Skip to main content

Table 6 Summary of notation and definitions

From: A survey on missing data in machine learning

Notation

Definition

b

The Bias

\(Dist_{xy}\)

The Euclidean distance

\(f(y_{obs})\)

The complete data in the data set

H

The separating hyper-plane

k

The data attributes

m

The number of observations

n

The number of observed data

p

The probability of missing data

q

The vector indicating the missingness association

R

The missing value matrix

\(v_j\)

Attributes containing missing data

w

The weight vector

\(w_j\)

Nearest neighbours

x

The input vector

\(x_i\cdot\)

The error terms for un-predicted determinants of \({\bar{y}}\)

\(X_k\)

Mean estimation

Y

The matrix of an entire data set

\(Y_m\)

The missing data in R

\(Y_o\)

The observed data in R

\({\bar{y}}\)

The predicted data