http://blog.chron.com/sciguy/2011/09/august-in-houston-was-a-1-in-10000-year-event/August’s heat in Houston was a 1-in-10,000-year event
…
The good thing about data is that it always gives you more than you expect. This data set is no exception to the rule, especially when drilling down to the data for August, with which we are most interested.
If we look at the histogram for the average temperature data for August, then the most apparent feature is the skewness; the cooler averages are clearly slightly more preferred. (The red bars represent the Gaussian distribution expected for the average and standard deviation of the data.)
…
Under most climate models, the monthly average temperature for August in 2100
http://www.ipcc.ch/pdf/assessment-report/ar4/wg1/ar4-wg1-spm.pdf">would be higher than it is now. However, even if we assume that the August monthly average temperature were raised by a full degree Fahrenheit to 84.6°F, the probability of having another August this warm is still only about 1 in 1,000. But if the typical monthly average temperature for August rises to 86.8°F, then this August becomes something that happens a couple of times each century.
…