🏠 홈
벤치마크
📊 모든 벤치마크 🦖 공룡 v1 🦖 공룡 v2 ✅ 할 일 목록 앱 🎨 창의적인 자유 페이지 🎯 FSACB - 궁극의 쇼케이스 🌍 번역 벤치마크
모델
🏆 톱 10 모델 🆓 무료 모델 📋 모든 모델 ⚙️ 킬로 코드 모드
리소스
💬 프롬프트 라이브러리 📖 AI 용어 사전 🔗 유용한 링크

AI 용어집

인공지능 완전 사전

162
카테고리
2,032
하위 카테고리
23,060
용어
📖
용어

Missing Completely At Random (MCAR)

Mechanism where the probability that an observation is missing depends neither on the observed data nor on the missing data. The missing data represent a simple random subset of the complete dataset.

📖
용어

Missing At Random (MAR)

Mechanism where the probability of missing data depends only on the observed values but not on the missing values themselves. This pattern allows for correction by imputation conditional on the observed variables.

📖
용어

Missing Not At Random (MNAR)

Mechanism where the probability of missing data depends directly on the missing values themselves. Standard imputation methods can introduce significant bias in this case.

📖
용어

Little's MCAR Test

Statistical hypothesis test with null hypothesis that the data are missing completely at random (MCAR). Based on comparing means and covariances between complete and incomplete cases.

📖
용어

Pattern Matrix

Binary matrix indicating the presence (1) or absence (0) of data for each observation and variable. Allows for visual identification of complex missing data structures.

📖
용어

Missing Data Mechanism

Underlying process that generates missing data in a dataset. Includes three main mechanisms: MCAR, MAR and MNAR, each requiring different treatment approaches.

📖
용어

Complete Case Analysis

Analysis method using only observations without any missing values. Simple to implement but can lead to significant data loss and biases if MCAR is not verified.

📖
용어

Available Case Analysis

Approach using all available data for each statistical calculation, allowing different sample sizes according to variables. Includes pairwise and listwise deletion methods.

📖
용어

Monotone Missing Pattern

Structure where if a variable is missing for an observation, all subsequent variables in a predefined order are also missing. Greatly simplifies multiple imputation methods.

📖
용어

Missingness Correlation

Measure of the association between missing data patterns of different variables. A strong correlation may indicate an MAR mechanism or suggest structural relationships in the data.

📖
용어

Missing Data Visualization

Set of graphical techniques (heatmaps, barplots, pattern plots) to explore and communicate the structure and extent of missing data. Essential for preliminary diagnosis.

📖
용어

Response Rate Analysis

Systematic evaluation of response rates by variable, by group, or over time. Allows identification of factors associated with non-response and detection of potential biases.

📖
용어

Missing Data Diagnostics

Comprehensive process of evaluating the characteristics, patterns, and mechanisms of missing data before imputation. Combines statistical analyses and visualizations to guide appropriate treatment.

📖
용어

Arbitrary Missing Pattern

Missing data structure without particular organization where absences can occur anywhere in the dataset. Requires more sophisticated imputation methods like MICE.

📖
용어

Missing Data Profile

Synthetic report describing the distribution, patterns, and characteristics of missing data. Includes descriptive statistics and visualizations for overall assessment.

🔍

결과를 찾을 수 없습니다