An aggregate consumption function for Canada: a cointegration approach

Abstract

This study utilizes cointegration theory and error correction models (ECMs) to specify a candidate dynamiac formulation of the aggregate consumption function using quarterly Canadian date. The variables entering the long-run equlibrium relationship are tested for unit roots using a variety of techniques such as the Dickey–Fuller, the augemented Dickey–Fuller and the Phillips–Perron test profedures. The Engle and Granger cointegration test, and the fully modified consistent and efficient estimator of Phillips and Hansen are used to estimate the cointegration relationship. Johansen’s maximum likelihood approach is also used to determine the rank of the cointegrating matrix. The error correction model, which appears to be a tentatively adequate conditional characterization of the date generating process, revelas that disposable income, wealth, government expenditures, relative prices and liquidity constraints (proxied by the unemployment rate) are important variables. Non-nested tests are carried out against a recent dynamaic specification found in Sawyer. Encompassing tests show that the model can encompass the Sawyer model.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 9 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.