Generative model | Level 1: Trial | Level 2: Experimental condition | Level 3: Subject-level effects (hyperparameters) | Simulations | Model likelihood | Parameter recovery | Maximum-likelihood estimation (MLE) | RStanTVA-ML: Single participant, single condition | RStanTVA-MLN: Single participant, condition as fixed effect | RStanTVA-MLR: Single participant, single condition, with regularization (priors) | RStanTVA-MLRN: Single participant, condition as fixed effect, with regularization (priors) | RStanTVA-NB: Bayesian non-hierarchical inference | RStanTVA-HB*: Bayesian hierarchical inference | Comparison of MLE and Bayes

What is statistical power? | An easy example: 2-sample t-test | Linear model formulation | Content | Steps of a power analysis | a) Create experimental design (desinr) | ANOVA + LMM: Random effects for subjects only, 1 within-subject factor | ANOVA + LMM: Random effects for subjects only, 2x3 within-subject design | LMM: Crossed random effects for subjects and items | Vary effect size | Based on a previous data set: latin square design | LMM: Crossed random effects for subjects and items - with continuous covariate | Logistic GLMM | Custom probability distributions and link functions

Setup | Experimental Design(s) | Complete within-subject and within-item design; no counterbalancing | Speed within-subject/within-item, Text within-subject/between-item; no counterbalancing | Age between-subject/within-item, Speed within-subject/within-item; no counterbalancing | Age between-subject/within-item, Speed between-subject/within-item; no counterbalancing | Counterbalancing Speed and Load | Outlook | Appendix | Acknowledgement | Packages

Background | Simulated dataset | Example: Treatment contrasts | Example: Sum contrast coding

Background | Creating a hypr object | Using and manipulating hypr objects | Deriving contrasts

Background | Example: Treatment contrasts