How to Use report() and get AI-Optimized Output | The "last statistical mile" | easystats in the Age of AI | Basic Usage | Setting the Option Globally | Converting a Quarto Document

Purpose | 1. Set package options | 2. Define the treatment text and prompt | 3. Preview the prompt before running | 4. Run the post-only simulation | 5. Inspect the raw output | 6. Summarize by identity | 7. Compare another group to Americans | When to use which function

Purpose | 1. Set package options | 2. Create a small text dataset | 3. Build the prompt | 4. Run the analysis | 5. Inspect the output | 6. Evaluate GPT against human labels | 7. Likert-style sentiment or emotion | 8. Repeated runs for reliability | 9. When to use this workflow | Reference

Step 1: Verify your connection with ellmer | Step 2: Run a minimal nalanda workflow

Purpose | Current package status | What the papers add | Recommended implementation steps | Why these steps matter | Step 1: Prompt layer | Step 2: Condition-based simulation wrapper | Step 3: Descriptive summaries and calibration | Step 4: Demographic profile infrastructure | Step 5: Ensemble controls | Step 6: Cumulative chapter designs | What can be applied directly to the existing chapter workflow? | Transferable immediately | Transferable with design adaptation | Less transferable without stronger validation | Where should calibration happen? | Why not pre-adjust inside simulation functions? | Why not leave calibration entirely to user scripts? | Recommended compromise | Proposed object designs | prompt_bank | ensemble_size | demographic_profiles | Proposed next steps | References

Overview | What the papers did, in simple language | What the supplement adds | 1. Prompting strategy matters | 2. Ensemble prompting matters | 3. Demographic conditioning is part of the method | 4. Absolute effect sizes need caution | Recommended take-aways for users | How this relates to nalanda | A concrete way to use nalanda today | Scenario 1: Pre/post chapter simulations | Scenario 2: Post-only simulations | Scenario 3: Control-versus-treatment chapter comparisons | What users should currently do themselves | 1. Build or manage a prompt bank manually | 2. Run ensembles manually | 3. Manage demographic profiles manually | 4. Estimate between-condition contrasts downstream | 5. Apply effect calibration explicitly | How to think about the 0.56 factor | When it is reasonable to use it | When to be cautious | Best current practice | A simple recommended workflow for users | Minimal workflow | Better workflow | What nalanda may support later | Final practical advice | References

Example 1 (Model syntax 1): | Example 2 (A CFA example): | Example 3 (A SEM example): | Example 4 (Model syntax 2): | Example 4.1 | Example 4.2 | Example 4.3 | Example 4.4 | Example 4.5 | Example 4.6 | Example 5 (Mediation) | Example 6 (Multilevel SEM) | Example 7 (total effects) | Example 8 (intercepts) | Example 9 (thresholds) | Example 10 (longitudinal invariance)

Installation | Supported Objects | Dataframes | Grouped Dataframes | Correlations, t-test, and Wilcox test | Regression models | Linear regression (lm) | anova (aov) | General Linear Models (GLMs) (glm) | Linear Mixed-Effects Models (merMod)

Getting started | Simple moderation: nice_mod | Open (or save) table to Word | Simple slopes: nice_slopes | Special cases | Covariates | Moderations | Simple slopes | Three-way interaction | Complex models: nice_lm | nice_lm | nice_lm_slopes | Thanks for checking in

Basic idea | Getting Started | Categorical Predictors | QQ Plots | Make the basic plot | Further customization | Density Plots | Density + QQ Plots | Outliers | Flagging outliers | Winsorizing outliers | Multivariate outliers | Homoscedasticity (equality of variance) | Make the basic table | Visualizing Variance | Thanks for checking in

Getting started | Save table to Word | Special cases | Student t-test (instead of Welch) | One-sided (instead of two-sided) | One-sample (instead of two-sample) | Paired t test (instead of independent samples) | Multiple comparison corrections | Integrations | broom table | report table | Thanks for checking in

regression | covariance | intercept | latent | constraints | mediation | indirect | user-defined parameters | custom

Basic idea | Getting started | Publication-ready tables | Custom table | Opening/Saving table to Word | Statistical formatting | Highlighting | Integrations | broom table | report table | rempsyc table | t-tests: nice_t_test | Moderations: nice_mod | Custom cell formatting | p-values | r-values | Custom functions | Further editing | Special situation: multilevel headers | Multilevel heading, with formatting | Thanks for checking in

Basic Idea | Getting started | Using nice_contrasts() | Make it publication-ready using nice_table(). | Make a violin plot comparing groups through nice_violin(). | Full Workflow | Make violin plots comparing groups through nice_violin. | Thanks for checking in

Basic idea | Getting started | Customization | Change x- and y- axis labels | Have points "jittered" | Change the transparency of the points | Remove points | Add confidence band | Set x- and y- scales manually | Change plot colour | Add correlation coefficient to plot and p-value | Change location of correlation coefficient or p-value | Plot by group | Use full range on the slope/confidence band | Change order of labels on the legend | Change legend labels | Add a title to legend | Plot by group + manually specify colours | Plot by group + use different line types for each group | Plot by group + use different point shapes for each group | Plot by group, point shapes, line types, legend + no colours (black and white) | Putting it all together | Special situation: Add group average | Black line + coloured lines | Black line, coloured dots | Thanks for checking in

Getting started | Save a high-resolution image file to specified directory | Customization | Change x- and y- axes labels | See difference between two groups | See difference between two other groups | Compare all three groups | Include effect size (Cohen's d) | Set the colours manually | Changing the names of the x-axis labels | Removing the x-axis or y-axis titles | Removing the x-axis or y-axis labels (for whatever purpose) | Set y-scale manually | With x number of groups | Plotting individual observations | Micro-Customizations | Bootstrapping | Putting it all together | Special situation: Add other plot elements | Thanks for checking in

What should I cite? | 1. Cite the main/important packages in the manuscript | 2. Present everything in Supplementary Materials | Where | cite_easystats()

Getting started with correlations | t-tests, ... | ANOVAs | Linear Models

1. Open an Issue on GitHub | 2. Use template file