← ds learning track
notes · 15

Time Series Fundamentals

Once variables are indexed by time, ordinary modelling intuition breaks. Trend, autocorrelation, seasonality, structural breaks, and lag effects all create patterns that can easily be mistaken for signal. Time series methods exist to separate real temporal structure from statistical illusion.

Start with stationarity and differencing, then move into ACF and PACF, then ARIMA building blocks, and finally into IFRS 9 macro-economic satellite models. The goal is to connect textbook time series logic with credit-risk use cases such as PIT PD projection and stress testing.

Time changes the modelling problem

Cross-section vs time series

In cross-sectional modelling, observations are usually treated as independent. In time series, that assumption breaks immediately: today depends on yesterday, and often on much more than yesterday.

This dependence is not a nuisance around the model. It is the model.

Time series = ordered observations with memory

Credit-risk applications

Time series logic appears everywhere in risk work: IFRS 9 macro-economic overlays, PIT calibration, stress testing, default-rate forecasting, and model monitoring.

If the temporal structure is mishandled, the result can look statistically impressive while being fundamentally invalid.

Core warning: spurious regression is one of the biggest traps in macro-credit modelling. Trending variables can create high R² and strong t-stats even when the relationship is fake. [oai_citation:2‡14-time-series.html](sediment://file_0000000099287246af7d6356568671cc)

A useful order for learning time series

01

Start with stationarity

Before asking which model to use, first ask whether the series has stable statistical properties over time.

02

Then inspect autocorrelation

ACF and PACF reveal the shape of dependence and often tell you more than a long list of coefficients.

03

Then build with ARIMA components

AR captures memory, I handles non-stationarity, and MA absorbs forecast errors. Those three pieces define a large share of classical forecasting logic.

04

Then connect it to risk use cases

In IFRS 9 and stress testing, the real question is not just “can you forecast?” but “can you forecast in a way that is economically interpretable and defensible?”

Stationarity is the entry ticket

A stationary series has stable mean, variance, and dependence structure. Most classical time series tools rely on that assumption either directly or after transformation.

ACF & PACF — the fingerprint of the process

ACF shows correlation by lag. PACF shows the direct correlation left after removing the effect of intermediate lags. Together they are the fastest classical guide to AR and MA structure.

ARIMA(p,d,q) — memory, differencing, and error structure

ARIMA is still the core classical workhorse. AR carries forward past values, I handles non-stationarity, and MA carries forward past shocks. Move each component and watch the process change.

Macro-economic PD projection under scenarios

This is where the theory starts feeling useful. A macro-economic satellite model translates GDP or similar drivers into default-rate projections under base, optimistic, and adverse scenarios.

Time series models in credit risk

Model Main use Stationarity required? Main assumption Typical risk use
ARIMAUnivariate forecastingAfter differencingLinear dynamicsDefault-rate forecasting, macro projection
VARMulti-series interactionUsually yesJoint linear dependenceGDP, unemployment, DR systems
VECMCointegrated systemsI(1) + cointegrationLong-run equilibriumLevel relationships across macro series
Regression + ARMA errorsMacro → DRResidual stationarityExogenous driversStandard IFRS 9 satellite logic
Markov-switchingRegime changesWithin regimeDiscrete statesBoom / bust regime analysis
GARCHVolatilityUsually returns stationaryVol clusteringMarket risk, stress volatility

Concepts every validator should keep

unit roots

ADF is not a ritual

Stationarity tests are not decorative. They decide whether classical inference is even valid in the first place.

spurious regression

The macro-model trap

Two trending variables can look strongly related without any real economic connection. Always be suspicious of “beautiful” level regressions.

cointegration

Sometimes levels can still be valid

If a non-stationary combination is itself stable, then the right object is usually cointegration or VECM, not plain OLS in levels.

lag structure

Economic effects are rarely immediate

Macro deterioration today often affects default rates with a delay. Lag choice is not just statistical tuning; it is economic timing.

out-of-sample truth

Forecast accuracy is the real test

In-sample fit is cheap in short macro series. Out-of-sample forecast behaviour is where the model proves whether it knows anything real.

scenario asymmetry

Weighted ECL is not linear

Probability-weighted scenarios matter because the loss function is nonlinear. A symmetric scenario set can still create asymmetric provision impact.

What to leave this page with

Time series modelling starts by respecting time itself. Stationarity, autocorrelation, lag structure, and structural breaks are not technical side notes; they are the substance of the problem.

The useful order is: first test stationarity, then inspect ACF and PACF, then build the right ARIMA-style structure, then bring that logic into macro-credit forecasting and IFRS 9 scenario modelling.

Once that structure is clear, macro models stop looking like ad hoc overlays and start looking like disciplined temporal systems.