Daniel Levitin’s A Field Guide to Lies and Statistics equips readers with the critical thinking tools necessary to navigate the increasingly complex world of information. The book sheds light on how data can be manipulated, misrepresented, and misinterpreted, empowering individuals to become more discerning consumers of statistics and research findings. This summary explores two key areas covered in Levitin’s work: the art of assessing data, including averages and graphical representations, and the power of the quadrant for critical thinking.
The internet has democratized information, making it accessible to a global audience. However, this ease of access also comes with the risk of encountering misinformation and flawed interpretations of research. Levitin’s book offers strategies for approaching data with a critical eye, ensuring that we are not easily misled by biased presentations or incomplete information.
One crucial aspect of interpreting data is understanding the context in which it was collected. Where did the research take place? How many participants were involved? A small sample size can significantly impact the reliability of results. For example, observing that 20% of babies born at a small, rural hospital in a given month are female might seem unusual. However, if only 20 babies are born that month, this statistic may not be representative of broader trends.
Averages, while seemingly straightforward, can also be manipulated or misinterpreted. Consider the question: If the average family has three children, how many siblings does the average child have? The answer is not necessarily two. This discrepancy arises because counting children per family (used to calculate the family average) differs from counting siblings per child. Larger families contribute more children to the sibling count, skewing the results. Furthermore, families with no children are included in the “how many kids” statistic but not in the “how many siblings” statistic. To overcome these issues, median and mode provide a more accurate view. The median represents the middle value in a dataset, while the mode identifies the most frequently occurring value.
The representation of data can also be deceiving. Graphs, in particular, are susceptible to manipulation. Unlabeled axes, dual vertical axes with different scales, or truncated axes can distort the perception of trends. For example, an increase of 10% in variable A can be made to appear as significant as a 5% increase in variable B by manipulating the scales of the vertical axes. Similarly, omitting portions of an axis can exaggerate small changes, making them appear more substantial than they are. Cumulative graphs can also mask negative trends, such as a decline in sales during the final quarter, by presenting an overall upward trajectory.
Levitin advocates for the use of a QUADRANT FOR CRITICAL THINKING to dissect statistical claims. This method involves organizing data into a table to understand the probabilities involved, as illustrated in the following example related to breast cancer risk.
Consider this statistic: 93% of breast cancer patients fall into the high-risk group. While alarming, this statement lacks crucial context. To properly interpret this figure, we need additional information: the overall chance of a woman having breast cancer (0.8%) and the percentage of women who fall into the high-risk group (57%). Using these figures, we can construct a quadrant to calculate the actual probability of a woman in the high-risk group having breast cancer.
By filling in the quadrant, we find that a woman in the high-risk group has a 1.2% chance of having breast cancer, compared to 0.8% for women in general. While the difference is notable, it is far less alarming than the initial statistic of 93% might suggest.
Levitin’s A Field Guide to Lies and Statistics serves as a vital resource for anyone seeking to navigate the complexities of data and avoid being misled by misinformation. By understanding the importance of context, recognizing the potential for manipulation in data representation, and employing critical thinking tools like the quadrant method, readers can become more informed and discerning consumers of information. In a world saturated with data, the ability to critically assess statistics is an essential skill for making sound decisions and avoiding manipulation.
REFERENCE
Levitin, D., 2016, A Fieldguide to Lies and Statistics – A Neuroscienetist on how to Make Sense of a Complex World, London: Viking (order this book)