[color=#0000ff]Mode (mo) is the most typical value of a variable.  [/color]It may not be unique but can be used with all scales. [br][br][color=#0000ff]Median (md) is the middlemost value of an ordered data. [/color] If number of observations is even, then median is the average of two middlemost values.  Median cannot be determined for variables in nominal scale.[br][br][color=#0000ff]Lower quartile (q[sub]1[/sub], Q[sub]1[/sub])[/color] is at 25% of an ordered data. [color=#0000ff]Upper quartile [color=#0000ff] (q[sub]3[/sub][/color][color=#0000ff], Q[/color][sub][color=#0000ff]3[/color][/sub][color=#0000ff])[/color][/color] is at 75% of an ordered data.  [color=#0000ff]Fractile[/color] is a general item for different percentages. [br][br]Statistics for location is easy to describe with Tukey's box-and-plot. For example, SPSS gives the observation number in a data for extremes and outliers. It helps in checking the values.[br]

[color=#0000ff]Mean[/color] is the most known statistical measure. It is very sensitive for extreme values. For that reason, it should not be informed alone like the above graph points out. [br][br]For discrete values, mean is solved with the formula[br][br] [br]  [math]\LARGE \overline{x} =\frac{\sum_{i=1}^n x_i}{n}.[/math][br]               [br][br]If some values are more important than the others, then values could be weighted:[br][br]  [math]\LARGE \overline{x} =\frac{\sum_{i=1}^n p_ix_i}{\sum_{i=1}^n p_i}.[/math][br][br][color=#0000ff]Trimmed mean[/color] ([math]\Large\overline t_a[/math]) may be used, if the data includes extremes. In that case,  [i]a[/i] % of obsevations are cut from both ends and the normal mean is solved for remaining values. In SPSS, cut is done at 5 %. [br][br][br][color=#0000ff]In windsorised mean[/color] ([math]\Large\overline w_a[/math]), the values are not cut but replaced with the nearest remaining value.

The case [i]b[/i] is the righthand tail and case [i]c[/i] is lefthand tail. They may be problematic in tradional analysis. [br][br]SPSS gives the value automatically:[br][list][*]if skewness > 0, it is the right hand tail [/*][*]if skewness < 0, it is the left hand tail[/*][*]if skewness is twice its standard error, then the distribution is not symmetric.[br][/*][/list][br]The[color=#0000ff] case [i]d[/i][/color] is a bimodal distribution, which indicates there may be two different normal-distributed groups included. [color=#0000ff]Do not use in your analysis[/color]!