The Excel sheet's knower-level inference closely matches fully Bayesian inference, with no discrepancies in posterior maxima¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2011 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2014: tool and model accuracy changes quickly

Subclaims¶

q2 i? On an independent data set of 56 children, the Excel approximation's posterior over knower levels differs from the full Bayesian posterior by a mean absolute difference of 0.2%, with no discrepancies in maxima. → Negen 2011

Evidence¶

Negen 2011¶

Negen, J., Sarnecka, B. W., & Lee, M. D. (2011). An Excel sheet for inferring children's number-knower levels from give-N data. Behavior Research Methods. https://doi.org/10.3758/s13428-011-0134-4

q2 · i? · design · r2

Comparison of the Excel approximation with fully Bayesian (Markov chain Monte Carlo) inference on the 56-child data set from Lee and Sarnecka. The article reports "The mean absolute difference" of 0.2% (SD 0.68%) and a largest absolute difference of 4.8%, with identical posterior maxima.

"The Excel sheet's inference is very close to the inference generated by fully Bayesian inference. In terms of maxima, there are no discrepancies. The mean absolute difference between the model's posterior over knower levels and the Excel sheet's approximate posterior is 0.2%, with a standard deviation of 0.68%."

Discussion¶

Related Claims¶

• Fully Bayesian inference on the calibration data set assigned 423 sessions across six knower levels and estimated an evidence value v of 16.94 — related
• The Excel sheet's knower-level estimates agree with a 2:1 heuristic on 38 of 56 children and are more lenient for larger set sizes — related
• Analyzing Give-N data by knower-level yields greater statistical power than analyzing by percent correct, plausibly explaining the discrepancy with Ansari et al. (2003). — related