Sunday 20 February 2022

Misleading Graphs

Misleading Graphs



Graphs are very useful in our daily lives. It is a way to present statistics as a form as evidence in order to back up a claim. However, there are also many ways a graph can be used to mislead an audience in order to try and fool someone. For example, in this graph the data represented here is on the number of COVID-19 tests per million of people. When the graph is formed this way, many people will assume Norway has had the most Covid tests out of all of these countries, however this graph fails to mention the population of each country and how small the country of Norway is compared to the country of US or Brazil. Below are some examples as to how a graph can fool you

1. Different Colours (colours are generally correlated for positive or negative effects)
2. Unique name of Axis (May cause the graphs to alter in shape and suggest other things)
3. Causation vs Correlation (Two different variables put in a graph may not mean that they are affected by each other)
4. Scaling of the axis and whether it starts at 0

No comments:

Post a Comment

Machine Learning

Today I learnt about decision trees. Decision trees are algorithms that classify things according to their features. To train the machine, a...