- ES Español (Latinoamérica)

- EN English

2.3. Probability and Statistical Computing (PSC)
This area bridges the theoretical foundations of probability and statistics with their computational implementation. It covers advanced probabilistic modeling, computational inference methods, and the design of experiments in silico. Students learn to apply stochastic processes, Bayesian methods, and resampling techniques to analyze complex systems and make data-driven decisions under uncertainty. This knowledge is crucial for modern data analysis, machine learning, and scientific computing.
| Knowledge Area (KA) | Core Tier1 | Core Tier2 |
2.3.1 Advanced Probability and Stochastic Processes | 1 | 1 |
2.3.2 Computational Statistical Inference | 1 | 1 |
2.3.3 Design of Computational Experiments | 1 | 1 |
2.3.4 Resampling and Validation Methods | 1 | 1 |
2.3.1. PSC/Advanced Probability and Stochastic Processes (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Measure-theoretic probability foundations
- Random variables and distributions
- Stochastic processes characterization
- Markov chains and Markov processes
- Brownian motion and diffusion processes
Learning Outcomes:
Core:
- Apply measure-theoretic concepts to probability spaces [Familiarity]
- Characterize different types of stochastic processes [Assessment]
- Analyze Markov chains for steady-state and transient behavior [Usage]
- Model systems using continuous-time stochastic processes [Usage]
2.3.2. PSC/Computational Statistical Inference (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Maximum Likelihood Estimation (MLE)
- Bayesian inference methods
- Markov Chain Monte Carlo (MCMC) methods
- Expectation-Maximization (EM) algorithm
- Bootstrap and jackknife resampling
Learning Outcomes:
Core:
- Implement Maximum Likelihood Estimation for various distributions [Usage]
- Apply Bayesian methods for parameter estimation [Usage]
- Implement MCMC algorithms for posterior sampling [Usage]
- Use EM algorithm for models with latent variables [Usage]
- Apply bootstrap methods for confidence intervals [Usage]
2.3.3. PSC/Design of Computational Experiments (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Factorial designs and fractional factorials
- Response surface methodology
- Space-filling designs (Latin hypercube)
- Optimal design of experiments
- Computer experiments and surrogate modeling
Learning Outcomes:
Core:
- Design factorial experiments for factor screening [Usage]
- Apply response surface methodology for optimization [Usage]
- Implement space-filling designs for computer experiments [Usage]
- Select optimal designs for specific objectives [Assessment]
- Construct surrogate models for expensive simulations [Usage]
2.3.4. PSC/Resampling and Validation Methods (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Bootstrap estimation and confidence intervals
- Cross-validation techniques
- Permutation tests and randomization
- Model selection and information criteria
- Ensemble methods and bagging
Learning Outcomes:
Core:
- Implement bootstrap for standard error estimation [Usage]
- Apply cross-validation for model assessment [Usage]
- Use permutation tests for hypothesis testing [Usage]
- Compare models using information criteria (AIC, BIC) [Assessment]
- Implement bagging for variance reduction [Usage]