In tadaadata/tadaatoolbox: Helpers for Data Analysis and Presentation Focused on Undergrad Psychology

knitr::opts_chunk$set(echo = TRUE)

library(tibble)
library(dplyr)
library(tadaatoolbox)
library(car)
library(broom)

Testing dataset

data_1 <- tibble(response = c(rnorm(20, mean = 5,   sd = 2), 
                              rnorm(20, mean = 6,   sd = 1.5), 
                              rnorm(20, mean = 6.5, sd = 2.1)),
                 factor_A_unordered = c(rep("groupA_1", 20),
                                        rep("groupA_2", 20),
                                        rep("groupA_3", 20)),
                 factor_A_ordered   = c(rep("groupA_low", 20),
                                        rep("groupA_mid", 20),
                                        rep("groupA_high", 20)),
                 factor_B_unordered = c(rep("groupB_1", 30),
                                        rep("groupB_2", 30))) %>%
          mutate(factor_A_unordered = factor(factor_A_unordered, ordered = F),
                 factor_A_ordered   = factor(factor_A_ordered,   ordered = T),
                 factor_B_unordered = factor(factor_B_unordered, ordered = F))

Contrasts

Current Contrasts of Test Data Factors

lapply(data_1[-1], contrasts)

Current R Defaults

getOption("contrasts") %>% as.tibble()

Unordered vs. Ordered Factors

One-Way

model_unord <- aov(response ~ factor_A_unordered, data = data_1) %>% tidy()
model_ord   <- aov(response ~ factor_A_ordered, data = data_1)   %>% tidy()

model_unord
model_ord

(model_unord == model_ord) %>% as.tibble()

Two-Way

model_unord <- aov(response ~ factor_A_unordered * factor_B_unordered, 
                   data = data_1) %>% tidy()
model_ord   <- aov(response ~ factor_A_ordered * factor_B_unordered, 
                   data = data_1) %>% tidy()

model_unord
model_ord

(model_unord == model_ord) %>% as.tibble()

tadaadata/tadaatoolbox documentation built on June 3, 2020, 10:34 a.m.