There is a considerable interest in quantifying near-surface ozone concentrations and associated trends, as they serve to define the impacts on ozone of the anthropogenic precursors reductions and to evaluate the effects of emission control strategies. A statistical test has been used to the ozone air concentrations measured in the French rural monitoring network stations, called MERA, in order to bring out spatio-temporal trends in air quality in France over the 1995-2003 period. The non-parametric Mann-Kendall test has been developed for detecting and estimating monotonic trends in the time series and applied in our study at annual values: mean, 98th percentile and median based on hourly averaged ozone concentrations and applied to daily maxima. In France, when averaged overall 9 stations between 1995 and 2003, a slight increasing trend of the O(3) levels (+0.6 +/- 1.3% year( - 1)) is observed, which is strongly influenced by the concentrations of the high altitude stations. In stations below 1000 m a mean rate of -0.48% year( - 1) from annual average concentrations, of -0.45% year( - 1) for medians and of +0.56% year( - 1) for P.98 over the 1995-2003 period were obtained. In stations above 1,000 m a mean rate of +1.75% year( - 1) from annual averages values, of +4.05% year( - 1) for medians and of +2.55% year( - 1) for P.98 were calculated over the 1997-2003 period. This situation is comparable to the one observed in other countries. In Europe and in France a reduction of precursor emissions is observed whereas a slight increasing trend of the O(3) levels is observed over the 1995-2003 period. One reason is the non-linearity of chemical ozone production with respect to precursor emissions. Possible explanations are an increase in near-surface ozone values caused by a reduced ozone titration by reduced NO( x ), the meteorological parameters change, an increase in bio-geogenic compound concentrations, the intercontinental transport from North America and Asia and the influence of stratospheric-tropospheric exchanges. These possible explanations must be interpreted carefully as on the short time scales considered.