KY, LA, ME, MD, MA, MI, MN, MS, MO, MT, NE, NV, NH, NJ, NM, NY, NC, ND, OH, OK, OR, PA, RI, SC, SD, TN, TX, UT, VT, VA, WA, WV, WI, WY, PR