Defending Dignity A Manual for National Human Rights Institutions on Monitoring Economic, Social and Cultural Rights 8.3.1. Range The first piece of information you might want to find from your data is the range; in other words, from where to where does your data stretch? Does it start with small numbers? Large numbers? Does it run from negative to positive? This is all essential information that will help you to deal with your data. Looking at the range will also help you to find errors in your data. For example, say you are looking at data related to the indicator: “Average years of schooling in the adult population”. You might find that your data ranges from 4 to 58. There is clearly a mistake; the likelihood that any adult in any country has 58 years of schooling is very small. You should go back to your data and check it. So how do you find your range? Simply go through your data and find the minimum and maximum values: the lowest and the highest, respectively. For example, say you have the following data on average years of schooling in the adult population for your own country, as well as for several neighbouring countries: 8.5, 5.8, 6.5, 7.6, 10.2, 8.4, 7.3, 7.2, 9.2, 9.3 • Question: What is the range of your dataset? • Answer: The lowest number (minimum) is 5.8 and the highest number (maximum) is 10.2. The range then is from 5.8 to 10.2. In a spreadsheet, you can do this by sorting the data from smallest to largest, or with the formulae =MIN and =MAX, using brackets to select the cells you want to include in the calculation; for example, =MIN(D12:D84). 8.3.2. Count The next important piece of information you might want to determine is how many things do you have data for. How many countries? How many households? And so on. How do you get this information from your data? Simply count it. In the dataset above, for example, there are ten observations. If the dataset is too large to count, you can use the formulae =COUNT when you have numbers in your cells or =COUNTA when you do not have numbers in your cells. Again, use brackets to select the cells you want to include in the calculation; for example =COUNTA(A5:A2089). This might seem simple. However, when it comes to analysis and interpretation of the data, it is very important. For instance, if you are comparing your data on hospitals in your country, is data for ten hospitals sufficient to make that comparison? 8.3.3. Averages The next piece of information you might want to look at is the “central value” and how the data is distributed in relation to that value. Does the central value give a good indication of the whole dataset, with an equal distribution of data points above and below it? Or is the distribution “skewed”, meaning there is a peak at one end of the data range with a long tail towards the other? The distribution tells you what kind of further descriptors are practical to use. There are a number of different ways to answer these questions. The mean (or “average”) is the most common way of looking at the “central value”. It will be familiar from reports; for example, average unemployment has increased in country X or average literacy rates have decreased for country Y. So how is the mean calculated? The mean is the sum of all the values in the dataset divided by the number of values there are. For example, say you are interested in determining the average household income. You have the following data on average annual household income, measured in dollars, for a number of households: 1120, 241, 876, 201, 112, 345, 567, 156, 154, 1345 90