Data | Fit | Profiles | Starting probabilities | Transitions | Sequences | Classification | Transition networks | Beyond homogeneous transitions | Assumptions

Data | Clustering within groups | Fit | Profiles | Group classes | Class sizes | Classification | Recovery of the known structure | Reference | Sampling weights | All tables | Assumptions

What the package supports | Data | Fitting the model | Mixed indicators | Ordinal and count indicators | Reference | Assumptions

Data | Fit | Profiles | Starting probabilities | Transitions | Sequences | Classification | Transition networks | Beyond homogeneous transitions | Assumptions

Data | Clustering within groups | Fit | Profiles | Group classes | Class sizes | Classification | Recovery of the known structure | Reference | Sampling weights | All tables | Assumptions

What the package supports | Data | Fitting the model | Mixed indicators | Ordinal and count indicators | Reference | Assumptions

Data | Fitting the candidate models | The table of candidates | Information criteria | Change with each added class | Classification quality | Checks of the estimation | Comparing candidates | Analysis of the chosen candidate | Functions

Linear regression | Batches | Seeds | Variables as distributions | Missing data | Treatment assignment | Group designs | Correlation structures | Non-normal margins with a Gaussian copula | Ordinal variables | Common factors | Item response theory | Latent profiles | Latent classes | Two-level latent profiles | Random intercepts | Growth curves | Vector autoregression | Proportional hazards | Competing risks | Sequences of states | Hidden Markov models | Groups, mixtures and behavioral data | Transition network analysis | Random graphs and blocks | Preferential attachment and small worlds | Temporal, bipartite and multiplex networks | Simulation functions

Why this tutorial | The corpus, deduplicated | Choosing the number of topics | Should you trust these topics? | Size on two scales | Two keyword views, one topic | The topics at a glance | Where to go from here

Data | Hypergraphs from observed groups | Frequent sets | Hypergraphs from sequences | Projection to a network | Node measures | Centrality | Communities and clusters | Null models | Other higher-order structures

Linear regression | Batches | Seeds | Variables as distributions | Missing data | Treatment assignment | Group designs | Correlation structures | Non-normal margins with a Gaussian copula | Ordinal variables | Common factors | Item response theory | Latent profiles | Latent classes | Two-level latent profiles | Random intercepts | Growth curves | Vector autoregression | Proportional hazards | Competing risks | Sequences of states | Hidden Markov models | Groups, mixtures and behavioral data | Transition network analysis | Random graphs and blocks | Preferential attachment and small worlds | Temporal, bipartite and multiplex networks | Simulation functions

Why cograph | Plotting | Specialized plots | Input formats | Wrangling | Selecting | Weights | Structure and editing | Centrality | Network properties | Community detection | Motifs | Robustness | Disparity filter | Multi-cluster visualization | Multilayer networks | Higher-order networks | TNA integration | Palettes | Further reading

How to read this catalogue | Notation | Catalogue index | Argument catalogue

Introduction | Installation and Loading | Package Overview | API Design | 1. Group Comparisons | Example: Treatment Effect Analysis | Advanced Features | Multiple Stratification Variables | Filtering Specific Levels | Post-hoc Comparison Table | Nonparametric Tests | Key Features | 2. Correlation Matrix | 3. Full Correlation Tables | Basic Usage | Stratified Correlations by Group | Multilevel Correlations | 4. Data Transformation | Mean Centering | Z-Score Standardization | Scaling | Reverse Coding | 5. Descriptive Statistics | 6. Categorical Frequency Tables | 7. Missing Data Analysis | Comprehensive Analysis | Imputation | 8. Latent Profile Clustering | 9. Categorical Variable Analysis | 10. Network Estimation | Best Practices | Data Preparation | Parameter Selection | Interpretation | Getting Help | Conclusion

The four input formats | Interval data | Contact data | Threaded data | Co-presence data | Choosing the format | Inspecting the network | Direction, loops, weights and attributes | Sessions | Observation windows | Vertex activity spells | Editing a network | Descriptive measures | Collapsing to a static network | References

Data | Constructing the temporal network | Visualisation | Structure over time | Participants | Reachability | Mixing between experience levels | Interpretation | Limitations | References

Data | Building the network | Measuring in windows | Daily density | Rolling weekly density | Vertex trajectories | Daily degree | Temporal centrality | Time-respecting paths | Routes | Tie dynamics | Next steps

The author | Pages that are already rendered | Any page at all | The reader

Introduction | Data | Transition Network Analysis | Transition probabilities with ts_tna() | Transition frequencies with ts_ftna() | State co-occurrence with ts_cna() | Attention-weighted transitions with ts_atna() | Indexing the model with series_networks() | Local direction with trend() | Visibility with vg() | Window similarity with tsn()

Introduction | Data | Discrete-state plots | Overlay | Ribbon | Heatmap | Stack | Local-direction plots | Points | Panels | Constructed-network plots | Network | Source series | Weighted distance network | Adjusting the network encoding | Transition Network Analysis plots | Combined | Extracted-model plots | Selecting a plot

Introduction | From measurements to a model | The bridge: this object is a Nestimate model | Four constructors, one interface | One series, and what it can support | Choosing states that mean something | One network per person | Describing the model | Centrality | How much of the sequence is structure, and how much is noise | Pruning | Bootstrap: which edges survive resampling? | Stability: would the same states rank first in a smaller study? | Markov order: is a first-order model enough? | Comparing two periods | More than two groups: one model per condition | Plotting a model | Where the line falls

The question | One call, one network per condition | Why not subset the data and build each model by hand? | First failure: the subset welds broken time back together | Second failure: each subset learns its own thresholds | The collection is data | Composition and dynamics | Composition | Mean first passage times | Entropy and centrality | Drawing the networks | Are the differences real? | The permutation test | The metric panel | Bootstrap and Bayesian certainty per group | Is first order enough, per group? | Stability under case dropping | Pruning the collection | What to watch for | When to use which | References

One object, two packages | Reading the model as data | Where the process spends its time | Which states and edges carry the structure? | How the process moves | Mean first passage times | Persistence, return, and sojourn | Is the chain well-behaved? | How predictable is the process? | Does history beyond one step matter? | Simplifying the model | How sure are we about the estimates? | Sequence bootstrap | Bayesian edge certainty | Whole-network statistics: the vertex bootstrap | Case dropping, in two flavours | Split-half reliability | Comparing two models | The difference itself | Four more verdicts on the same pair | Link prediction | Grouped models | What does not apply, and why | The compatibility map | References

1. Why flows need their own view | 2. Aggregated flows: the alluvial | 3. Individual flows: one line per student | 4. Flows inside a single trajectory | 5. Controlling colour, bundling, and layout | 6. The transition network: movement collapsed over time | Sequences and network side by side | Where flow plots fit

Using your own data | One call | Evaluate the clustering | Tidy fit indices | Name groups after inspecting them | The same analysis in four explicit steps | State plots | Sequence and trajectory plots | Compare candidates in full detail

1. The complete analysis in one call | 2. Choosing and defending the number of states | 3. Understanding what the states are | 4. Sequences: how states unfold over time | 5. Trajectories: groups of similar journeys | 6. Describing what the trajectories mean | 7. Relabeling without refitting | 8. Full control: explicit steps and grid comparisons

Drawing a fitted network | The data and the fit | The default graph | Layouts | Nodes and labels | Edges | Bootstrap diagnostics | Themes | Group networks | Export | The splot arguments at a glance

Data and preprocessing | Fitting the model | Reading the output | Visualizing the network | References

Data and preprocessing | Fitting the model | Reading the output | Visualizing the network | References

Data and preprocessing | Fitting the model | Reading the output | Visualizing the network | References

Design principles | Method coverage | Worked validation surface | Validation boundaries | Visualization | Caveats | References

The entropy of a transition network | Which states are decision points? | The entropy network | Entropy over time | Bayesian estimation | When to use which | References

The modelling problem | Method selection | Data and preprocessing | Worked selection example | Caveats | References

The data | Running preprocess and reading the diagnostics | What the flags mean | Cleaning non-stationary series with detrend | References

Data and preprocessing | Fitting the model | Reading the output | Visualizing the network | References

Data | 1. Genre co-occurrence (delimited field) | Comparing similarity measures | Which similarity to use? | 2. Counting methods | 3. Scaling | 4. Filtering | 5. Actor co-occurrence (long/bipartite format) | 6. Splitting by groups | 7. Output formats | Gephi | cograph (with Gephi layout) | igraph | Matrix | 8. Converters | 9. Six input formats, one result | 10. Complete pipeline | References

Introduction | Data | Dissimilarity-based Clustering | Visualizing Clusters | Distance Metrics | Clustering Methods | Choosing k, dissimilarity, and method | Validating the choice with cluster_diagnostics() | Mixture Markov Models | Building Networks per Cluster | From build_clusters() to per-cluster networks | Shortcut: cluster_network() (distance-based) | Fitted MMM clustering and its networks | Comparing Clusters | Workflow Summary

Setup | Form 1 — Named list of per-actor frames | Form 2 — Single combined frame with actor_type | Form 3 — Single combined frame with node_groups | 3a. Named list of code vectors | 3b. Two-column data frame (codebook) | All forms produce the same network | Handling code-label collisions with disambiguate = | Splitting into cohorts with group = | Cheat sheet

What a Gaussian graphical model is | The data | Fitting the network with psychnet() | Inspecting edges with summary() | Checking numerical optimality with certificate() | Describing node position with net_centralities() | Quantifying node predictability with net_predict() | Visualizing the fitted network with cograph::splot() | Sensitivity to the correlation estimator | Applying a substantive edge threshold | A nonparanormal sensitivity model | Reporting the analysis | Why the model removes weak connections | Mathematical foundations | Precision matrix and conditional independence | Penalized likelihood | EBIC model selection | KKT optimality conditions | Predictability from the precision matrix

What an Ising network is | The data | Fitting the network with psychnet() | Inspecting interactions with summary() | Checking numerical optimality with certificate() | Describing node position with net_centralities() | Evaluating binary predictability with net_predict() | Comparing an unregularized Ising estimator | Visualizing the network with cograph::splot() | Reporting the analysis | How the Ising network is estimated | Mathematical foundations

Using the Dynalytics event-data grammar | What a network from event data represents | The event log | Estimating one actor-level network with psychnet() | Inspecting actor-level edges with summary() | Checking numerical optimality with certificate() | Visualizing the actor-level network | Estimating one network per achievement level | Estimating a person-centered session network | Keeping the within- and between-actor networks | Reporting the analysis | How event counts and levels are constructed

What stepwise model selection does | The data | Fitting the network with psychnet() | Inspecting the selected edges with summary() | Checking the fitted solution with certificate() | Comparing the selected model with the graphical lasso | Describing node position with net_centralities() | Quantifying node predictability with net_predict() | Visualizing the network with cograph::splot() | Sensitivity to rank correlations | Reporting the analysis | How stepwise selection works | Mathematical foundations | Gaussian graphical model | Information criterion | Constrained maximum-likelihood certificate | Predictability

What an information-filtering network is | The data | Building the correlation backbone with psychnet() | Inspecting the TMFG edges with summary() | Estimating conditional associations with LoGo | Checking the TMFG structure with certificate() | Checking the LoGo solution with certificate() | Describing node position with net_centralities() | Quantifying node predictability with net_predict() | Visualizing the conditional network with cograph::splot() | Sensitivity to rank correlations | Reporting the analysis | How information filtering works | Mathematical foundations | TMFG edge count | LoGo precision matrix | Numerical certificate | Predictability

What a mixed graphical model is | The data | Fitting the network with psychnet() | Inspecting mixed edges with summary() | Checking numerical optimality with certificate() | Describing node position with net_centralities() | Evaluating predictability with net_predict() | Sensitivity to the edge-combination rule | Visualizing the network with cograph::splot() | Reporting the analysis | How the mixed network is estimated | Mathematical foundations

What a relative-importance network is | The data | Fitting the network with psychnet() | Inspecting directed contributions with summary() | Checking the decomposition with certificate() | Reading incoming explanation with net_predict() | Reading outgoing contribution with net_centralities() | Visualizing direction with cograph::splot() | Sensitivity to rank correlations | Reporting the analysis | How relative importance is computed | Mathematical foundations

Define the sequence data | Fit the model | Read the fitted transitions | Visualise the fitted model | Add uncertainty evidence | Start from a raw event log | Fit groups | Compare groups | In short

A specific transition: edge-level uncertainty | A significant transition: robustness to information loss | The whole network: structural reliability | More than chance: an assumption-free null | Two groups: inference under exchangeability | In short

Fit a model | Read the result | Plot the model | Check uncertainty | Where next

Same grammar as TNA | Wide sequence data | Long event logs | tna objects | Nestimate objects | Back to tna

Summary | The method | What the package provides | Fitting and reading a model | Visualisation | Group comparison | Confirmatory battery | Interoperability | Bundled data

The data and the fitted model | Reading the model | The network | Inference | Summary

Residual heatmap | Residual network | Transition network (a TNA model) | Chord and sunburst | Uncertainty forests | Group comparison | Grouped fits | The worker functions | In short

Overview | Workflow 1: Basic TNA Analysis | Step 1: Simulate Data | Step 2: Fit TNA Model | Step 3: Extract Components | Step 4: Visualize | Workflow 2: Comparing Model Types | Fit Multiple Models | Compare Models | Workflow 3: Network Comparison | Using compare_networks() | Using compare_centralities() | Using compare_edge_recovery() | Workflow 4: Batch Processing | Fitting Multiple Models | Applying Functions to Multiple Models | Comparing to Reference | Workflow 5: Grid Simulations | Create Parameter Grid | Run Grid Simulation | Analyze Results | Workflow 6: Summarizing Results | Simulation Summary | Network Summary | Data Format Conversions | Wide to Long | Long to Wide | Prepare for TNA Package | Complete Example: Recovery Study | Tips for Effective Workflows | Summary

1. Building a heterogeneous network | 2. Plotting the network | 3. Per-actor sequence plots | 4. Centralities | 5. Bootstrap | 6. Centrality stability | 7. Split-half reliability | 8. Comparing two networks | 9. Permutation test | 10. Path patterns

Why attention weighting | The four profiles | A worked example | Attention is a deliberate choice, not a default | Where attention applies | How it works | References

1. Introduction and the standard schema | 2. Custom data and separators | Custom CSV — map columns by name | Custom columns and separators (no reader needed) | The document identifier | A separate separator for references | Quoted values | A safety net for the wrong delimiter | 3. read_biblio() | 4. Scopus | 5. Web of Science | 6. Dimensions | 7. Lens.org | 8. BibTeX & RIS | 9. Crossref via rcrossref | 10. OpenAlex — two paths | Path A: flat CSV | Path B: in-memory tibble from openalexR | 11. Building data manually | 12. The split_field() helper | 13. Combining data from multiple sources | 14. Inspecting and sanity-checking | 15. Troubleshooting | Further reading

Introduction | Data import | Network builders | Weighting and aggregation | Implementation | Export formats | Output | Quick start | Reading your own data | Scholarly exports | A custom CSV | A plain data frame, directly | The standard schema | Datasets used here | Author collaboration | Counting methods | Attention weights | Reference co-citation | Document coupling and citation | Keyword co-occurrence | Countries, institutions, and sources | Generic co-networks | Normalization | Reducing large networks | Temporal networks | Local citations and historiographs | Author-name normalization | Exporting | Reading a bibnets_network | References

1. Fit | 2. Inspect the fit | 3. The pathway tables | 4. Prune to the reliable tree | 5. Predict | 6. A first tree plot | 7. Trajectory trees: where sequences go, and how predictably | By frequency -- how many sequences walk each path | By predictability -- how confidently the model calls each step | Where to go next

The shared dataset | Route A -- a state-sequence (stslist) object | Route B -- a tna transition-network object | Route C -- a Nestimate network object | They agree | The boundary: sequences, never aggregated transitions | Group objects

1. The data | 2. Fit | 3. Inspect | 4. The pathway tables | 5. Per-context diagnostics | 6. Prune to the reliable tree | 7. Held-out predictive quality | 8. Bootstrap reliability | 9. Do high and low achievers regulate differently? | Synthesis

Setup | 1. Smoothing schemes | 2. Pruning criteria | 3. Cross-validated tuning | 4. Bootstrap pathway reliability | 5. Comparing two cohorts | 6. Tree introspection | 7. Mining contexts and sequences | 8. Imputing gaps | 9. Generating sequences

Setup | 1. The fitted tree, four ways | Horizontal phylogram (default) | Radial dendrogram | Icicle / sunburst (needs ggraph + tidygraph) | Interactive collapsible tree (needs visNetwork) | 2. Pathway-centric plots | Next-state heatmap | Divergence lollipop | Per-context distributions | 3. Diagnostic plots | How much memory does one pathway need? | Predictive quality | 4. Forward trajectory trees (needs ggforce) | 5. Inferential plots | Bootstrap forest plot | Per-pathway resample distributions | Cohort comparison: permutation null | Tuning surface | Group difference map | Recap

Part I: Transition Network Analysis | Theoretical Grounding | Data | Building Networks | Transition Network (TNA) | Frequency Network (FTNA) | Attention Network (ATNA) | Co-occurrence Network from Binary Data | Window-based TNA (WTNA) | Mixed Network (Transitions + Co-occurrences) | Validation | Reliability | Bootstrap Analysis | Centrality Stability | Clustering | Permutation Test for Clusters | Post-hoc Covariate Analysis | Part II: Psychological Network Analysis | Regularized Network (EBICglasso) | References

Data | Selecting mostly-active learners | Sequence plots | Transition networks | Mean First Passage Times | Stationary distribution | Markov Stability

1. The dataset | 2. Split by time — early vs late interactions | 3. Build the grouped network | 4. Compare patterns between early and late | How to read the residuals | 5. Pyramid plot | 6. Heatmap | 7. Sort by frequency | 9. Note on the test choice

The dataset | 1. type = "heatmap" — clustered carpet | 1.1 Default — LCS distance, ward.D2 dendrogram | 1.2 Switch the sort strategy | 1.3 Cluster separators with k | 1.4 Legend position, custom palette, title | 1.5 Cell borders + tick thinning | 1.6 frame = TRUE brings back the outer box | 2. type = "index" — gap-ready carpet with facets | 2.1 Single panel | 2.2 Visible row gaps | 2.3 Faceted by net_clustering (auto 2×2 for k = 3) | 2.4 Force a 1×3 row | 3. type = "distribution" — state proportions over time | 3.1 Default stacked area | 3.2 Stacked bars, count scale | 3.3 NA band on/off | 3.4 Faceted by cluster | Cheat sheet

What parse_names() is | The three name conventions | Output styles: format | The "parts" attribute | Input shape: vector, not data frame | Recommended workflow: normalise before building | Applying to an existing edgelist (and its hazards) | Limitations | Summary

Daily EMA — value distribution ticks | Daily EMA — distribution bars | Activity timelines | Line snake | Timeline snake | Tick lines with correlation arcs | Dot plot with dark bands | Mean and median markers | Faceted multi-construct | Survey sequence | Sequential distribution | Sequence snake | Built-in palettes

Overview | Why Bootstrap and Power Analysis? | Bootstrap Analysis | Power Analysis | Bootstrap Simulations | Basic Bootstrap | Evaluating Bootstrap Results | Advanced Bootstrap Options | Approach 1: Grid Simulation | Running Grid Simulation | Analyzing Power Results | Finding Minimum Sample Size | Approach 2: Targeted Power Study | Interpreting Results | Key Metrics | Visualizing Power Curves | Edge Recovery Analysis | Recovery Metrics | Factors Affecting Power | Sample Size (n_sequences) | Sequence Length | Network Size (n_states) | Network Density | Comprehensive Power Study Design | Recommended Protocol | Reporting Results | Power Analysis Report Template | Summary | Key Functions | Recommended Workflow | Rules of Thumb

Overview | Network Objects | Matrices & Sequences | Hierarchical & Social Data | Simulating Network Objects | igraph Networks with simulate_igraph() | Graph Algorithms | Choosing Name Regions | Weighted Networks | statnet Networks with simulate_network() | Fitted TNA Models with simulate_tna_network() | Simulating Transition Matrices | Simple Matrices with simulate_matrix() | Matrix Types | Controlling Edge Density | Custom Node Names | Multi-Type Matrices with simulate_htna() | Custom Type Configuration | Using with tna Package | Simulating Sequences | Basic Sequences with simulate_sequences() | Providing Your Own Parameters | Selecting Learning State Categories | Adding Missing Values | Getting Parameters Back | Advanced Sequences with simulate_sequences_advanced() | Stability Modes | Simulating Hierarchical Data | Long Format with simulate_long_data() | Variable Group Sizes | Achievement Levels | One-Hot Encoded Data | Simulating with simulate_onehot_data() | Edge List Simulation | Social Networks with simulate_edge_list() | Network Properties | Complete Network Generation | Generate TNA Datasets with simulate_tna_datasets() | Generate Fitted Networks with simulate_tna_networks() | Random Probabilities with generate_probabilities() | Reproducibility | Performance Tips | Summary

Overview | Understanding Multi-Type Networks | What Makes HTNA/MLNA Different? | Educational Research Applications | Simulating Multi-Type Networks | Basic Usage | Understanding the Output | Default Learning Categories | Customizing Network Structure | Number of Types and Nodes | Custom Type Names | Custom Learning Categories | Controlling Edge Probabilities | Within vs. Between Type Connectivity | Analyzing Connectivity Patterns | Using with tna Package | Visualization with plot_htna | Visualization with plot_mlna | Fitting Models to Multi-Type Data | Advanced Applications | Group TNA Networks | Using simulate_tna_matrix() | Educational Research Examples | Example 1: Self-Regulated Learning Study | Example 2: Collaborative Learning Study | Example 3: Multimodal Data Integration | Comparing Multi-Type Networks | Comparing Two HTNA Networks | Analyzing Type-Level Patterns | Summary | Key Functions | Key Parameters | Output Components | Next Steps

Overview | Installation | Getting Started | Your First Simulation | Fitting a TNA Model | Extracting Network Components | Key Concepts | Learning States | Transition Matrices | Multi-Type Networks (HTNA/MLNA) | Basic Workflows | Workflow 1: Simulate and Analyze | Workflow 2: Compare Two Networks | Workflow 3: Bootstrap Analysis | Data Formats | Wide Format (Default) | Long Format | Next Steps | Getting Help

Overview | Available Categories | Complete Learning States Reference | Metacognitive (20 verbs) | Cognitive (30 verbs) | Behavioral (30 verbs) | Social (30 verbs) | Motivational (30 verbs) | Affective (30 verbs) | Group Regulation (9 verbs) | LMS Actions (30 verbs) | Using Learning States | Basic Retrieval | Random Sampling | Smart Selection | Biased Selection | Integration with Simulation Functions | With simulate_sequences() | Specifying Categories | With simulate_matrix() | With simulate_htna() | Direct Access to LEARNING_STATES | Global Names Dataset | Educational Research Applications | Self-Regulated Learning (SRL) | Socially Shared Regulation of Learning (SSRL) | Learning Analytics (LMS Data) | Collaborative Learning | Custom State Names | Complete Reference Table | Summary | Key Functions | Category Summary | Usage Tips

Pattern Discovery | Early Warning Signals | Regime Detection