How to generate an expected normal data to measure normality of an observed data?

29 Views Asked by At

Suppose we have a set of data, that do not follow normal distribution. In order to make it follow the normal distribution approximately, we use Box Cox transformation. Then, we need to measure its normality possibly using QQ plot. According to wikipedia page here https://en.wikipedia.org/wiki/Normality_test, it says that

A graphical tool for assessing normality is the 
normal probability plot, a quantile-quantile plot 
(QQ plot) of the standardized data against the 
standard normal distribution. Here the correlation 
between the sample data and normal quantiles 
(a measure of the goodness of fit) measures 
how well the data are modeled by a normal distribution. 
For normal data the points plotted in the QQ plot should
fall approximately on a straight line, indicating 
high positive correlation. These plots are easy to interpret
and also have the benefit that outliers are easily identified.

My question is how to know the normal quantiles. What we have is a data set that the BoxCox transformation was applied. Is the following correct?

  • Obtain standard deviation and mean of the data
  • Set them as a parameter of normal distribution
  • Sample as many data from the normal distribution as the data we have

  • Compute the correlation b/w expected normal-distributed samples and observed transformed data

  • Plot them