Applied Time Series with Gretl: From Data to Trading Strategies
This is a small book (or, as of now, a set of notes) to give you a feel for time series analysis and forecasting with some application in economics and finance.
Each chapter is designed by:
intuition-first
data-driven
applications (trading = huge plus)
clean structure
📘 PART I — Data, Uncertainty, and Financial Returns¶
Chapter 1 — Why Time Series Matter¶
What is a time series?
Examples: GDP, inflation, stock prices
Why economists care
Why traders care
Preview of the course
Chapter 2 — Returns and Financial Data¶
Prices vs returns
Simple vs log returns
Compounding intuition
Stylized facts (fat tails, volatility clustering)
Chapter 3 — A Quick Review of Probability and Statistics¶
randomness and distributions
normal, t, F (light, intuitive)
hypothesis testing (visual + intuitive)
Part I Capstone — Working with Financial Data¶
📘 PART II — Seeing Patterns in Time Series¶
Chapter 4 — Visualizing Time Series¶
plotting data
trends, cycles, noise
rolling averages (Excel-friendly)
Chapter 5 — Smoothing and Trend Estimation¶
moving averages
exponential smoothing
Holt / Holt–Winters
LOESS, splines, HP filter
bias–variance trade-off
Chapter 6 — Trading Indicators as Filters¶
moving average crossover
MACD
RSI
Bollinger Bands
Part II Capstone — Seeing Patterns and Trading Signals¶
📘 PART III — Core Time Series Concepts¶
Chapter 7 — Randomness and Dependence¶
white noise
random walk
persistence
Chapter 8 — Stationarity¶
what is stationarity?
why it matters
visual intuition
Chapter 9 — ACF and PACF¶
correlation across time
identifying patterns
Chapter 10 — Unit Roots and Differencing¶
random walk revisited
unit root intuition
ADF test (light)
detrending vs differencing
Part III Capstone — Dependence, Stationarity, and Unit Roots¶
📘 PART IV — Linear Time Series Models¶
Chapter 11 — Autoregressive Models (AR)¶
AR(1) → AR(p)
intuition + Yule–Walker
Chapter 12 — Moving Average Models (MA)¶
Chapter 13 — ARMA Models¶
Chapter 14 — ARIMA Models¶
non-stationarity
differencing
modeling workflow
Part IV Capstone — Building and Evaluating ARIMA Models¶
📘 PART V — Forecasting¶
Chapter 15 — Forecasting Methods¶
static vs dynamic
intuition
Chapter 16 — Evaluating Forecasts¶
MSE, RMSE, MAE, MAPE
Theil’s U
decomposition
📘 PART VI — Relationships Between Time Series¶
Chapter 17 — Spurious Regression¶
why regression can fail
Chapter 18 — Dynamic Models¶
distributed lag
Chapter 19 — Granger Causality¶
Chapter 20 — Cointegration¶
long-run relationships