Lane Kenworthy, The Good Society
December 2025

Some of the evidence we look to in attempting to understand societies, institutions, policies, and outcomes is quantitative. One of the best ways to evaluate quantitative information is in graphical form. Pictures convey information more efficiently than written text — a picture, as the saying goes, is worth a thousand words. And it turns out that showing information graphically tends to reduce misperceptions. Graphs, in other words, give us a lot of information, and they give it to us in a way that usually improves our understanding of that information.

Here is a brief introduction to two common types of graph: line graphs and scatterplots.

LINE GRAPH

Graphs nearly always have a horizontal axis and a vertical axis. Sometimes we call the vertical axis the “Y” axis and the horizontal axis the “X” axis. You don’t need to worry about why; just know that this is commonly-used lingo.

Figure 1 is a line graph. Typically a line graph shows a value over time.

Figure 1. Public social programs
Share of GDP. Data source: Esteban Ortiz-Ospina and Max Roser, “Public Spending,” Our World in Data, using data for 1880-1930 from Peter Lindert, Growing Public, volume 1, Cambridge University Press, 2004, data for 1960-1979 from OECD, “Social Expenditure 1960-1990: Problems of Growth and Control,” OECD Social Policy Studies, 1985, and data for 1980ff from OECD, Social Expenditures Database. “Asl” is Australia; “Aus” is Austria.

The horizontal axis in this graph represents time. Here time is measured in years. That’s common, but time could be measured in months or days or hours or decades or centuries.

The value shown on the vertical axis of the graph is the share of a country’s gross domestic product (GDP) that its government spends on social programs. This is a common measure of the size of a country’s safety net, it’s welfare state.

A line graph could have this information for just one country, but this graph shows the information for all of the world’s rich longstanding-democratic nations.

There’s a lot of information in this graph, but two pieces of information are especially important. First, we can see that the values for all of the countries increase over time. All of these countries had either no welfare state or a very tiny one as recently as 1930. Since then, government social programs have grown steadily in size and scope, such that they now account for, on average, about 25% of GDP in these countries. In other words, about one out of every four dollars in the economy goes to the government in taxes and is spent on a program such as pensions for retirees, healthcare, assistance for the unemployed, childcare, paid parental leave, or others.

The second key piece of information is that while all of the countries share this general pattern of a steady rise over the past century, they also differ. The government safety net is larger in some countries than in others.

SCATTERPLOT

The graph in figure 2 is called a scatterplot. It has values of something on the horizontal axis and values of something else on the vertical axis. And the thing on the horizontal axis usually isn’t time.

Figure 2. Life satisfaction by GDP per capita across countries
The dots are 126 countries. 2019. Life satisfaction: scale is 0 to 10. GDP per capita: in purchasing-power-parity-adjusted dollars. “k” = thousand. Data sources: Gallup World Poll and World Bank, via the World Happiness Report 2020, online appendix. The line is a loess curve.

In this scatterplot a country’s wealth, measured as GDP per capita, is on the horizontal axis. Life satisfaction, a common measure of happiness, is on the vertical axis. The data points are countries.

With a scatterplot we typically are looking to see if there is a correlation between the two things. Often we think one of the things may be causing the other. We put the hypothesized cause on the horizontal axis and the hypothesized outcome on the vertical axis. So for this graph the hypothesis would be that a country’s wealth affects how happy people are.

The line in the graph summarizes the correlation between national wealth and happiness. Because it goes from lower left to upper right, it suggests a positive association. In other words, the higher the wealth of a country, the happier it’s citizens tend to be. The line here actually is a curve, but often this type of graph will have a straight line.

When it comes to the correlation in a scatterplot, we typically want to think about three questions: First, is there a correlation? Second, is it positive or negative? Third, is it strong or weak? In the graph here, there is a correlation. It’s a positive correlation. And it’s a fairly strong one.

How can we tell if it’s a strong one? It’s strong if a difference in the hypothesized cause is associated with a large difference in the outcome. Here people in countries that are richer tend to be a lot happier, not just a little happier.

How do we know they’re a lot happier? We can see in the graph’s footnote that life satisfaction is measured on a scale of 0 to 10. The line suggests that countries with low GDP tend to have an average life satisfaction of perhaps 4 on this scale, whereas in rich ones life satisfaction tends to be around 7. That seems like a pretty big difference. It would be a small effect if poor countries had an average life satisfaction of 4 and in rich countries it was only, say, 4.2.

To understand a graph, it helps to read the footnote that comes with it, which usually is located below the graph. The footnote will have information about the measures used, the data sources, and sometimes other things. It’s almost always worth taking a minute to read it.