Jurgen A. Doornik, David F. Hendry and Bent Nielsen
  (1998)
  'Inference in cointegrated models: UK M1 revisited'
  Journal of Economic Surveys 12, p 533-572

  ABSTRACT:
  The paper addresses the empirical application of multivariate
  cointegration analysis to a small model of narrow money, prices,
  output and interest rates in the UK. Practical determination of
  cointegration rank is difficult for many reasons: determinisitc
  terms play a crucial role in limiting distributions, and systems
  may not be formulated to ensure similarity to nuisance parameters;
  finite-sample critical values may differ from asymptotic
  equivalents (the latter are usually obtained via simulation, but
  could be based on response surfaces); dummy variables alter
  critical values, often greatly; multiple cointegration vectors
  must be identified to allow inference; the data may be I(2) rather
  than I(1), altering distributions; and conditioning to partical
  systems must be done with care.