μ (mu) | mean value, a measure of location |
π, Π (pi) | lower-case: ratio of circumference to diameter for a circle; upper-case: product operator |
σ, Σ (sigma) | as a variable: standard deviation (lower-case) or covariance matrix (upper-case), measuring dispersion; as an operator: summation |
AIC | Akaike (pronounced "A-kye-ih-key") Information Criterion |
ANOVA | ANalysis Of VAriance |
AUC | Area Under the Curve (typically the ROC curve) |
BIC | Bayesian Information Criterion |
C_p | Colin Mallow's selection criterion for 'p' predictors |
CEO | Chief Executive Officer |
CSV | Comma Separated Values |
CV | Cross Validation |
df | degrees of freedom |
DOI | Digital Object Identifier |
EM | Expectation Maximization |
ESL | The Elements of Statistical Learning |
F | A variable that arises as the ratio of two chi-squared variables; named for Ronald Fisher, as in F statistic, F distribution, F test |
FN | False Negative [Actual = Positive; Prediction = Negative] |
FP | False Positive [Actual = Negative; Prediction = Positive] |
GAM | Generalized Additive Model |
GLM | Generalized Linear Model |
HTTP | Hyper Text Transfer Protocol |
ISBN | International Standard Book Number |
ISL | Introduction to Statistical Learning |
ISLR | An Introduction to Statistical Learning with Applications in R |
ISSN | International Standard Serial Number |
K | A variable that represents a count; e.g. K Nearest Neighbor, K Fold Cross Validation, K Means |
KNN | K Nearest Neighbor |
l0, l1, l2 | Lesbegue space, where the norm is defined as the "p"-th root of the sum of abolute values raised to the "p"-th power |
LASSO | Least Absolut Shrinkage and Selection Operator |
LDA | Linear Discriminant Analysis |
log | logarithm [base is 'e' (Euler's number), unless specified otherwise] |
MASS | Modern Applied Statistics with S |
ML | Machine Learning |
MLP | Multi-Layer Perceptron |
MNIST | Modified National Institute of Standards and Technology data |
MSE | Mean Squared Error |
n | A variable that represents the number of observations in a sample |
NaN | Not a Number |
NCI | National Cancer Institute |
NLL | Negative Log Likelihood |
OJ | Orange Juice |
OOB | Out Of Bag |
p | A variable that represents the number of predictors |
p value | the probability of a false rejection of the null hypothesis |
PCA | Principal Components Analysis |
PCR | Principal Components Regression |
PLS | Partial Least Squares |
PVE | Proportion of Variance Explained |
QDA | Quadratic Discriminant Analysis |
R | A freeware version of the S language for statistical analysis by Robert and Ross (Robert Gentleman and Ross Ihaka) |
R^2 | A measure of error reduction for a model (compared to the null model, with no predictors) |
ROC | Receiver Operating Characteristic |
RSE | Residual Standard Error |
RSS | Residual Sum of Squares |
S | A language for statistical analysis |
SGD | Stochastic Gradient Descent |
SSE | Sum of Squared Errors |
SVD | Singular Value Decomposition |
SVM | Support Vector Machine |
t | A variable often used for a test statistic, as in t statistic, t distribution, t test |
^T | Transpose: an 'n' x 'p' matrix is changed to a 'p' x 'n' matrix by exchanging the row and column indices; i.e. element[i,j] becomes element[j,i] |
TN | True Negative [Actual = Negative; Prediction = Negative] |
TP | True Positive [Actual = Positive; Prediction = Positive] |
TSS | Total Sum of Squares |
TSV | Tab Separated Values |
US | United States |
USA | United States of America |