Missing data pattern | Description |
---|---|

Missing completely at random (MCAR) |
• Data are missing for reasons not related to observed or unobserved variables • Simple statistical approaches to deal with missing data can provide unbiased results |

Missing at random (MAR) |
• Probability of missingness is related to observed data but not to unobserved data • MAR is the assumption for most imputation methods |

Missing not at random (MNAR) | • Missingness is related to unobserved data |