Data Analysis Super Big Flashcard Set

an exhaustive list of near everything we've learned this semester (so far)

< -

stores value in object

=

assigns values or specifies function arguments

+

addition

-

subtraction

*

multiplication or interaction effects in ANOVA

/

division

^

raises number to a power

%%

returns remainder

==

tests equality

!=

not equal to

>

greater than

<

less than

>=

greater than or equal to

<=

less than or equal to

!

reverses logical value (true becomes false) ; means NOT ; df [ !(df$a >3), ] keep rows where a is NOT greater than 3

&

logical and ; both conditions must be true

|

logical or ; one condition must be true

:

creates a sequence

( )

function call or order of operations

[ ]

extracts element by position

[ [ ] ]

extracts specific component from a list ; returns the actual element itself

$

accesses columns or list

{ }

group code together

~

formula notation ; aov(response variable ~ factor)

%>%

passes output one step to the next

?

help

c( )

combines values into a vector ; vector contains elements that are same type (numeric, character, etc. )

mean( )

calculates mean

sum( )

adds values together

class( )

shows the object type (numeric, character, data.frame, etc.)

str( )

displays object structure

is.integer( )

checks if values or integer

is.character( )

checks if values are character strings

is.na( )

check for missing values

as.numeric( )

converts data to numeric

as.logical( )

converts data to TRUE/FALSE

as.factor( )

converts data to factor ; ANOVA

factor( )

creates categorical variables

seq( )

creates sequences

rep( )

repeats values

sqrt( )

calculates square root

log( )

calculates natural logs

data.frame( )

creates a data frame ; combine vectors into a structured table format ; like a spreadsheet

list( )

creates a list

matrix( )

creates a matrix

table( )

creates frequency table (?)

sort( )

sorts values smallest to largest

order( )

returns positions in order ; x ← c(0, 20, 10, 15) output is 1 3 4 2 since smallest number is at position 1, next smallest is 3, then 4, then 2 (why would you ever do it this way)

rank( )

assigns ranks to values ; x← c(3, 1, 4, 15, 92) output is 2 1 3 4 5

rowSums( )

adds values across rows

colMeans( )

calculates means of columns

subset( )

filters rows using conditions

aggregate( )

summarizes data by groups

tapply( )

applies a function to groups

group_by( )

creates groups for summaries

summarise( )

produces summary statistics

levels( )

displays factor levels

sd( )

calculates standard deviation

var( )

calculates variance

qt( )

returns t critical values

t.test( )

performs a t-test

aov( )

performs ANOVA

summary( )

shows statistical results

TukeyHSD( )

post-hoc after ANOVA

residuals( )

returns model residuals

shapiro.test( )

tests normality

sample( )

generates a random sample

rnorm( )

generates random normal values

set.seed( )

same sequence of random numbers is produced each time the code is run

plot( )

creates base plots in R

barplot( )

creates bar chart

boxplot( )

creates a boxplot

hist( )

creates a historgram

ggplot( )

starts a ggplot graph

aes( )

axes

geom_point( )

creates scatterplot points

geom_line( )

creates line graph

geom_bar( )

creates bar plot

geom_col( )

creates bars from supplies values

geom_boxplot( )

creates boxplot

geom_historgram( )

creates histograms

geom_smooth( )

adds trend lines

geom_errorbar( )

adds error bars

labs( )

adds titles and labels

theme( )

customize plot appearance

theme_classic( )

applies theme to plot

scale_y_continuous

modifies the y-axis scale

sec_axis( )

creates secondary axis

ggsave( )

saves ggplot as image

manova( )

performs MANOVA ; multiple response variables

cbind( )

combines objects by columns

rbind( )

combines objects by rows

summary.aov( )

produces ANOVA summaries ; or use summary(model1) or whatever you names the ANOVA

lm( )

fits linear regression model

paired = TRUE

means R treats each value in group1 as matched with the value in the same position in group2

residuals

observed - predicted ; tells us how far each observation is from what the model predicted

mtcars[mtcars$mpg > 25, ]

the comma means only keep rows where mpg > 25 but keep all columns