Electronic Proceedings of the Twentyfifth Annual International Conference on Technology in Collegiate MathematicsBoston, Massachusetts, March 2124, 2013Paper C032
This is an electronic reprint, reproduced by permission of Pearson Education Inc. Originally appeared in the Proceedings of the Twentyfifth Annual International Conference on Technology in Collegiate Mathematics, ISBN10: 0133866726, Copyright (C) 2014 by Pearson Education, Inc. 
Is My Data Normal? Using Technology To Test For Normality 
James Graziose
Palm Beach State College

Click to access this paper:

In elementary statistics classes, many of our statistical tests that we perform on small data sets (n < 30) require the population from which the sample data was obtained be normally distributed. We explain to our students, a random variable X is normally distributed, or approximately normal, if the graph of the histogram is symmetric and bellshaped or a normalquantile plot which is linear. But in reality, we never obtain a perfect symmetric histogram or a normal quantile plot which is linear. Given a data set, which was obtained from a simple random sample whose distribution is unknown, we will apply two methods; a normalquantile plot and Lilliefors test to assess the normality of the random sample.
Keyword(s): statistics