Goal:
The data below shows (in order) the date, median, average, high and low of a survey taken on each of the dates. Out of the data set, the average or median of each row will be used for future analysis.
Date Med (K) Avg (K) High (K) Low (K)
8/14/2003 73 74 81 65
8/21/2003 105 109 90 135
8/28/2003 70 70 80 58
09/04/2003 73 72 82 59
09/11/2003 91 99 78 130
9/18/2003 95 95 109 78
Q1. Based off of the columns of data available, is there enough data to determine whether or not each row is skewed or symmetrical, and to thus base on whether to take the average or median for that row?
My idea was that maybe this could be achieved by observing where the average and median fall between high and low.
Q2. For rows where the median and average are close together, for example, row 1 where the median = 73K and average = 74K, which of these two values could be chosen for further calculations?
Being new to statistics, the language or understanding of methods in this question may be inaccurate, so apologies if this is the case.