Percentages as Misleading Statistics

This is a technical issue more than a policy issue, but it has some policy implications, in keeping with this website’s slogan. It is prompted by so many recent polls that purport to show that Republicans seem to be backing Trump with no diminution in fervor. Many of these polls are cited by Charles Blow in his op-ed pieces in the New York Times. And today’s Washington Post-ABC poll shows a similar split between Republicans (67% support exiting the climate agreement) and Independents (22%) and Democrats (8%).

My question is, do those statistics reflect no change in Trump support, or is something else going on as well? In particular, is the percentage of people who self-identify as Republicans going down, leaving only the most fervent supporters in those retaining allegiance to the party?

I have a similar question about the data from the Energy Information Administration (EIA) posted by James Wimberly. In the EIA example, the percent of energy use is depicted over time, showing, for example, that hydropower has gone from generating 30 percent of total US electricity in 1950 to six percent in 2016.

Now it may be that some dams were decommissioned over the past sixty-odd years. I would guess, however, that it’s more likely that the total amount of hydropower-generated electricity has not dropped very much, but that its share has dropped because we are using more electricity overall. A better graphic would be one that shows the actual output of each source instead of its share of the total. [And an even better graphic would be one that stacked the contributions one on top of the other, adding up to the total energy usage, which would show the actual contributions rather than the relative contributions.]

Author: Mike Maltz

Michael D. Maltz is Emeritus Professor of Criminal Justice and of Information and Decision Sciences at the University of Illinois at Chicago. He is currently an adjunct professor of sociology at the Ohio State University His formal training is in electrical engineering (BEE, Rensselaer Polytechnic Institute, 1959; MS & PhD Stanford University, 1961, 1963), and he spent seven years in that field. He then joined the National Institute of Law Enforcement and Criminal Justice (now National Institute of Justice), where he became a criminologist of sorts. After three years with NIJ, he spent thirty years at the University of Illinois at Chicago, during which time he was a part-time Visiting Fellow at the US Bureau of Justice Statistics. Maltz is the author of Recidivism, coauthor of Mapping Crime in Its Community Setting, and coeditor of Envisioning Criminology.

8 thoughts on “Percentages as Misleading Statistics”

  1. Huffington Post's Pollster has party-ID graphs. They seem to show that since the election, Republican party ID has been flat, but more people are switching from being self-declared Democrats to being "independent". But if you plot the actual poll numbers, one thing you notice is that there's a gigantic amount of spread in the numbers-I suspect that party ID depends very heavily on polling methodology, and in a few cases, the samples get tweaked to produce some predetermined fraction of Democrats and Republicans (if I recall correctly, one reason Rasmussen's numbers are so weird is that they do this).

  2. (Just eyeballing it, it appears that that happens after every presidential election-the losing party loses party ID share to "independent". Often the winning party does too, but with a delay of several months.)

  3. I used the generating share chart because it was available, if second best. But another chart shows that growth in electricity demand is now negligible, so the shares are a good proxy for volumes. Percentages do become misleading under rapid change - say Tesla's and GM's shares of EV sales. The shares chart correctly identifies the underlying process of substitution.

    I beg to differ on the merits of stacked bar charts versus line graphs for showing trends. The eye cannot easily follow one component of the stack. The impression depends on the order of the components, which line charts avoid.

  4. There has been a large reported widening of the enthusiasm gap - Trumpists are going lukewarm and resisters fiery. Enthusiasm strikes me as an understated factor in polling. Large majorities of Americans accept AGW and the desirability of climate action. But the issue always comes way down in the list of priorities.

    Just possibly, Trump's Paris stunt may have changed the dynamic here, which is sensitive to leadership. Suddenly waving the bloody green flag has become an attractive option to 246 city mayors at last count and 9 state governors led by Jerry Brown. The plutocracy is divided - Musk, Zuckerberg, Immelt are just a few of the defenders of Paris. Pruitt's lies about new coal jobs may turn out costly, as they can be held up next year against grim reality in coal country.

  5. Now a day’s education has become the basic requirement of the life. If you want to have a better future and career you must be educated enough. Our essay writing help left a positive and virtuous mark on all of our readers.

  7. I loved your article post. And I can't wait to explore more of it. Your post is fabulous and I to make sure it gets the credit it deserves.
    Keep up the amazing work!

Comments are closed.