## Introduction

First, let define and distinguish the terms Population, and Sample

– If the data consist of all possible observations of a certain phenomenon, we call it Population
– If the data contains only a part of these observations, we call it Sample
Often, we need to represent a set of data in terms of a single (or a few) number
These are what we usually call Descriptive Statistics
Which kind of number we choose depends on the particular characteristics we
want to describe

• We start considering those measures which describe the center or middle of a set of
data, the measures of Central Location
Vives

## Median

Sometimes, samples contain very small or very large values that substantially affect
the Mean, and its ability in describing properly the data

• These values are usually called outliers
Example: Five light bulbs burned for 867,849,840,852,822 hours. The mean is 4230/5 = 846. If
we record incorrectly the second value, that is 489 instead of 849, the mean would be 3870/5=774
To avoid the problems related with the presence of outliers, we can use another
measure of central location: the Median
• The Median of a set of data is the value of the middle item when the data are
ordered (in an increasing or decreasing order)
Example: Eleven large corporations reported that in 2013 they made cash donations to
9,16,11,19,11,10,13,12,6,9,12 colleges
! Arranging in an increasing order: 6 9 9 10 11 11 12 12 13 16 19
) The Median is 11
Vives