Statistics and Data Science I (ABC) CHEAT SHEET

Word Equations Summary Tables Simple Statistics

outcome = explanatory + other stuff # compute five-number summary mean(data_set$Y)
Y = X + other stuff favstats(~ Y, data = data_set) var(data_set$Y)
sd(data_set$Y)
# create frequency table
tally(data_set$Y) cohensD(Y ~ X, data = data_set)
Basics tally(~ Y, data = data_set) cor(Y ~ X, data = data_set)
print("Hello world!")
# tally by condition b1(Y ~ X, data = data_set)
# assign value to object tally(~ Y < 1900, data = data_set) b1(one_model)
myNumber <- 5
# two-way frequency table pre(Y ~ X, data = data_set)
# combine values into vector tally(Y ~ X, data = data_set, margin = TRUE, f(Y ~ X, data = data_set)
myVector <- c(1, 2, 3) format = “proportion”)

# first element in vector Data Frame

myVector[1]
# structure of data frame # arrange rows by variable
# orders values or cases str(data_set) arrange(data_set, Y)
sort(myVector)
# view first/last six rows # creates data frame from csv file
# arithmetic operations head(data_set) data_set <- read.csv("file_name", header = TRUE)
sum(1, 2, 100), +, -, *, / tail(data_set)
sqrt(157) # convert quantitative variable
abs(data_set$Y) # select multiple variables # to categorical
select(data_set, Y1, Y2) factor(data_set$Y)
# logical operations factor(data_set$Y, levels = c(1,2), labels =
>, <, >=, <=, ==, !=, |, & # first six rows of selected variables c("A", "B"))
head(select(data_set, Y1, Y2))
# results in a variable with values # transform values
# of TRUE or FALSE recode(data_set$Y, "0" = 0, "1" = 50, "2" = 100)
data_set$C <- data_set$A > data_set$B # select variable (a column)
data_set$Y # creates two equal sized groups
Probability Distribution ntile(data_set$Y, 2)
# calculate the probability area # find rows that meet condition
# convert categorical variable
xpnorm(65.1, data_set$mean, data_set$sd) data_set[data_set$Y > 40] # to quantitative
filter(data_set, Y > 300) as.numeric(data_set$Y)
zscore(data_set$Y) filter(data_set, Y != "NA")

# returns t at this probability

qt(.975, df = 999)
# returns F at this probability
qf(.95, df1 = 1, df2 = 100)

# CI using t distribution
confint(empty_model)

# calculate p-value using F-distribution

xpf(sample_F, df1 = 2 , df2 = 10)

Page: 1 ▷ Updated: 2023-04 ▷ Learn more about CourseKata @ https://coursekata.org

Statistics and Data Science I (ABC) CHEAT SHEET
Simulation Fitting and Evaluating Models
# sample without replacement # bootstrap sampling distribution of b1s, # empty model
sample(data_set, 6) # centered on sample b1 empty_model <- lm(Y ~ NULL,
sdob1_boot <- do(1000) * data = data_set)
# sample with replacement b1(Y ~ X, data = resample(data_set))
resample(data_set, 10) # use one expanatory variable
# count the number of b1s at the upper one_model <- lm(Y ~ X, data = data_set)
do(3) * resample (data_set, 10) # and lower extreme
tally(sdob1$b1 > sample_b1 | # create a function from a formula
# mixes up values in a variable sdob1$b1 < -sample_b1) one_model_fun <- makeFun(one_model)
shuffle(data_set$Y)
one_model_fun(x_level_1)
# simulate sampling 10000 Ys # return TRUE for middle 95% of distribution
# from normal distribution middle(sdob1$b1, .95) # model predictions and residuals
sim_Y <- rnorm(10000, Y_stats$mean, data_set$empty_predict <- predict(empty_model)
Y_stats$sd) # randomize sampling distribution of PREs data_set$empty_resid <- resid(empty_model)
sdoPRE <- do(1000) * PRE(shuffle(Y) ~ X,
# put simulated Ys into dataframe data = data_set) # produce ANOVA table
data_set<- data.frame(sim_Y) anova(empty_model)
# randomize sampling distribution of Fs supernova(one_model)
# simulate sampling distribution of sdoF <- do(1000) *
means fVal(shuffle(Y) ~ X, data = data_set) # t-test, using pooled variance
sim_SDoM <- do(10000) * mean(rnorm(157, t.test(Tip ~ Condition, data = data_set,
Y_stats$mean, Y_stats$sd)) # counts extreme Fs var.equal=TRUE)
tally(~fVal > sample_F, data = sdoF)
# bootstrap sampling distribution of # pairwise comparison
means # corrections: "Bonferroni" or "none"
bootSDoM <- do(10000) * pairwise(one_model, correction = "none")
mean(resample(data_set$Y, 157))

# randomize sampling distribution

# of b1s, centered on 0
sdob1 <- do(1000) *
b1(shuffle(Y) ~ X, data = data_set)

Page: 2 ▷ Updated: 2023-04 ▷ Learn more about CourseKata @ https://coursekata.org

Statistics and Data Science I (ABC) CHEAT SHEET
Visualizations
gf_boxplot(Y ~ X, data = data_set) # sampling distribution of b1
gf_histogram(~ Y, data = data_set) %>% gf_histogram(~b1, data = sdob1,
# change labels fill = ~middle(b1, .95)) %>%
gf_labs(title = "Graph Title", x = "Y_Name", # modify the limits on x- and y-axes
y = "Frequency") gf_lims(x = c(-12, 12), y = c(0, 70))

gf_point(Y ~ X, data = data_set)

# faceted grid of histograms

gf_histogram(~ Y, data = data_set) %>%
gf_facet_grid(X ~ .)

gf_point(Y ~ X, data = data_set) %>%

# add model predictions as red points
gf_point(Y ~ X , shape = 1, size = 3,
color = "firebrick") %>%
gf_jitter(Y ~ X, data = data_set) # add best fitting model as a red line
gf_model(one_model, color = “red”)

gf_dhistogram(~ Y, data = data_set, fill =

"orange") %>%
gf_density()

gf_boxplot(Y ~ X, data = data_set, fill =

"orange") %>%
gf_jitter(height = 0, alpha = .2, size = 3)
pairwise(one_model, plot = TRUE)

gf_bar( ~ Y, data = data_set)

Page: 3 ▷ Updated: 2023-04 ▷ Learn more about CourseKata @ https://coursekata.org