Level 6 Level 8
Level 7

Basic statistical analysis


41 words 0 ignored

Ready to learn       Ready to review

Ignore words

Check the boxes below to ignore/unignore words, then click save at the bottom. Ignored words will never appear in any learning session.

All None

Ignore?
lm(V1 ~ V2)
linear model where response V1 is modelled by V2
aov(V1 ~ V2)
fit an analysis of variance model on V1 by a call to lm for each group (stratum) of V2
glm(V1 ~ V2, family=poisson())
generalized linear model where a response (e.g. count poisson) V1 is modelled by V2
deviance(Model)
returns the deviance of fitted model object Model
df.residual(Model)
returns the residual degrees-of-freedom extracted from fitted model object Model
influence.measures(Model)
compute regression (leave-one-out deletion) diagnostics for linear or generalized linear Model
arima(Ts, order=c(1, 0, 0))
fit an ARIMA (e.g. with order AR 1) model to a univariate time series Ts
HoltWinters(Ts)
computes Holt-Winters Filtering of a given time series Ts
stl(Ts)
decompose a time series Ts into seasonal, trend and irregular components
confint(Model)
computes confidence intervals for one or more parameters in a fitted model Model
predict(Model)
makes predictions from the results of a Model
t.test(V1, V2)
performs two sample t-tests on vectors V1 and V2
TukeyHSD(Model, which="var1")
tests differences between the means of the levels of a factor (e.g. which="var1") in Model
prop.test(x=c(25, 27), n=c(100, 100))
proportions test used for testing that probabilities in several groups are the same (e.g. 25 over 100 and 27 over 100) or that they equal a value
chisq.test(M)
performs chi-squared contingency table tests over matrix M
bartlett.test(V1 ~ V2)
performs Bartlett's test on V1 of the hypotesis that variances in each of the groups of V2 are the same
dist(M)
computes and returns the distance matrix of matrix-like object M
kmeans(M, centers=2)
perform k-means clustering on a data matrix M finding n clusters (e.g. 2 clusters/centers)
hclust(X)
hierarchical cluster analysis on a distance matrix X
prcomp(M)
performs a principal components analysis on the given data matrix M
smooth.spline(V1, V2)
fits a cubic smoothing spline given the predictor variable V1 and the response variable V2
mad(V)
compute the median absolute deviation (a robust measure of the standard deviation) of V
rnorm(10)
random generation of 10 numbers from the normal distribution
runif(10)
random generation of 10 numbers from the uniform distribution
rbinom(10, size=10, prob=0.1)
random generation of 10 numbers from the binomial distribution with parameters size (e.g. 10 trials) and prob (e.g. 0.1)
rpois(10, lambda=10)
random generation of 10 numbers from the Poisson distribution with parameter lambda (e.g. mean of 10)
pnorm(V)
distribution function of quantiles V from the normal distribution
punif(V)
distribution function of quantiles V from the uniform distribution
pbinom(V, size=10, prob=0.1)
distribution function of quantiles V from the binomial distribution with parameters size (e.g. 10 trials) and prob (e.g. 0.1)
ppois(V, lambda=10)
distribution function of quantiles V from the Poisson distribution with parameter lambda (e.g. mean of 10)
dnorm(V)
density of quantiles V from the normal distribution
dunif(V)
density of quantiles V from the uniform distribution
dbinom(V, size=10, prob=0.1)
density of quantiles V from the binomial distribution with parameters size (e.g. 10 trials) and prob (e.g. 0.1)
dpois(V, lambda=10)
density of quantiles V from the Poisson distribution with parameter lambda (e.g. mean of 10)
qnorm(V)
quantile function of probabilities V from the normal distribution
qunif(V)
quantile function of probabilities V from the uniform distribution
qbinom(V, size=10, prob=0.1)
quantile function of probabilities V from the binomial distribution with parameters size (e.g. 10 trials) and prob (e.g. 0.1)
qpois(V, lambda=10)
quantile function of probabilities V from the Poisson distribution with parameter lambda (e.g. mean of 10)
ks.test(V, "pnorm")
perform a one (or two) sample Kolmogorov-Smirnov test over V for continuous distributions (e.g. Norma with "pnorm")
optim(V, Fun)
general purpose optimization of parameters V over function Fun
library(help="stats")
shows help on additional statistical methods from pakage "stats"