Censored data

Censored Data

Censored data (pronunciation: /ˈsensərd ˈdeɪtə/) is a type of data that is not fully observed or recorded, but is known to exist within certain constraints. This type of data is commonly encountered in medical research and statistical analysis.

Etymology

The term "censored" in this context originates from the statistical term "censoring", which refers to the process of limiting, modifying, or suppressing data that is considered unacceptable or irrelevant. The term "data" is derived from the Latin word "datum", which means "something given".

Definition

Censored data refers to data that is incomplete due to it being cut off at a certain point. This can occur for a variety of reasons, such as the end of a study period or the loss of contact with study participants. Despite this, censored data can still provide valuable information, as it indicates that the event of interest has not occurred up to the point of censoring.

Types of Censored Data

There are several types of censored data, including:

Right-censoring: This occurs when the event of interest has not yet occurred by the end of the study period.
Left-censoring: This occurs when the event of interest has occurred before the start of the study period.
Interval-censoring: This occurs when the exact time of the event is unknown, but it is known to have occurred within a certain interval.

Related Terms

Survival analysis: A branch of statistics that deals with the analysis of time-to-event data, which often involves dealing with censored data.
Kaplan-Meier estimator: A non-parametric statistic used to estimate the survival function from lifetime data, often used in the presence of censored data.
Cox proportional hazards model: A regression model commonly used in medical research for investigating the association between the survival time of patients and one or more predictor variables.