• Introduction.
• The statistical characterisation of time series.
• The change-point search in time-series analysis.
• Final change-point determination and test of randomness of the derived homogeneous sequences.
• Example. The annual averages of the air temperature 1908-1995 at Casablanca (Cuba).
• Conclusion.
• References.
• Tables.
• Annex.

Introduction.

The exact determination of the climate evolution is of most importance as well for theoretical purposes as for practical applications. Moreover, if the change-point way of evolution of the climate has already been evidenced in the nineteen-fifties (Sneyers 1997), Monte-Carlo experiments have shown the limits of change-point detection (Easterling and Peterson 1995).

The purpose of this paper is to summarise the principles of change-point detection for their complete determination and their exact significance as alternative assumption to randomness.

The analysis of the Casablanca temperature series is given for illustrating the method.