We have been discussing measures of center of data sets including means and Mean Absolute Deviation (average of distances from mean). We have been talking about the difference between sample means and population means and how their distributions differ. We have been emphasizing that the more data that is gathered, the closer a sample mean will approach the population mean. We gathered sample means from the same population (used excel to generate a random sample of data) and analyzed how our sample means from the same population data were different. Today, (Thurs) we are looking at whether two sample means of populations are different using MADs and interquartile ranges (difference between 1st and 3rd quartiles; this is not the rigorous tests of an upper-level statistics course, but a simplified version to explore how far apart data means/medians are). Friday of this week and Monday of next week we will conduct a population sampling experiment (tag and release) using dried beans of different varieties. We will try to use our tag/release algorithms to see if we can determine the actual percentage of each beans existing in the population (which I will create using ratios of cups to the whole, but I am not counting all the beans to verify actual percentages).