Should I eliminate outliers?
Removing outliers is legitimate only for specific reasons. Outliers can be very informative about the subject-area and data collection process. Outliers increase the variability in your data, which decreases statistical power. Consequently, excluding outliers can cause your results to become statistically significant.
What does log transformation do to outliers?
Log transformation also de-emphasizes outliers and allows us to potentially obtain a bell-shaped distribution. The idea is that taking the log of the data can restore symmetry to the data. A log transformation is not always essential to analyzing the data. It can depend on the statistical analysis we are performing.
Is it better to remove outliers before or after transformation?
Removal of outliers creates a normal distribution in some of my variables, and makes transformations for the other variables more effective. Therefore, it seems that removal of outliers before transformation is the better option.
What’s the best way to reduce the impact of an outlier?
One option is to try a transformation. Square root and log transformations both pull in high numbers. This can make assumptions work better if the outlier is a dependent variable and can reduce the impact of a single point if the outlier is an independent variable. Another option is to try a different model.
Do you have to look for outliers in data?
It usually makes no sense to judge outliers as such based only on the available data. Outliers are rare, and the will be “visible” from data only if there is a considerable amount of data.
Is it better to make assumptions or outliers?
This can make assumptions work better if the outlier is a dependent variable and can reduce the impact of a single point if the outlier is an independent variable. Another option is to try a different model. This should be done with caution, but it may be that a non-linear model fits better.