BioNinja

Measures of Central Tendency

Measurements of central tendency function to represent the most typical value within a dataset

• Mean – the mathematical average (used for continuous data)

• Median – the exact middle value of a dataset (used for ordinal data)

• Mode – the most commonly occurring number (may be used for nominal data)

Most experiments will use either the mean or the median to represent the central tendency of a dataset

• The mean should not be used when the measurement scale is non-linear (e.g. pH is a logarithmic scale)

• The mean is also highly susceptible to the influence of outliers (i.e. avoid using if the data is skewed)

Skewness is a measure of how well the dataset conforms to a normal distribution (bell-shaped curve)

• Continuous data should typically conform to a normal distribution unless the dataset is skewed by outliers

• A negative skew value indicates the majority of values are greater than the mean, while a positive skew value indicates the majority of values are less than the mean

• A skew value of greater than 2.0 suggests substantial non-normality (requires the use of median instead of mean)

Distribution