Skip to main content

Table 2 Bayesian model averaging results for boys and girls

From: Bayesian probabilistic forecasting with large-scale educational trend data: a case study using NAEP

  PIP Post Mean Post SD Cond. Pos. Sign
Boys
 ReadBoyDiff 1.00 0.05 0.01 1.00
 TOTREVdiff 0.21 0.05 0.13 1.00
 PTRatioDiff 0.19 − 0.01 0.03 0.00
 BoysEnrollDiff 0.16 0.01 0.02 1.00
 NSLPLunchDiff 0.12 0.00 0.00 0.87
 FTEdiff2 0.12 − 0.00 0.00 0.37
Girls
 ReadGirlDiff 0.98 0.06 0.02 1.00
 GirlsEnrollDiff 0.72 − 0.09 0.07 0.00
 PTRatioDiff 0.46 − 0.04 0.05 0.00
 TOTREVdiff 0.41 0.16 0.24 1.00
 NSLPLunchDiff 0.13 − 0.00 0.00 0.28
 FTEdiff2 0.13 0.00 0.00 0.95
  1. PIP: Posterior inclusion probability; Post Mean: expected a posteriori estimate; Cond.Pos.Sign: Probability that the sign of the estimate is positive conditional on inclusion in the model