Glossary

abstract syntax tree (AST)
FIXME
accuracy (AST)
FIXME
aggregation
FIXME
alias
FIXME
alternative hypothesis
FIXME See also: null hypothesis, *p* value.
Amdahl's Law
FIXME
analysis of variance (ANOVA)
FIXME
automatic variable
FIXME
Bayes' Rule
FIXME
Benjamini-Hochberg *p* value correction
FIXME
Bernoulli distribution
FIXME
Bessel correction
FIXME
bin
FIXME
binomial distribution
FIXME
blob
FIXME
Bonferroni correction
FIXME See also: *p* hacking, *p* value.
Boolean
Relating to a variable or data type that can have either a logical value of true or false. Named for George Boole, a 19th century mathematician.
box-and-whisker plot
FIXME
broadcast
FIXME
build action
FIXME
build prerequisite
FIXME
build rule
FIXME
build target
FIXME
build tool
FIXME
Central Limit Theorem
FIXME
central moment
FIXME
character encoding
FIXME
Chebyshev's Inequality
FIXME
chi-square test
FIXME
Cliff's $$\delta$$
FIXME
Cohen's *d*
FIXME
Cohen's kappa coefficient
FIXME
comma-separated values (CSV)
FIXME
conditional probability
FIXME
confidence interval
FIXME
continuity correction
FIXME
convergence
FIXME
convolution
FIXME
correlation
FIXME
covariance
FIXME
covariance matrix
FIXME
cumulative distribution function (CDF)
FIXME
curve fitting
FIXME
data manifest
FIXME explain where data comes from.
data science
Statistics, but less rigorous and better paid.
dataframe
FIXME
de-anonymization
FIXME
degrees of freedom
FIXME
dependent variable
FIXME See also: response variable.
descriptive statistics
FIXME
docstring
FIXME
effect size
FIXME
escape character
FIXME
event
FIXME
expected value
FIXME See also: mean.
explanatory variable
A variable whose value is an input to a statistical model rather than being predicted by it. Explanatory variables determine the values of response variables.
F measure
FIXME
F test
FIXME
false negative
FIXME
false positive
FIXME
fat arrow function
FIXME
filter
FIXME
Gamma distribution
FIXME
Gamma function
FIXME
geometric distribution
FIXME
Gini coefficient
FIXME
goal-question-metric (GQM)
FIXME
Greenhouse-Geisser correction
FIXME
gzip
FIXME
harmonic mean
FIXME
header row
FIXME
hero developer
FIXME
histogram
FIXME
independent variable
FIXME See also: explanatory variable.
interquartile range (IQR)
FIXME
ISO date format
FIXME
jitter
FIXME
Kano scale
FIXME
key
FIXME
Kruskal-Wallis test
FIXME
learner persona
A brief description of an idealized learner that captures key demographic features of a lesson’s intended audience.
Likert scale
FIXME
linear regression
A modeling technique that assumes y = ax+b where y is a response variable and x is an explanatory variable.
linter
FIXME
Little's Law
FIXME
logistic regression
FIXME
long tail
FIXME
Lorenz curve
FIXME
magic number
FIXME
main driver
FIXME
Mann-Whitney U test
FIXME Also known as a Wilcoxon rank sum test test.
Martha's Rules
A simple set of guidelines for consensus-based decision making.
Mauchly's test for sphericity
FIXME
maximum likelihood estimation
FIXME
mean
FIXME
median
FIXME
method chaining
FIXME
method of moments
FIXME
minification
FIXME
multiple linear regression
FIXME
n-gram analysis
FIXME
negative binomial distribution
FIXME
negative binomial regression
FIXME
Noble's Rules
A simple set of guidelines for organizing a small data analysis project.
normal distribution
FIXME
Not Available (NA)
FIXME
Not a Number (NaN)
FIXME
nuisance factor
FIXME
null
FIXME
null hypothesis
FIXME See also: , *p* value.
one-sided distribution
FIXME
one-sided test
FIXME See also: two-sided test.
outlier
FIXME
overdispersion
FIXME
*p* hacking
FIXME See also: Bonferroni correction, *p* value.
*p* value
FIXME See also: alternative hypothesis, null hypothesis.
pair programming
FIXME
pattern rule
FIXME
Pearson correlation coefficient
FIXME
percentile
FIXME
personal identifying information (PID)
FIXME
phony target
FIXME
Poisson distribution
FIXME
pooled sample variance
FIXME
population
FIXME
population moment
FIXME
power law distribution
FIXME
pre-registration
FIXME
precision
FIXME
principal component analysis (PCA)
FIXME
probability density function (PDF)
FIXME
probability mass function (PMF)
FIXME
property
FIXME
quartile
FIXME
queueing theory
FIXME
random number generator (RNG)
FIXME
rank correlation
FIXME
raster graphics
FIXME
recall (AST)
FIXME
regular expression
FIXME
relational database
FIXME
reproducible research
FIXME
response variable
A variable whose value depends on (and hopefully can be predicted from) the value of an explanatory variable.
right censoring
FIXME
sample
FIXME
sample moment
FIXME
sample variance
FIXME
Scalable Vector Graphics (SVG)
FIXME
seed
FIXME See also: random number generator.
Shapiro-Wilk test
FIXME
sigmoidal curve
FIXME
slice
FIXME
sliding window
FIXME
smoothing
FIXME
Spearman's rank correlation
FIXME
SQL
FIXME
standard deviation
FIXME
standard normal distribution
FIXME
standard uniform distribution
FIXME
state machine
FIXME
statistic
FIXME
statistical model
FIXME
*t* distribution
FIXME
*t* test
FIXME
tar
FIXME
Taschuk's Rules
A simple set of guidelines for writing robust data analysis scripts.
test-driven development
FIXME
throttle
FIXME
tidy data
Tabular data that satisfies four conditions: 1. Each column contains one statistical variable (i.e., one property that was measured or observed).
  1. Each different observation is in a different row. 3. There is one table for each set of observations. 4. If there are multiple tables, each table has a column containing a unique key so that related data can be linked.
two-sided test
FIXME See also: one-sided test.
uniform distribution
FIXME
utilization
FIXME
variance
FIXME
vector graphics
FIXME
violin plot
FIXME
Visitor pattern
FIXME
weighting
FIXME
wheel
FIXME
Wilcoxon rank sum test
Another name for the Mann-Whitney U test.
Wilcoxon signed rank test
FIXME
YAML
FIXME
Z test
FIXME
Zipf's Law
An empirical rule stating that frequency is inversely proportional to rank.
Zipf-Mandelbrot distribution
FIXME