In wardfont/edcpR: Ecological Data Collection and Processing Package

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

library(edcpR)

Data

use the dataset "varechem_s2" provided in the course pacakge:

data(varechem_s2, package= "edcpR")

Tips

Find useful tips and function suggestions on the cheat-sheet vignette:

browseVignettes(package = "edcpR")

Part 1

• Check the structure and data type of the data (and change in R if necessary)
• Extra: Try to assign meaningful levels for the variable Managementtype
• Check NA and incorrect values (and change in R if necessary)
• TIP: anyNA(), complete.cases(), ...
• Calculate summary metrics (min, max, mean, ...) to check for anomalies
• Visualize your data
• Try different types of graphs (scatterplot, histogram, boxplot...)

Part 2

• Perform outlier analysis
• for a univariate case: let's consider S
• for a multivariate case: let's consider P~K here
  • do we have influential outliers?
  • TIP: olsrr-package

Part 3

• Check distribution of variables
• Is the data normally distributed?
• Make a visual inspection for the variable Potassium (K) and Calcium (Ca)
• Use a statistical test
• Apply transformations to normalize variables
• Let's do this for the variable Calcium (Ca)
• Apply transformations to linearize relationships
• Do this for the relationship between Iron (Fe) and Zinc (Zn)

Assignment 2

Access the assignment:

vignette("assignment-2", package = "edcpR")

Remember to upload everything before October 27, 12 am (= at noon!).

wardfont/edcpR documentation built on Dec. 23, 2021, 5:07 p.m.