Logarithmic Transform

 

Menu locations: Data_Transforming and Deriving_Common Transforms_Log (Natural) and _Log (Base 10).

Data_Transforming and Deriving_Common Transforms_Log (Natural).

Data_Transforming and Deriving_Common Transforms_Log (Base 10).

 

Logarithmic transformation can be used to stabilise the variance of a sample (Bland, 2000).

 

The function named Log (natural) calculates the natural (Naperian, log to the base e) logarithm of the data you select.

 

The function named Log (base 10) calculates the common (log to the base 10) logarithm of the data you select.

 

The results are stored in a new column that is marked Log(natural):<name> or Log(base 10):<name> where <name> is the original column label. Indeterminable values (i.e. log of any data < 0) are marked as missing data unless you opt to add a suitable constant to all data (you are prompted if you need to do this). It is best to consult with a statistician before using constants in log transformations.

 

Effects of log transformation:

• Variance stabilisation.
• Increasing slopes in x in relation to another variable are linearized.
• Positively skewed distributions of x are normalized.