Stochastic processes

Preface

Prerequisites

Learning ethics

Introduction

What is a stochastic process?

Space of states

A time series is a stochastic process indexed by a discrete monotonic increasing set.

Type of stochastic dependence between random variables

https://stats.stackexchange.com/questions/126791/is-a-time-series-the-same-as-a-stochastic-process

1.1 La ecuación de regresión lineal simple poblacional
1.2 Diagrama de dispersión
1.3 Estimación de la ecuación de regresión lineal simple
1.4 Confiabilidad de las predicciones
1.5 Prueba de hipótesis acerca del coeficiente de regresión

2.1 Modelo de regresión múltiple
2.2 Notación matricial
2.3 Prueba de hipótesis para los parámetros del modelo

3.1 Supuestos de la correlación simple
3.2 Coeficiente de correlación lineal poblacional
3.3 Coeficiente de correlación lineal muestral
3.4 Prueba de hipótesis acerca del coeficiente de correlación lineal

4.1 Elementos de una serie de tiempo
4.2 Tipos de series de tiempo
4.3 Estructura de una serie de tiempo
4.3.1 Tendencia
4.3.2 Estacionalidad
4.3.3 Movimientos cíclicos
4.3.4 Variaciones inesperadas
4.4 Modelos para el análisis de series de tiempo
4.4.1 Modelos de media cero
4.4.2 Caminata aleatoria
4.4.3 Modelos de tendencia
4.4.4 Modelos de estacionalidad

Why does time serie analysis matter to you?

Research

Ecosystem

Standards, jobs, industry, roles, …

Python libraries

https://github.com/lmmentel/awesome-time-series

https://github.com/rjt1990/pyflux

https://github.com/facebook/prophet

https://github.com/blue-yonder/tsfresh

https://www.aeon-toolkit.org/en/latest/

https://github.com/ethanrosenthal/skits

https://github.com/dmbee/seglearn

Story

FAQ

Worked examples

Characteristics of time series

The nature of time series data

Classic

Static covariates

Time series can contain static data.

Hierarchical time series

Exercises and Projects

  1. Logic. Mathematics. Code. Automatic Verification such as Lean Proven or Frama-C.
  1. Languages in Anki.

Summary

FAQ

Worked examples

Reference Notes

Analysis

White noise

Autocorrelation

Dynamic Time Warping

DTW Windows

Transformations

Calendar adjustments

Population adjustments

Inflation adjustments

Mathematical transformations

log

Box-Cox transformations Box & Cox, 1964

Bias adjustments

back-transformed

Data windowing

Windowing operations

https://pandas.pydata.org/docs/user_guide/window.html#window-exponentially-weighted

https://www.oreilly.com/radar/the-world-beyond-batch-streaming-101/

https://www.oreilly.com/radar/the-world-beyond-batch-streaming-102/

https://softwaremill.com/windowing-in-big-data-streams-spark-flink-kafka-akka/

Exercises and Projects

Summary

FAQ

Reference Notes

Exploratory analysis

Time series graphics

Frequency

Annual, Quartely, Monthly, Weekly, Bussiness days

No time based

Time series patterns

Trend

Seasonal

Cyclic

Seasonal plots

Seasonal subseries plots

Scatterplots

Lag plots

Exercises and Projects

Summary

Design decisions

FAQ

Reference Notes

Curve fitting and signal estimation

Function approximation

Time series forecasting and prediction

The forecaster’s toolbox

Residual diagnostics

Evaluating models

Backtesting

Prediction intervals

Some simple forecasting methods

Judgmental forecasts

Time series regression models

TIme series decomposition

Exponential smoothing

ARIMA models

Forecasting hierarchical or grouped time series

Advanced forecasting methods?

Complex seasonality

Vector autoregressions

Bootstrapping and bagging

Deep learning models

Exercises and Projects

Summary

Design decisions

FAQ

Reference Notes

Time series classification

https://www.timeseriesclassification.com/

The classifier’s toolbox

Evaluating models

Anomaly detection

Time series segmentation

Practical issues dealing with stocastic processes

Weekly, daily and sub-daily data

Time series of counts

Ensuring forecasts stay within limits

Forecast combinations

Prediction combinations

Prediction intervals for aggregates

Backcasting

Very long and very short time series

Forecasting on training and test sets

Visualization in real-time

Grafana

Metabase

Storage

Postgres and TimeseriesDB

https://www.timescale.com/

Next steps

Explainable time series models

https://www.youtube.com/watch?v=e5qs9PG0HFM&list=PLH3Ao8RnwtkTtqDeRum-t-GD1OP0pm_kv

References

1. Shumway, Robert H., and Stoffer, David S. Time Series Analysis and Its Applications: With R Examples, Third Edition. Springer Verlag. Available here.
2.
Bisgaard, Søren, and Kulahci, Murat. Time Series Analysis and Forecasting by Example, 1st Edition. John Wiley & Sons. Available here.
3.
Beck, V.L. (2017). Linear Regression: Models, Analysis, and Applications. Nova Science Publishers. Available at: EBSCOhost.
4.
Bingham, N. H., & Fry, J. M. (2010). Regression: Linear Models in Statistics. Springer. Available at: Springer Link [Clásica].
5.
Bowerman, B.L., O'Connell, R.T., Koehler, A.B. (2007). Pronósticos, series de tiempo y regresión: un enfoque aplicado. Ed. Cengage Learning. [Clásico].
6.
Ciaburro, G. (2018). Regression Analysis with R: Design and Develop Statistical Nodes to Identify Unique Relationships Within Data at Scale. Packt Publishing. Available at: EBSCOhost.
7.
Giuseppe, C. (2018). Regression Analysis with R: Design and Develop Statistical Nodes to Identify Unique Relationships Within Data at Scale. Packt Publishing. Available at: EBSCOhost.
8.
Tattar, P.N. (2017). Statistical Application Development with R and Python - Second Edition. Vol 2nd ed. Packt Publishing.
9.
Stanimirović, I. (2020). Correlation and Regression Analysis: Applications for Industrial Organizations. Arcler Press. Available at: EBSCOhost.
10.
Pal, D.A. (2017). Practical Time Series Analysis. Packt Publishing. Available at: EBSCOhost.
11.
Montgomery, D.C., Peck, E.A., Vining, G. (2002). Introducción al análisis de regresión lineal. Ed. Grupo Patria Cultural. [Clásico].

  1. Nielsen, A. (2020). Practical time series analysis: Prediction with statistics and machine learning. O’Reilly.
  1. Atwan, T. A. (2022). Time Series Analysis with Python Cookbook: Practical Recipes for Exploratory Data Analysis, Data Preparation, Forecasting, and Model Evaluation. Packt Publishing.
  1. Hyndman, R.J., & Athanasopoulos, G. (2018) Forecasting: principles and practice, 2nd edition, OTexts: Melbourne, Australia. https://otexts.com/fpp2/. Accessed on 12 January, 2023
  1. Bickel, P. J., & Doksum, K. A. (1981). An analysis of transformations revisited. Journal of the American Statistical Association76(374), 296–311.
  1. Box, G. E. P., & Cox, D. R. (1964). An analysis of transformations. Journal of the Royal Statistical Society. Series B, Statistical Methodology26(2), 211–252. [DOI]