Problem Set 1a .Rmd

---
editor_options:
  markdown:
    wrap: 200
output:
  html_document: default
  word_document: default
  pdf_document: default
---



# HM 878 Applied Biostatistics Problem Set #1a

## Descriptive Statistics, Confidence Intervals, 5-point Summary, Frequencies, Graphs

*Goals: This Problem Set will provide students with the opportunity to
learn how to use R to conduct basic statistical tests, replicating many
tests that were already done in HM 802. The main goal is to make sure
you are familiar with R as a system for statistical analysis. You did
these same analyses in HM 802, using the same datasets and SPSS. I've
included SPSS output here so that you can check your work. You don't
have to conduct hypothesis tests. Include your output from R. If you are
not getting the same information in R (it may be formatted differently
or called a different thing and that is ok), you should keep trying. For
now, I'm only interested in making sure you can use R to do these
analyses.*

Analyses include:

-   Descriptive statistics

-   Frequency distributions

-   Graphical displays of data

------------------------------------------------------------------------

*Setting up the code environment*

```{r}
library(dplyr)
```

```{r}
df = read.csv("C:\\Users\\ljens\\Downloads\\Anticonvulsants.csv")
head(df)
```

------------------------------------------------------------------------

## Question 1

Data: Anticonvulsants.csv. Variable: convulsions. Use R to calculate
descriptive statistics: mean, median, mode, and standard deviation.
Calculate quartiles. Calculate a 5-point summary and the upper and lower
fences to determine outliers.

```{r}
summary(df$convulsions)
```

```{r}
mode_tbl = table(df$convulsions)
print(paste("Mode: ", substr(toString(names(mode_tbl[mode_tbl==max(mode_tbl)])), 1, 5)))
```

```{r}
print(paste("Standard Deviation: ", substr(toString(sd(df$convulsions)), 1, 5)))
```

```{r}
print(paste("IQR: ", substr(toString(IQR(df$convulsions)), 1, 5)))
```

```{r}
print(paste("Upper Fence: ", substr(toString(quantile(df$convulsions, 0.75) + 1.5*IQR(df$convulsions)), 1, 5)))
```

```{r}
print(paste("Lower Fence: ", substr(toString(quantile(df$convulsions, 0.25) - 1.5*IQR(df$convulsions)), 1, 5)))
```

------------------------------------------------------------------------

## Question 2

Data: Anticonvulsants.csv. Variable: center size. Use R to create a
frequency table.

```{r}
df <- df |> mutate(center_size_coded = recode(center_size, `1`="Small", `2`="Medium", `3`="Large" , .default = NA_character_))

table(df$center_size_code)
```

------------------------------------------------------------------------

## Question 3

Data: Cumulative Confirmed Cases and Deaths Among Confirmed Cases.csv.
Use R to create a dual line graph showing confirmed COVID-19 Deaths and
Cases on the same graph.

```{r}
df = read.csv("C:\\Users\\ljens\\Downloads\\Cumulative Confirmed Cases and Deaths Among Confirmed Cases.csv")
```

```{r}
head(df)
```

```{r}
colnames(df)
```

```{r}
library(tidyverse)
```

```{r}
df = df |> mutate(Date = mdy(Date))
```

```{r}
head(df)
```

```{r}
ggplot(df, aes(Date)) + 
  geom_line(aes(y=Cumulative_Cases, color = "Cases"), group=1)+
  geom_line(aes(y=Cumulative_Deaths, color="Deaths"), group=1) + 
  labs(title="COVID Cases & Deaths", y="Cummulative Count", ) +
  ggplot2::theme_classic()
```

------------------------------------------------------------------------

## Question 4

Data: COVID-19 Knowledge, Attitudes, and Behaviors.csv. Variable:
Generations. Using R, Create a Pie Chart and Histogram.

```{r}
df = read.csv("C:\\Users\\ljens\\Downloads\\COVID-19 Knowledge, Attitudes, and Behaviors.csv")
```

```{r}
tbl = df |> group_by(Generations) |> summarize(counts = length(Age))
```

```{r}
ggplot(tbl, aes(x='', y=counts, fill=Generations)) +
  geom_bar(stat='identity', width=1) +
  coord_polar('y', start=0) +
  theme_void() 
```

```{r}
df = df |> mutate(Gens = recode(Generations, 'Baby Boomers'=1, 'Gen X'=2, 'Millenials'=3, 'Gen Z'=4, .default = NA_real_))
```

```{r}
ggplot(df, aes(Gens)) +
  geom_histogram(color='white', binwidth = 1 ) +
  scale_x_continuous(breaks= seq(1,4), labels = c('Baby Boomers','Gen X','Millenials','Gen Z'))
```

------------------------------------------------------------------------

## Question 5

Data: COVID-19 Knowledge, Attitudes, and Behaviors.csv. Variable: AGE.
Using R, create a Box and Whisker plot.

```{r}
summary(df$Age)
```

```{r}
ggplot(df, aes(Age)) +
  geom_boxplot() +
  coord_flip()

```

------------------------------------------------------------------------

## Question 6

Data: COVID-19 Knowledge, Attitudes, and Behaviors.csv. Variables:
libcons and KnowledgeScore. Using R, Create a graph to show the
relationship between these two variables.

```{r}
df$LibCons = as.character(df$LibCons)
```

```{r}
df$KnowledgeScore = as.numeric(df$KnowledgeScore)
```

```{r}
tbl = df |> group_by(LibCons) |> summarize(mean=mean(KnowledgeScore), sd=sd(KnowledgeScore))
```

```{r}
tbl
```

```{r}
ggplot(tbl, aes(x=LibCons, y=mean)) +
  geom_point() +
  geom_errorbar(aes(ymin=mean-sd, ymax=mean+sd, width=.2)) +
  ylim(0,13) +
  labs(y="Mean Knowledge Score", x="Liberal-Conservative Scale", )
```