91Ó°ÊÓ

The median is a popular measure of central tendency, especially useful for data sets with outliers. When we talk about the median, picture this: if you list all your data points in order, the median is smack dab in the middle. Imagine you’re looking at university employee salaries. You might find most salaries are moderate, then *bam*, a very high salary figure for a top executive. This extremely high salary pulls the mean (or average) up. However, the median remains unaffected by these extreme values.
So, for a skewed distribution, particularly like the one you’d find with salaries, the median truly shines. It keeps things fair and mellow, showing the center without getting swayed by the extremities. Using the median helps:

• Give an accurate picture of where the *middle* of your data truly is.
• Prevent distortion from those way-out-there numbers.
• Reflect what a "typical" data point looks like in a skewed series.

The mean is another key player when measuring central tendency. It's what most people think of when they hear "average" – you add up all your numbers and divide by the count of numbers. For situations like the time taken on a difficult exam, where students finish at varying times but still cluster around an average, the mean gives us a true sense of the typical experience. When data is symmetrically distributed with few outliers, the mean and median will generally be close together. This makes the mean ideal for data sets like exam times or standardized test scores, which often tend to have a symmetrical shape. The mean gives us:

• A general insight into the "center" of the data when extremes aren’t throwing it off.
• A straightforward calculation useful in symmetrical distributions.
• A reliable measure when data points are evenly spread.

The shape of the distribution is like the DNA of your data set—it tells you a lot about how your data behaves. Think of a distribution as the spread of data points across a graph. The shape could be symmetrical, like a bell curve (normal distribution), or skewed, where more data accumulates on one side. In scenarios with a normal distribution, like standardized test scores designed to display a range of abilities, data points generally spread out evenly on both sides of the mean. This normal, symmetrical shape signifies that using the mean provides a clear picture of central tendency. However, when we examine distributions such as employee salaries, which likely skew right with a tail dipping towards higher values, the median gets into the spotlight as it isn't swayed by those extremes. Understanding the shape helps decide:

• Which measure, mean or median, gives the best picture of the "center" of your data.
• How to interpret the data's spread, helping to decode its story.
• Whether to expect more extreme (outlier) values on one side.