What is sampling bias?
A type of error that occurs when a sample is collected in such a way that it is not representative of the population it is intended to represent
sampling bias explained in plain English
Sampling bias happens when the way data is collected influences the results, making them not accurately reflect the whole group or population being studied
Analogy
Imagine trying to determine the average height of all people in a city by only measuring the heights of basketball players, the results would be skewed and not representative of the entire city's population
Example
A survey about a new policy that is only conducted on social media may be biased towards younger, more tech-savvy individuals and not representative of the entire population
How is sampling bias used?
Sampling bias can occur in various fields such as medicine, social sciences, and marketing research, and can lead to incorrect conclusions and decisions if not addressed
Common misconceptions about sampling bias
One common misconception is that a large sample size can eliminate sampling bias, but even with a large sample, bias can still occur if the sample is not collected in a way that represents the population
History
The concept of sampling bias has been recognized and studied in statistics and research methods for many decades, with early discussions dating back to the 19th century
People also read
- attribute
A characteristic or feature of an object or concept
- automation bias
The tendency to over-rely on automated systems and ignore or underweight human judgment
- bias
A systematic error or distortion in a machine learning model's results
- bias (math) or bias term
A constant added to a linear combination of inputs in a machine learning model
- calibration layer
A component in a neural network that adjusts the output to match the true probabilities of a task
- Confabulation
When an AI produces a confident, fluent answer that sounds true but is factually wrong — generating plausible language without a reliable link to reality.
- confirmation bias
The tendency to favor information that confirms existing beliefs or expectations
- counterfactual fairness
A fairness metric in AI that ensures decisions are fair by comparing actual outcomes with hypothetical outcomes where a sensitive attribute is different
- coverage bias
A type of bias that occurs when the data used to train a model does not accurately represent the population or phenomenon being studied
- demographic parity
A fairness metric in machine learning that ensures equal outcomes for different demographic groups