For a final assignment, my two group members and I have created a biased survey called
Should Public Schools Implement a Uniform Policy? We have about 2-3 quantitative data questions, with one being
Estimate the amount of time it takes you to plan, pick out, and accessorize your outfit for school every morning.We have gathered the responses and created a table of values of the responses, which contains the frequency of each option. The chart is I have also calculated the Measures of Central Tendencies of the responses, with the mean being 5.2857 (round to 5.3), median being 6, and modes being 1 & 10 (both occur twice). There are no outliers. The part that I am having trouble with is determining which average is the most appropriate to represent my data above, and most importantly WHY is the best average. I believe that the best average is either the median or mode.
I think the
median the best average because our set of data consists of a mean, median and mode that do not equal to each other, and so our data distribution is not normally distributed. Also, our sample size only consists of students attending our high school (population consists of all high school students from our School Board). Despite there being no outliers, the median can be the better average. I think the
mode can also be the best average because the graph for the amount of time a student takes to pick, plan, and accessorize their outfit for school every morning is categorical (different time ranges), then it could represent the better average. However, the mode will not provide the better average, as it only speaks on the most occurring time ranges.
I feel like I don
t logically make sense as to why these averages are most appropriate, and that Im just throwing general facts, which is kind of incorrect in my opinion. I know that sometimes, the mode is the best way to get a representative sample of what people want, and the median splits my data into two sections, and each section has the same number of elements.
How would I be able to justify the what measure of central tendency best fits my set of data without sounding too general, too minimal, or too confusing?