Although there are no formal guidelines for the amount of data needed for a correlogram, larger samples more clearly indicate patterns in the data.
The sample data should be selected randomly
In statistics, random samples are used to make generalizations, or inferences, about a population. If your data were not collected randomly, your results may not represent the population.
The relationship between variables should be linear
If your variables do not have a linear relationship, the correlogram will not accurately reflect the strength of the relationship. Examine a matrix plot to look for other relationships.
Unusual values can have a strong effect on the results
Because unusual values can have a strong effect on the results, use a matrix plot to identify these values. You should investigate outliers because they can provide useful information about your data or process.