The Granger Centre for Time Series Econometrics

GC 18/02: Testing for strict stationarity in a random coefficient autoregressive model



We propose a procedure to decide between the null hypothesis of (strict) stationarity and the alternative of non-stationarity, in the context of a Random Coefficient AutoRegression (RCAR). The procedure is based on randomising a diagnostic which diverges to positive infinity under the null, and drifts to zero under the alternative. Thence, we propose a randomised test which can be used directly and - building on it - a decision rule to discern between the null and the alternative. The procedure can be applied under very general circumstances: albeit developed for an RCAR model, it can be used in the case of a standard AR(1) model, without requiring any modifications or prior knowledge. Also, the test works (again with no modification or prior knowledge being required) in the presence of infinite variance, and in general requires minimal assumptions on the existence of moments.

Download the paper in PDF format



Lorenzo Trapani

View all Granger Centre discussion papers | View all School of Economics featured discussion papers


Posted on Wednesday 28th November 2018

The Granger Centre for Time Series Econometrics

School of Economics
University of Nottingham
University Park
Nottingham, NG7 2RD