R & Quarto: Elevating Research Transparency

David Brocker

Roadmap

1. Research
2. Teaching
3. Service
4. Documentation
5. Fun

Research

1. Example
2. Import Data

Import Data

# Read and Clean Data
 mcu <- read_excel("UpdatedMCdata.xlsx")

Import Data

# Read and Clean Data
 mcu <- read_excel("UpdatedMCdata.xlsx")
# Clean
 mcu_cln <- 
  mcu %>% 
  # Get participants who finished 
  filter(Finished == "1") %>% 
  # Get participants who consented 
  filter(`Consent?` == "1") %>% 
  # Remove unneeded columns 
  select(-DistributionChannel,-UserLanguage) %>% 
  # Clean variable names 
  rename_with(~gsub(" ","_",.x)) %>% 
  # Make Score Columns numeric 
  mutate_at(vars(SC0:SC14),as.numeric) %>% 
  # Remove SC0 and replace with scale name 
  rename( 
    Morbid_Curiosity_Overall = SC0, 
    Mind = SC1, 
    Body = SC2, 
    Violence = SC3,
    Paranormal = SC4, 
    Horror_Typology_Overall = SC5, 
    AJ = SC6, 
    WK = SC7, 
    DC = SC8, 
    Trait = SC9, 
    State_Pre = SC10, 
    Positive_Choice = SC11,
    Negative_Choice = SC12,
    PN_Choice = SC13, 
    State_Post = SC14) |>
  mutate(
    # Divide all MC Total Score by 24
    Morbid_Curiosity_Overall = Morbid_Curiosity_Overall/24,
    # Divide all HT Total Score by 19
    Horror_Typology_Overall = Horror_Typology_Overall/19 ) |>
    # Divide each MC Subscale Item by 6
    mutate_at(vars(Mind:Paranormal),scale_six) |> 
    # Divide each HT Subscale Item by 6
    mutate_at(vars(AJ:DC),scale_seven)

Import Data

# Subset Scales
 mc_scale <- 
  mcu_cln |> 
  select(Morbid_Curiosity_Overall:State_Post)

Visualize Data

Clean Data

1. Identify any nonstandard naming conventions (tOgglECase, Spaces in Name, etc.)

2. Clean with Regular Expressions ¹ or janitor

1. Maybe another time!

Name Cleaning

• Before
• After

mcu |> names()

[1] "StartDate"             "EndDate"               "Status"               
[4] "Progress"              "Duration (in seconds)" "Finished"             

mcu |> 
clean_names() |> 
  names()

[1] "start_date"          "end_date"            "status"             
[4] "progress"            "duration_in_seconds" "finished"           

Exploratory Data Analysis

1. Visualize Possible Relationships

mcu_cln |> 
  select(where(is.numeric)) |> 
  pairs()

Exploratory Data Anlaysis

1. Scan for possible outliers

mcu_cln |> 
  select(where(is.numeric)) |> 
  boxplot()

Teaching

1. Example

1. Include Interactivity

2. Match Formatting

3. \(M = \Sigma\frac{x}{n}\)

4. Build Testing Materials

Service

1. Evaluate Data

Internship Placements

1. Present Findings

2. Present Solutions

Emphasize Certain Areas

Direct Students to Specific Sites

Documentation

1. Convert ‘static’ Documents

** Put Picture of PDF Manual Here **

2. Update and Modernize

Fun

1. Data is fun!