How would you respond to each of the 2 responses indicated below to the question. The question was:
Every year the government shares with us the US Household Median Income. We know that both mean and median are central measures. Why is the Median Income used and not the Average? What do you believe that the average income will be? What type of datasets have similar mean and median? What type of datasets have different mean and median?
The Median income (53,657) is used and not average because the Median is more symmetrically/continues distributed data. Maybe the data was skewed (You can use the average or median when the population is symmetrical because they will give you almost an identical result.) I believe that the average income would be a lot less and inaccurate. Interval/ratio datasets have similar mean and median. Nominal datasets use mode to calculate so they have different mean and median.
The reason that the government reports the Median Income is because the mean would be skewed higher due to extremes. The wealthiest 1% of Americans make significantly more than the rest of the country and if the government reported the mean it would be significantly higher than what the middle American actually makes.
The types of data sets that have a similar mean and median are data sets without outliers. Also data sets with a normal distribution have a similar mean and median. On the contrary, data sets with different mean and medians are data sets with outliers. The US Household Median Income would be a perfect example of a data set that has a different mean and median.