Mean_SD_Table.R Tutorial - sciencesharon/MicrobialSeq GitHub Wiki

Mean_SD_Table.R Tutorial

Mean ± Standard Deviation Table

Have you ever wanted to make a nice little mean ± standard deviation table of numerical data for publication?

Perhaps one that looks a little like this?

Then this is the script for you!

Example Data Input

Example_Data_Table.csv

How to use the script

Step 1: Load the data into R

data <- read.csv("/path/to/your/data/Example_Data_Table.csv")

Step 2: Separate and list the groups to compare

Male <- data[data$Gender %in% c("Male"),]

Female <- data[data$Gender %in% c("Female"),]

data_list <- list(Male = Male, Female = Female)

Step 3: Set the numerical columns which will be compared between the groups

columns <- colnames(data)[1:10]

Step 4: Set your output directory

dir <- ("/path/to/save/your/output")

Step 5: Utilize the function

means <- calculate_mean_sd(data_list = data_list, columns= columns, file_name = "mean_SD.csv", directory = dir, decimal_places = 2, statistical_test = "ttest", p_adjust_method = "BH", stars = TRUE)

Options in the function are as follows:

  • data_list: this is the data input

  • columns: these are the column names of numerical columns you wish to summarize and compare between the groups

  • file_name: this is the output .csv file name

  • directory: path to save the file

  • decimal_places: this is the number of decimals to round the output

  • statistical_test: default is NULL, can either be set to "ttest" or "wilcox" to perform t-test or Wilcox Rank Sum Test

  • p_adjust_method: default is NULL, can either be set to "bonferroni" or "BH" to adjust p_value

  • stars: default is FALSE, if TRUE will output "stars" column with * = 0.05, ** = 0.005, *** = 0.0005, **** = 0.00005, and ***** = 0.000005

Example Output

mean_SD.csv

This can easily be made into a pretty table with minor formatting :)

Like this:

mean_SD.xls