<p>LL = log likelihood (higher is better). MSE = mean squared error (lower is better). The best value in each row is shown in <b>bold</b>.</p
Model fitting statistics and coefficients (R-sq = R square, BIC = Bayesian Information Criterion, SR...
<p>The relative measure of model performance, i.e. the per-bin log-likelihood Δ<i>p</i> (see <a href...
<p>The highest model evidence (bold) and second highest model evidence (italic) models are highligh...
<p>(<i>A</i>) Predictive log-likelihood for each model, on prediction trials, relative to the statio...
<p>Note: vs = versus, -2LL = -2 log likelihood, df = degrees of freedom, <i>p</i> = <i>p</i>-value</...
Columns show different versions of the task. Rows show model fits for (A) the distance model (unscal...
A DDM fits to the rule-based condition for the base model, with no bias terms (dashed lines; note th...
Fig A. Unscaled-Evidence Strength Model: The Distance Model. Fig B. Scaled-Evidence Strength Model: ...
Model log likelihood for each combination of parameters (W, θ) for each participant. Colours represe...
<p>Log likelihoods are quoted relative to that of the saturated model. County-level saturated model ...
Rows represent the datasets in which the given model was best-fitting and each column within a row i...
<p>Lesser values indicate better model fit. According to all criteria the modified Mathews et al. (1...
Rows represent generative models and each column within a row indicates the probability that a datas...
<p>Notes: <i>c</i> - specificity parameter, <i>k</i> -criterion parmeter, <i>w</i> - attention weigh...
<p>Abbreviations: LM, linear model; OR, odds ratio; PLS, partial least squares.</p><p>Sample size fo...
Model fitting statistics and coefficients (R-sq = R square, BIC = Bayesian Information Criterion, SR...
<p>The relative measure of model performance, i.e. the per-bin log-likelihood Δ<i>p</i> (see <a href...
<p>The highest model evidence (bold) and second highest model evidence (italic) models are highligh...
<p>(<i>A</i>) Predictive log-likelihood for each model, on prediction trials, relative to the statio...
<p>Note: vs = versus, -2LL = -2 log likelihood, df = degrees of freedom, <i>p</i> = <i>p</i>-value</...
Columns show different versions of the task. Rows show model fits for (A) the distance model (unscal...
A DDM fits to the rule-based condition for the base model, with no bias terms (dashed lines; note th...
Fig A. Unscaled-Evidence Strength Model: The Distance Model. Fig B. Scaled-Evidence Strength Model: ...
Model log likelihood for each combination of parameters (W, θ) for each participant. Colours represe...
<p>Log likelihoods are quoted relative to that of the saturated model. County-level saturated model ...
Rows represent the datasets in which the given model was best-fitting and each column within a row i...
<p>Lesser values indicate better model fit. According to all criteria the modified Mathews et al. (1...
Rows represent generative models and each column within a row indicates the probability that a datas...
<p>Notes: <i>c</i> - specificity parameter, <i>k</i> -criterion parmeter, <i>w</i> - attention weigh...
<p>Abbreviations: LM, linear model; OR, odds ratio; PLS, partial least squares.</p><p>Sample size fo...
Model fitting statistics and coefficients (R-sq = R square, BIC = Bayesian Information Criterion, SR...
<p>The relative measure of model performance, i.e. the per-bin log-likelihood Δ<i>p</i> (see <a href...
<p>The highest model evidence (bold) and second highest model evidence (italic) models are highligh...
DOI
Add to ORKG