What is referred to as a prejudice in the data when the sample is not representative of the population being tested?

A prejudice in the data, when the sample is not representative of the population being tested, is referred to as bias. Bias occurs when the data collection method leads to systematic errors that make the sample deviate from the characteristics of the actual population. This can result from various factors, such as selection bias, where certain groups are overrepresented or underrepresented in the sample. Bias can severely impact the validity of conclusions drawn from the data, as it can lead to misinterpretations and incorrect insights.

In contrast, an outlier refers to a data point that significantly differs from other observations, which may skew results but does not inherently imply a systematic error regarding representation. Error generally refers to inaccuracies in data collection or measurement rather than a consistent pattern of misrepresentation. The median is a statistical measure that represents the middle value in a dataset and does not relate to the issues of sample representation. Therefore, the concept of bias is crucial for researchers and data analysts to understand to ensure they draw valid, reliable conclusions from their studies.