How do you choose the appropriate statistical test for your data analysis?

During my final year in college, I worked on a project where we conducted a survey on student satisfaction in our university. We collected responses from over 200 students with questions rated on a scale from 1 to 5. To analyze this data, I had to choose the appropriate statistical test. Since we were comparing the mean satisfaction scores between different departments, I decided to use ANOVA. This was ideal because it allowed us to see if there were significant differences among multiple groups. By correctly applying this test, we found that the engineering department had significantly lower satisfaction scores compared to others, which helped the administration take necessary actions.

I volunteered for a local charity where we organized a fundraising event. After the event, we wanted to analyze the impact of different marketing strategies on donation amounts. We gathered data from two different groups: one that received email marketing and another that received social media promotions. Since we were comparing two independent groups, I chose to use an independent t-test. This allowed us to see if there was a statistically significant difference in the mean donations between the two groups. The results showed that the email marketing group donated more, leading us to adjust our future marketing strategies.

In my first job as a data analyst at a retail company, I was tasked with analyzing customer feedback gathered through various channels. We wanted to determine if there was a difference in customer satisfaction ratings between our online and in-store shopping experiences. Given that we had two independent samples, I opted for a t-test. This decision was based on the normal distribution of our data and the requirement to compare the means. The analysis revealed that in-store shopping had higher satisfaction ratings, which prompted the management to enhance the online shopping experience based on the feedback.