The basic properties of any data series, for example temperature, can be defined in terms of the mean over time and the amount of variance about the mean. Other meteorological variables require more complicated statistical calculations. For instance, rainfall is episodic. In many parts of the world, much of the annual rainfall falls in a short rainy season. In addition, most of that rain may be concentrated in a few heavy falls and small shifts in the large-scale weather patterns from year to year may significantly alter the amount and/or the distribution of seasonal rainfall. More complex techniques are usually needed to interpret variations in rainfall.