This column is brought to you by the Department of I Can’t Believe We’re Still Having This Argument.

As you know, the state’s political-media-good-government elite has long argued that the top-two primary was going to have a moderating effect. Indeed, this has become more than argument, it has become an article of faith. I speak from personal experience when I say it’s hard to argue against religion.

In the past month, I’ve had phone calls from reporters for two of our nation’s most prominent newspapers, top-notch journalists who were writing stories with possible lines that the top-two primary has been a factor in changing the state’s politics. I presented the evidence to both; so far, it hasn’t made any difference.

So I’m done arguing. On the theory that whatever the right people believe in the media and in the academy think must be true is true, my answer to these questions will be: whatever.

For that tiny minority of Californians interested in actual evidence and reality (a group that, when it manages to engage in political debate, will, of course, be dismissed as unrealistic, the favored insult of the right people), I will refer you to the most thorough study of the subject I’ve ever encountered.

The study is called “A Primary Cause of Partisanship? Nomination Systems and Legislator Ideology,” and is being published in the American Journal of Political Science. A link to it is here.

It looked at data on state legislators across the states, for the period 1992 through 2010, and looks at all kinds of primary systems. And its conclusions: “The results of this analysis suggest that the openness of a primary election system has little to no effect on the ideological positions of the politicians it elects… The overall polarization is roughly the same across systems… An approach that gives open primaries as much credit as possible fails to confirm a simple moderating effect… The results suggest that these systems have little consistent effect on legislator ideology.”

And then: “Our analysis suggests we should expect little from open primary reform in the modern political age. The effect is inconsistent and weak, and where it is stronger and more robust, it is the opposite of the one that is generally intended.”

This isn’t a surprise. Previous studies focused on particular states have found the same thing.

Will this change the media-good government story line? Not a chance. Some people will seize on the “little” in “little if any” effect and persist in believing that the Easter Bunny exists, and that he will be a moderating force on the Democratic party if he can just pick up that Senate seat in Ventura. Among the Bunny’s first acts will presumably to permit limited genetic engineering so that bipartisanship can grow on trees.

But Californians who care about evidence can now safely stop reading when this subject comes up in the future.