How would you determine if a data set is normally distributed?

In one of my college projects, I conducted a survey to gauge student satisfaction with various campus services. After collecting the responses, I wanted to determine if the satisfaction scores followed a normal distribution. I started by creating a histogram of the data, which helped me visualize the distribution shape. I noticed a bell curve, but to be thorough, I also performed a Shapiro-Wilk test, which confirmed that my data was normally distributed. This experience taught me the importance of using both visual and statistical methods to validate assumptions in data analysis.

As a volunteer for a local community center, I helped analyze attendance data for various events. I gathered the attendance figures and plotted them in a histogram. The shape appeared roughly bell-curved, suggesting normality. To validate this, I used a Q-Q plot, which showed that the data points closely followed the diagonal line, indicating normal distribution. This experience reinforced my understanding of data analysis and how crucial it is to ensure assumptions are met, especially when making decisions based on data.

In my first job as a junior analyst, I was tasked with analyzing sales data over the past year. I needed to check if the daily sales figures were normally distributed to apply certain statistical models. I first visualized the data using a histogram, which showed a slight skew but wasn't conclusive. I then conducted a Kolmogorov-Smirnov test, which indicated a deviation from normality. This prompted me to apply transformations to the data, ultimately leading to better model accuracy. This experience highlighted the importance of thorough data assessment and the practical application of statistical tests.