ETC3450 Chap.5 Higher-Order Dynamics and Lag Polynomials

Higher-Order Dynamics and Lag Polynomials

An AR(p) model relates the current value to several past values and an innovation. Coefficients describe a conditional recursion holding the other lags in the equation. Dynamic response emerges from their combined roots, so signs and magnitudes should not be interpreted one at a time without the system. Too few lags leave dependence in residuals; too many consume degrees of freedom and can destabilise forecasts.

Theory, sampling frequency and diagnostics all inform order selection. Quarterly behaviour may depend on the immediately previous quarter and the same quarter in an earlier cycle. A single-lag model can leave a patterned residual ACF even if its first coefficient looks plausible. Write the full lag vector, derive the implied characteristic polynomial and inspect residual dependence after estimation.

Compare candidate orders out of sample rather than selecting the best in-sample fit automatically. Econometric interpretation begins by fixing the stochastic object behind AR(p): its conditioning information, time index and maintained assumptions. Derive the implication for lag order before inserting estimated values, because a numerical answer can conceal a wrong model.

Diagnostics then ask whether residual behaviour is compatible with the specification. The lag operator shifts a series backward, allowing an autoregression to be written compactly as a polynomial in that operator. Stability is determined by the roots of the autoregressive polynomial under the course convention. Root location summarises the combined dynamic effect that individual coefficients can obscure.

A unit root creates random-walk-like persistence and signals differencing. Complex roots can produce damped oscillation when stable. Repeated roots alter the shape of adjustment. The mathematical result must be translated back into a path and forecast implication. Two coefficient sets can share a positive first lag yet have different root patterns because of the second lag.

One produces decaying oscillations; another fails the stability condition and lets shocks persist or grow. State the polynomial convention before quoting the root test. Substitute a candidate root to verify it, then describe the implied shock response. A root calculation without a dynamic interpretation is unfinished econometrics. A time-series calculation should be accompanied by a probability statement.

For lag operator, separate a realised path from the process that could generate many paths. State which moments are stable and how characteristic root changes with the lag. When the result depends on stability, identify the parameter region and initial condition explicitly.

When stability depends on an initial condition, inspect the admissible parameter region explicitly; a boundary value can expose an incoherent long-run claim. Diagnose the lag polynomial by comparing level and transformed plots, tracing its characteristic roots, estimating a defensible candidate and testing whether residual dependence remains.

What this chapter covers

• 01

  AR(p) distributes dependence across several lags

• 02

  Lag-polynomial roots decide stability

Against a limiting case: AR(p) distributes dependence across several lags

Key terms

AR(p) lag structure

AR(p) distributes dependence across several lags — An AR(p) model relates the current value to several past values and an innovation. Coefficients describe a conditional recursion holding the other lags in the equation. Dynamic response emerges from their combined roots, so signs and magnitudes should not be interpreted one at a time without the system. Write the full lag vector, derive the implied characteristic polynomial and inspect residual dependence after estimation. Compare candidate orders out of sample rather than selecting the best in-sample fit automatically.

Lag-polynomial stability roots

Lag-polynomial roots decide stability — The lag operator shifts a series backward, allowing an autoregression to be written compactly as a polynomial in that operator. Stability is determined by the roots of the autoregressive polynomial under the course convention. Root location summarises the combined dynamic effect that individual coefficients can obscure. State the polynomial convention before quoting the root test. Substitute a candidate root to verify it, then describe the implied shock response. A root calculation without a dynamic interpretation is unfinished econometrics.

Higher-Order Dynamics and Lag Polynomials FAQ

Exam move

Keep a derivation and diagnostic sheet for Higher-Order Dynamics and Lag Polynomials. Write every process assumption before calculating a moment, response or forecast. Begin with AR(p) and reconstruct the reasoning without looking at the worked response. Then change one condition in the example and decide whether lag order still explains the outcome.

Use the chapter questions to compare direct observation with inference, and write the strongest rival account in full. Before closing the chapter, return to stability and state the precise boundary it places on transfer. Check that every conclusion names an observable consequence and that uncertainty is attached to the step it affects.

A final retrieval pass should be fast enough to reproduce the method from headings and diagrams while leaving the detailed prose for checking nuance.

ETC2410 Introductory Econometrics · ETC2420 Statistical Thinking · ETC3460 Financial Econometrics