Americans’ Beliefs about the Evidence for Global Warming, by Departure of Local Weather from Normal Temperature in Week Prior to Survey. Egan and Mullin, 2009

Local weather’s effect on beliefs that Earth is getting warmer. Figure 3 displays the simple bivariate relationship between temperature and beliefs about the evidence for global warming. Because the dependent variable is dichotomous, a typical scatterplot is inappropriate to display the relationship. To construct the figure, we divided the cases in our dataset into 100 percentiles on the basis of the ddt_week variable and calculated the percentage of respondents in each percentile who agreed that there is solid evidence for global warming. In the figure, the weather percentiles are plotted on the x‐axis and opinion on global warming is plotted on the y‐axis. To summarize the relationship, the figure displays the best linear fit for the data along with a nonparametric smoother drawn with the lowess technique (Cleveland 1993). The figure shows a clear and substantial relationship between the two variables: as local temperatures rise above normal, so does the percentage of Americans believing that global warming is a reality. The smoother consistently traces the regression line, indicating that the relationship between the two variables is close to linear.

Patrick J. Egan, Megan Mullin, How Citizens Integrate Information without Ideological Cues: Local Weather and Americans’ Beliefs about Global Warming, working paper, version April 29, 2009 [pdf] via The Oil Drum