These are my recent Pin​board​.in links:

• Attrac­tive Mod­els — Kieran Healy

  “Now, if you write a paper describ­ing neg­a­tive results—a model where noth­ing is significant—then you may have a hard time get­ting it pub­lished. In the absence of some spe­cific con­tro­versy, neg­a­tive results are bor­ing. For the same rea­son, though, if your results just barely cross the thresh­old of con­ven­tional sig­nif­i­cance, they may stand a dis­pro­por­tion­ately bet­ter chance of get­ting pub­lished than an oth­er­wise quite sim­i­lar paper where the results just failed to make the thresh­old. And this is what the graph above shows, for papers pub­lished in the Amer­i­can Polit­i­cal Sci­ence Review. It’s a his­togram of p-​​values for coef­fi­cients in regres­sions reported in the jour­nal. The dashed line is the con­ven­tional thresh­old for sig­nif­i­cance. The tall red bar to the right of the dashed line is the num­ber of coef­fi­cients that just made it over the thresh­old, while the short red bar is the num­ber of coef­fi­cients that just failed to do so. If there were no bias in the pub­li­ca­tion process, the shape of the his­togram would approx­i­mate the right-​​hand side of a bell curve. The gap between the big and the small red bars is a con­se­quence of two things: the unwill­ing­ness of jour­nals to report neg­a­tive results, and the efforts of authors to search for (and write up) results that cross the con­ven­tional threshold.”
  
  sta­tis­tics academic-​​culture pub­lish­ing meta-​​analysis