Discover published sets by community

The belief that past random events affect the probabilities in future random events. For example, thinking a coin is 'due' to land on heads after several tails flips is a gambler's fallacy.

Ignoring general population statistics (base rates) when evaluating the likelihood of events. For instance, ignoring the base rate of a population's cancer prevalence when assessing the significance of a positive result from a cancer screening test.

Focusing only on the surviving examples or successes, leading to a false estimate of the total picture. A common example is when companies study successful businesses without considering the many more that have failed.

Selectively presenting only the data that supports your claim while ignoring data that contradicts it. For example, showcasing only positive customer reviews while ignoring negative ones.

A sample is collected in such a way that some members of the intended population are less likely to be included than others. For example, conducting a survey on a college campus and then generalizing the findings to all age groups.

Incorrectly inferring that one thing is the cause of another. An example would be claiming the rooster's crow causes the sun to rise.

Cherry-picking data clusters to suit an argument, or finding a pattern to fit a presumption. This fallacy is akin to a shooter firing shots at a barn wall, then painting a target around the tightest cluster of hits to claim accuracy.

The phenomenon where extreme cases tend to be closer to the average on a subsequent measure. For example, athletes with extraordinary performance one season are likely to perform closer to the average in the next season.

Mistaking a relationship for causation when there is a third variable influencing both factors. For instance, ice cream sales and shark attacks are both higher in the summer, but that doesn't mean one causes the other; the third variable is the summer season itself.

Assuming that because one event followed another, the first caused the second. An example would be believing that because a patient took a homeopathic remedy and then recovered, the remedy caused the recovery.

Making sweeping conclusions based on limited or very specific data. For example, saying that 'all swans are white' after only seeing white swans, without considering other populations.

Presenting two options as the only possibilities when in fact more options exist. For instance, claiming that 'you're either with us or against us' without allowing for neutral or alternative positions.

Presenting data in a way that visually distorts it to lead to incorrect conclusions. For example, a bar graph where the y-axis doesn't start at zero, exaggerating the differences between the bars.

The alteration of behavior by the subjects of a study due to their awareness of being observed. For example, workers might temporarily increase their productivity when they know they are being studied.