AEI’s Stan Veuger asks whether the GOP presidential candidates who won’t be allowed into the early debates are being treated unfairly.

Their arguments and those of others who argue for more debaters are basically that poll numbers at this stage are both meaningless and imprecise.
Do they have a point? In these early stages of the campaign, poll numbers are probably to a certain extent driven by candidates’ name recognition from having multiple close relatives who are former presidents, from their past as TV show hosts, or from the outrageous things they say. That said, people like Sen. Marco Rubio and Gov. Scot Walker will easily qualify for the debates based solely on the basis of their political skills, policy proposals and track record in office.

A conundrum.

Dr. Veuger presents a method for answering these criticisms.

Let’s assume that the “true” popularity of each candidate is the average of his results in the last five high-quality national polls. Assume furthermore that poll results are drawn from binomial distributions that we approximate with normal distributions centered on these averages, with standard deviations that are bounded from below by those that apply at the 0.5 percent threshold.
Next, draw five new opinion polls from these distributions a thousand times, average them to produce a thousand different rankings, and count in how many of these the candidates in the true top 10 would get to be on the stage. It turns out that this is the case for 85 percent of these 1,000 simulations. Furthermore, the top five candidates make the debates every single time, and number six through eight fail to make it just once. In addition, the three weakest candidates among the 16 never make the cut. If we decide to draw the line somewhere, this is a reasonable way to do it.

Read his whole essay here.