Introduction heading

Hello world! Test - italics, bold, link

To do headings “#”, subheadings “##” or “###” or…

Unordered lists: - first item - second item

Ordered lists: 1. first 2. second

We can insert an image like this: alt text

We can add citations 1

R Code

values <- rnorm(5)
values
## [1] -0.3548660 -0.3427437  0.3367141 -0.3111891  1.4513610

R Code

eval=FALSE - do not run code (only input) echo=FALSE - do not show code (only output)

R Code - eval=FALSE

values <- rnorm(5)
values

R Code - echo=FALSE

## [1] -0.14688084 -1.32246017  0.85901799 -0.01430145 -2.90588176
library(ggplot2)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
data(ToothGrowth)
View(ToothGrowth)

Group 2 (ToothGrowth)

Load the ‘toothGrowth’ data set using this code:

{data(ToothGrowth)}

1. Describe and summarize your assigned data set.

head(ToothGrowth)
##    len supp dose
## 1  4.2   VC  0.5
## 2 11.5   VC  0.5
## 3  7.3   VC  0.5
## 4  5.8   VC  0.5
## 5  6.4   VC  0.5
## 6 10.0   VC  0.5
tail(ToothGrowth)
##     len supp dose
## 55 24.8   OJ    2
## 56 30.9   OJ    2
## 57 26.4   OJ    2
## 58 27.3   OJ    2
## 59 29.4   OJ    2
## 60 23.0   OJ    2
dim(ToothGrowth)
## [1] 60  3
nrow(ToothGrowth)
## [1] 60
ncol(ToothGrowth)
## [1] 3
names(ToothGrowth)
## [1] "len"  "supp" "dose"
str(ToothGrowth)
## 'data.frame':    60 obs. of  3 variables:
##  $ len : num  4.2 11.5 7.3 5.8 6.4 10 11.2 11.2 5.2 7 ...
##  $ supp: Factor w/ 2 levels "OJ","VC": 2 2 2 2 2 2 2 2 2 2 ...
##  $ dose: num  0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 ...
summary(ToothGrowth)
##       len        supp         dose      
##  Min.   : 4.20   OJ:30   Min.   :0.500  
##  1st Qu.:13.07   VC:30   1st Qu.:0.500  
##  Median :19.25           Median :1.000  
##  Mean   :18.81           Mean   :1.167  
##  3rd Qu.:25.27           3rd Qu.:2.000  
##  Max.   :33.90           Max.   :2.000
View(ToothGrowth)
dplyr library
glimpse(ToothGrowth)
## Rows: 60
## Columns: 3
## $ len  <dbl> 4.2, 11.5, 7.3, 5.8, 6.4, 10.0, 11.2, 11.2, 5.2, 7.0, 16.5, 16.5,…
## $ supp <fct> VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, VC, V…
## $ dose <dbl> 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 1.0, 1.0, 1.0, …
skim library
library(skimr)
skim(ToothGrowth)
Data summary
Name ToothGrowth
Number of rows 60
Number of columns 3
_______________________
Column type frequency:
factor 1
numeric 2
________________________
Group variables None

Variable type: factor

skim_variable n_missing complete_rate ordered n_unique top_counts
supp 0 1 FALSE 2 OJ: 30, VC: 30

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
len 0 1 18.81 7.65 4.2 13.07 19.25 25.27 33.9 ▅▃▅▇▂
dose 0 1 1.17 0.63 0.5 0.50 1.00 2.00 2.0 ▇▇▁▁▇

2. Does tooth length increase with dosage? (len vs dose; numerical vs numerical)

ggplot(ToothGrowth, aes(x = dose, y = len)) + 
  geom_point()

Only boxplot

ggplot(ToothGrowth, aes (x = factor(dose), y = len)) +
  geom_boxplot()

Boxplot + Jittered Individual Points + Labels

ggplot(ToothGrowth, aes (x = factor(dose), y = len)) +
  geom_boxplot() +
  geom_jitter(width = 0.1, alpha = 0.6) +
  labs (
    x = "Dosage",
    y = "Tooth Length",
    title = "Tooth Length by Dosage"
  )

Violin Plot

ggplot(ToothGrowth, aes (x = factor(dose), y = len)) +
  geom_violin()

Violin Plot + Jittered Individual Points

ggplot(ToothGrowth, aes (x = factor(dose), y = len)) +
  geom_violin() +
  geom_jitter(width = 0.1, alpha = 0.6)

Linear Model (lm (response ~ predictor))

lm(len ~ dose, data = ToothGrowth)
## 
## Call:
## lm(formula = len ~ dose, data = ToothGrowth)
## 
## Coefficients:
## (Intercept)         dose  
##       7.422        9.764

As the slope is positive / >0 (in this case slope = 9.764 (9.764 increase per 1 dose unit increase), the intercept of 7.422 just says that at dose=0 that 7.422 is the starting point), then yes tooth length increases with dosage size.

3. Which supplement type (VC or OJ) is more effective? (len vs supp; numerical vs categorical)

ggplot(ToothGrowth, aes(x = supp, y = len)) + 
  geom_point()

Only boxplot

ggplot(ToothGrowth, aes (x = factor(supp), y = len)) +
  geom_boxplot()

Boxplot + Jittered Individual Points + Labels

ggplot(ToothGrowth, aes (x = factor(supp), y = len)) +
  geom_boxplot() +
  geom_jitter(width = 0.1, alpha = 0.6) +
  labs (
    x = "Dosage",
    y = "Tooth Length",
    title = "Tooth Length by Dosage"
  )

Violin Plot

ggplot(ToothGrowth, aes (x = factor(supp), y = len)) +
  geom_violin()

Violin Plot + Jittered Individual Points

ggplot(ToothGrowth, aes (x = factor(supp), y = len)) +
  geom_violin() +
  geom_jitter(width = 0.1, alpha = 0.6)

Aggregating the group means

aggregate(len ~ supp, data=ToothGrowth, mean)
##   supp      len
## 1   OJ 20.66333
## 2   VC 16.96333

QQ plots - kinda wonky, seems like the data isn’t normally distributed

ggplot(ToothGrowth, aes(sample = len)) +
  stat_qq() +
  stat_qq_line() +
  facet_wrap(~ supp)

Two-sample t-test - p=0.06. I don’t think using a t-test was the correct way to go, but having a p>0.05 anyways means that this isn’t right

t.test(len ~ supp, data = ToothGrowth)
## 
##  Welch Two Sample t-test
## 
## data:  len by supp
## t = 1.9153, df = 55.309, p-value = 0.06063
## alternative hypothesis: true difference in means between group OJ and group VC is not equal to 0
## 95 percent confidence interval:
##  -0.1710156  7.5710156
## sample estimates:
## mean in group OJ mean in group VC 
##         20.66333         16.96333

4. Graph your data and explore the relationship between dose and supplement.

ggplot(ToothGrowth, aes(x = factor(dose), y = len, fill = supp)) +
  geom_boxplot(position = position_dodge(width = 0.8)) +
  geom_jitter(
    aes(color = supp),
    position = position_jitterdodge(jitter.width = 0.1, dodge.width = 0.8),
    alpha = 0.6
  ) +
  labs(
    x = "Dose",
    y = "Tooth length",
    fill = "Supplement",
    color = "Supplement",
    title = "Tooth Length by Dose and Supplement"
  )

  1. footnotes↩︎