W1 self test

Welcome to the PSYC3361 coding W1 self test. The test assesses your ability to use the coding skills covered in the Week 1 online coding modules.

In particular, it assesses your ability to…

choose packages/functions
read in data
group_by and summarise
make notes using RMarkdown
insert pictures in an Rmd document
write data to csv

It is IMPORTANT to document the code that you write so that someone who is looking at your code can understand what it is doing. Above each chunk, write a few sentences outlining which packages/functions you have chosen to use and what the function is doing to your data. Where relevant, also write a sentence that interprets the output of your code.

Your notes should also document the troubleshooting process you went through to arrive at the code that worked.

For each of the challenges below, the documentation is JUST AS IMPORTANT as the code.

Good luck!!

Jenny

1. customise your Rmd document by adding your name as the author, a table of contents and choosing a theme that you like.

2. load the packages you will need

library(tidyverse)

3. read the birthweight data

birthweight_data = read_csv("./data/birthweight_data.csv")
glimpse(birthweight_data)

## Rows: 788
## Columns: 5
## $ true_ID         <dbl> 3100, 3101, 3102, 3103, 3104, 3105, 3106, 3107, 3108, …
## $ birthweight     <dbl> 3030, 3710, 3770, 3660, 3800, 3540, 3400, 3650, 3460, …
## $ gestation_age_w <chr> "39", "40", "42", "38", "39", "41", "37", "39", "39", …
## $ child_ethn      <chr> "Middle-Eastern", "Caucasian", "African/African-Americ…
## $ plurality       <chr> "singleton", "singleton", "singleton", "singleton", "s…

4. calculate the mean birt hweight separately for twins and singletons

birthweight_by_plurality = birthweight_data %>%
  group_by(plurality) %>%
  summarise(sum(birthweight))
print(birthweight_by_plurality)

## # A tibble: 2 × 2
##   plurality `sum(birthweight)`
##   <chr>                  <dbl>
## 1 singleton            2416589
## 2 twin                  101670

5. identify the earliest (i.e. the minimum value) gestational age for each ethnicity group

birthweight_data %>% 
  group_by(child_ethn) %>%
  summarise(min(gestation_age_w))

## # A tibble: 10 × 2
##    child_ethn                        `min(gestation_age_w)`
##    <chr>                             <chr>                 
##  1 Aboriginal/Torres Strait Islander 33                    
##  2 African/African-American          26                    
##  3 Caucasian                         26                    
##  4 East Asian                        33                    
##  5 Hispanic/Latino                   37                    
##  6 Middle-Eastern                    28                    
##  7 Missing                           36                    
##  8 Polynesian/Melanesian             28                    
##  9 South Asian                       28                    
## 10 South-East Asian                  29

6. write some notes about how group_by and summarise work with the pipe below, including a link to documentation or a blog post that you think is useful

The official R documentation for the dplyr functions group_by, and summarise

https://www.rdocumentation.org/packages/dplyr/versions/1.0.10/topics/group_by

https://www.rdocumentation.org/packages/dplyr/versions/0.7.8/topics/summarise

How does group_by work?

Group by takes an ungrouped dataframe and returns a grouped dataframe. In data analysis, mostly one wants to perform operations on groups, not on the whole table. For example, we often care about the differences between groups in an experiment, or in a between subjects design, the differences between two trial types.

This is the purpose of the group_by function. This is very powerful, because it allows us to store all our data in one dataframe, but still be able to make comparisons between subsets of this data. Using the earlier analogy of an RCT, this would mean that we don’t have to keep the control and intervention group’s data separate, we can keep them in the same file with a column that indicates group membership. Storing all data in a 2d table is best practice, and the group_by function is both the reason for this and critical to the functioning of this system.

How does summarise work?

Another fundamental operation in data analysis is summarising data. For example, in an RCT it is very common to compare the mean scores of two different groups on some outcome measure. This is a form of summarisation.

Summarise takes a column or columns as input and returns a single value for these data. It also take a function to apply to these data, which is how it obtains the single value representing the input data.

7. download a picture of a baby from the internet and insert it into your document below

8. write the summary of mean birthweight by twins/singletons that you made in step 3 above to a new csv file

write_csv(birthweight_by_plurality, "birthweight_by_plurality.csv")