Index

Accuracy

Additive model

Alcohol

Alternative hypothesis

ARIMA

Association rule

Assumptions

Astronomy

Audit

Baseline

Bias

Binomial distribution

Binomial sample

Binomial trial

Birth order

Blinding

Blocking

Bootstrap

bias-corrected

caveats

parametric

percentile

Box and whiskers plot

Box plot

Boyle’s Law

Carcinogen

CART (see Decision tree)

Cause and effect

Cell culture

Census

Chemistry

Classification

Clinical trials

Cluster sampling

Coefficient

Combinations

Conditional probability

Confidence interval

Confound

Contingency table

Continuous scale

Controls

Correlation

Covariance

Craps

Cross-validation

Cumulative distribution

Cut-off value

Data collection

Data files

creating

editing

retrieving

spreadsheet

storing

Data type

categorical

continuous

discrete

metric

ordinal

Debugging

Decimal places

Decision tree

Decisions

Degrees of freedom

Dependence

Deviations

Dice

Digits

Distribution

binomial

Cauchy

center

continuous vs. discrete

empirical

exponential

mixtures

normal

sample mean

Domain expertise

Dose response

Dropouts

Editing files

Effect size

Election

Empirical distribution

Epidemic

Equally likely events

Equivalence

Errors, observational

Estimation

consistent

minimum variance

point

unbiased

Ethnicity

Events

Examples

agriculture

astrophysics

bacteriology

biology

botany

business

climatology

clinical trials

economic

education

epidemiology

genetics

geologic

growth processes

hospital

law

manufacturing

marketing

medicine

mycology

physics

political science

psychology

sports

toxicology

welfare

Exact tests

Exchangeable observations

Expected value

Experimental design

Experimental unit

Extreme values

Factorial

FDA

FTC

Fisher’s exact test

Fisher-Freeman Halton test

Fisher’s omnibus statistic

Geiger counter

GIGO

Goodness of fit

measures

vs. prediction

Graphs

Greek symbols

Group sequential design

Growth processes

Histogram

HIV

Horse race

Hospital

House prices

Hotelling’s T²

Hypothesis

formulation

testing

Independence

Independent events

Independent identically distributed variables

Independent observations

Interaction

Intercept

Interdependence

Interpreter

Interquartile range

Invariant elimination

Jury selection

Likert scale

Logarithms

Long-term studies

Losses

Lottery

Marginals

Market analysis

Martingale

Matched pairs

Matrix

Maximum

Mean, arithmetic

Mean, geometric

Mean squared error

Median

Meta-analysis

Minimum

Misclassification costs

Missing data

Modes

Model

additive

choosing

synergistic

Moiser’s method

Monotone function

Monte Carlo

Multinomial

Multiple tests

Mutually exclusive

Mutagen

Nonrespondents

Nonresponders

Nonsymmetrical (see Skewed data)

Normal data

Null hypothesis

Objectives

Observations

exchangeable

identically distributed

multivariate

Omnibus test

One- vs. two-sided

Ordered hypothesis

Outcomes vs. events

Outliers

Parameter

Pearson correlation

Pearson χ²

Percentile

Permutation

Permutation methods

Pie chart

Placebo effect

Poisson distribution

Population

dispersion

Power

vs. Type II error

Precision

Prediction

Predictor

Preventive measures

Prior probability

Probability

Protocol deviations

p-value

Quantile (see Percentile)

Quetlet index

R functions

R programming tip

Random numbers

Randomize

Range

Ranks

Rearrangement

Recruitment

Recursion

Regression

Deming or EIV

LAD

linear

multivariable

nonlinear

OLS

quantile

stepwise

Regression tree (see Decision tree)

Reportable elements

Research objectives

Residual

Response variables

choosing

surrogate

Retention

Retrieving files

from MS Excel

rh factor

Robust

Rounding

Roulette

R-squared

Sample

precision

random

representative

size

splitting

Sampling

adaptive

clusters

method

sequential

unit

Scatter plot

Selectivity

Sensitivity

Shift alternative

Significance, statistical vs. practical

Significance level

Significant digits

Simulation

Skewed data

Single- vs. double-blind

Software

Standard deviation

Standard error

Statistics

choosing

vs. parameters

Stein’s two-stage procedure

Strata (see Blocking)

Strip chart

Student’s t

Sufficient statistic

Support

Survey

Synergistic

Terminal node

Tests

assumptions

exact

k samples

one-sided

one- vs. two-sided

one vs. two-sample

optimal

paired t-test

permutation vs. parametric

robust

two-sided

Treatment allocation

Type I, II errors

Units of measurement

Validation

Variance

Variation

sources

Venn diagram