Fit Hidden Markov Model
Skill Verified ActiveFit hidden Markov models using the Baum-Welch (EM) algorithm with model selection, Viterbi decoding for state sequences, and forward-backward probabilities. Use when observations are generated by unobservable latent states, you need to segment a time series into latent regimes (market regimes, speech phonemes, biological sequences), compute sequence probabilities, decode the most likely hidden state path, or compare models with different numbers of hidden states.
To provide a precise and robust implementation for analyzing time series data generated by unobservable latent states.
Features
- Fit HMMs using Baum-Welch (EM) algorithm
- Perform Viterbi decoding for most likely state sequence
- Implement model selection using BIC/AIC
- Handle Gaussian, discrete, Poisson, and multinomial emissions
- Support multiple restarts to avoid local optima
Use Cases
- Segment time series into latent regimes (e.g., market regimes, speech phonemes)
- Compute probabilities of observed sequences
- Decode the most likely hidden state path
- Compare models with different numbers of hidden states
Non-Goals
- Handling of non-sequential data
- Models with infinite hidden states
- Real-time streaming data processing
- Advanced state-dwell time modeling (e.g., HMM-MARKOV)
Workflow
- Define Hidden States and Observation Model
- Initialize Parameters
- Run Baum-Welch EM for Parameter Estimation
- Apply Viterbi Decoding for Most Likely State Sequence
- Perform Model Selection (BIC/AIC Across Model Orders)
- Validate with Held-Out Data and Posterior Decoding
Practices
- Statistical modeling
- Time series analysis
- Machine learning
- Algorithm implementation
Prerequisites
- Observations sequence/matrix
- Number of hidden states (integer or range)
- Emission type string (gaussian, discrete, poisson, multinomial)
Practical Utility
- info:Usage examplesWhile the SKILL.md provides detailed inputs and a procedure, concrete, ready-to-run examples showing input, invocation, and output are missing.
Installation
/plugin install agent-almanac@pjt222-agent-almanacQuality Score
VerifiedTrust Signals
Similar Extensions
Statsmodels
98Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.
Fit Drift Diffusion Model
100Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.
OraClaw Forecast
100Time series forecasting for AI agents. ARIMA and Holt-Winters predictions with confidence intervals. Predict revenue, traffic, prices, or any sequential data. Sub-5ms inference.
TimesFM Forecasting
100Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.
Generate Statistical Tables
99Generate publication-ready statistical tables using gt, kableExtra, or flextable. Covers descriptive statistics, regression results, ANOVA tables, correlation matrices, and APA formatting. Use when creating descriptive statistics tables, formatting regression or ANOVA output, building correlation matrices, producing APA-style tables for academic papers, or generating tables for Quarto and R Markdown documents.
PyMC Bayesian Modeling
99Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.