Types of functions | Built-in simulation experiments | User-defined simulation experiments | Types of power analyses to evaluate | Prospective/post-hoc power analysis | Compromise power analysis | A priori power analysis | Sensitivity power analysis | Criterion power analysis | Multiple power evaluation functions | SpowerBatch() | SpowerCurve()

Correlation | Example 3.3; Difference from constant (one sample case) | Test against constant $\rho_0=0$ | Example 27.3; Correlation - inequality of two independent Pearson r's | Example 28.3.1; Correlation - inequality of two dependent Pearson r's (no common index) | Example 28.3.2; Correlation - inequality of two dependent Pearson r's (common index) | Example 28.3.3; sensitivity analysis | Example 16.3; Point-biserial correlation | Example 31.3; tetrachoric correlation | Proportions | Example 4.3; One sample proportion tests | Example 22.1; Wilcoxon signed-rank test | Laplace($\mu$, 1) version | Example 5.3; Two dependent proportions test (McNemar's test) | Multiple Linear Regression (Fixed IVs) | Example 13.1 | Example 14.3 | Example 14.3b | Multiple Linear Regression (Random IVs) | Example 7.3 | Simple linear regression | Example 12.3 | Fixed effects ANOVA - One way (F-test) | Example 10.3 | $t$-test: Linear regression (two groups) | Example 17.3 and 18.3 | Variance tests | Example 26.3; Difference from constant (one sample case) | Example 15.3; Two-sample variance test | t-tests | Example 19.3; Paired samples t-test | Example 20.3; One-sample t-test | Wilcoxon tests | Example 22.3; One-sample test with normal distribution | Two-sample test with Laplace distributions | Example 23.3: Paired-samples test with Laplace distributions

Type S errors via simulation | Manual specification | Implementation using built-in p_t.test() function | Type M errors via simulation

Logical returns | Confidence (and credible) intervals | Using previouls defined simulation code | Precision criterion | Bayes Factors | Bayesian power analysis via posterior probabiltes | Regions of practical equivalence (ROPEs) | Equivalence testing | Bayesian approach to ROPEs (HDI + ROPE)

(Potential Prerequisite) Converting warnings to errors explicitly via manageWarnings() | Error Managing Workflow | Define the functions | Run the simulation | What to do? | Explicit debugging | Manual debugging via try() | Extracting error seeds for hard-to-find bugs

Introduction | Local parallel computing | Network computing | Using the future framework

A general overview | Simulation: Determine estimator efficiency | Define the conditions | Define the functions | Putting it all together | Interpreting the results | Conceptual walk-through of what runSimulation() is doing

Including fixed objects | Scoping | Exporting functions for parallel computing | Exporting third-party libraries | Exporting user-defined functions | Exporting objects in SimDesign

Introduction | Standard setup on HPC cluster | Example | Limitations | Array jobs | Converting runSimulation() workflow to one for runArraySimulation() | Expand the standard simulation design object for each array ID | Construct and record proper random seeds | Extract array ID information from the .slurm script | Organize information for runArraySimulation() | Putting it all together | Post-evaluation: Combine the files | Array jobs and multicore computing simultaneously | Extra information (FAQs) | Helpful Slurm commands | My HPC cluster excution time is limited and terminates before the simulation is complete | Uploading array jobs related to previous array submissions | Create new conditions for missing replications, and use rbindDesign() | Submit the new job, evaluating only the new conditions

Option: save = TRUE (Default is TRUE) | store_results (TRUE by default) | Option: save_results = TRUE (FALSE by default; set to TRUE if RAM is an issue) | Recommendations

Description of structure | An example | AnalyseIf() | Applying one analyse function per-condition

mirtCAT Vignette Files

mirt Vignette Files