pacman::p_load(ggstatsplot, rstantools, PMCMRplus, tidyverse)
exam_data <- read_csv("data/Exam_data.csv")Rows: 322 Columns: 7
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (4): ID, CLASS, GENDER, RACE
dbl (3): ENGLISH, MATHS, SCIENCE
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Using gghistostats().
set.seed(1234)
gghistostats(
data = exam_data,
x = ENGLISH,
type = "bayes",
test.value = 60,
xlab = "English scores"
)
Using ggbetweenstats().
ggbetweenstats(
data = exam_data,
x = GENDER,
y = MATHS,
type = "np",
messages = FALSE
)
Using ggbetweenstats().
ggbetweenstats(
data = exam_data,
x = RACE,
y = ENGLISH,
type = "p",
mean.ci = TRUE,
pairwise.comparisons = TRUE,
pairwise.display = "s",
p.adjust.method = "fdr",
messages = FALSE
)
Using ggscatterscats().
ggscatterstats(
data = exam_data,
x = MATHS,
y = ENGLISH,
marginal = FALSE
)
Using ggbarstats().
exam1 <- exam_data %>%
mutate(MATHS_bins =
cut(MATHS,
breaks = c(0, 60, 75, 85, 100)))
ggbarstats(exam1,
x = MATHS_bins,
y = GENDER)
pacman::p_load(readxl, performance, parameters, see)
car_resale <- read_xls("data/ToyotaCorolla.xls", "data")
car_resale# A tibble: 1,436 × 38
Id Model Price Age_0…¹ Mfg_M…² Mfg_Y…³ KM Quart…⁴ Weight Guara…⁵
<dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 81 TOYOTA Cor… 18950 25 8 2002 20019 100 1180 3
2 1 TOYOTA Cor… 13500 23 10 2002 46986 210 1165 3
3 2 TOYOTA Cor… 13750 23 10 2002 72937 210 1165 3
4 3 TOYOTA Co… 13950 24 9 2002 41711 210 1165 3
5 4 TOYOTA Cor… 14950 26 7 2002 48000 210 1165 3
6 5 TOYOTA Cor… 13750 30 3 2002 38500 210 1170 3
7 6 TOYOTA Cor… 12950 32 1 2002 61000 210 1170 3
8 7 TOYOTA Co… 16900 27 6 2002 94612 210 1245 3
9 8 TOYOTA Cor… 18600 30 3 2002 75889 210 1245 3
10 44 TOYOTA Cor… 16950 27 6 2002 110404 234 1255 3
# … with 1,426 more rows, 28 more variables: HP_Bin <chr>, CC_bin <chr>,
# Doors <dbl>, Gears <dbl>, Cylinders <dbl>, Fuel_Type <chr>, Color <chr>,
# Met_Color <dbl>, Automatic <dbl>, Mfr_Guarantee <dbl>,
# BOVAG_Guarantee <dbl>, ABS <dbl>, Airbag_1 <dbl>, Airbag_2 <dbl>,
# Airco <dbl>, Automatic_airco <dbl>, Boardcomputer <dbl>, CD_Player <dbl>,
# Central_Lock <dbl>, Powered_Windows <dbl>, Power_Steering <dbl>,
# Radio <dbl>, Mistlamps <dbl>, Sport_Model <dbl>, Backseat_Divider <dbl>, …Using lm() from Base Stats of R.
model <- lm(Price ~ Age_08_04 + Mfg_Year + KM + Weight + Guarantee_Period,
data = car_resale)
model
Call:
lm(formula = Price ~ Age_08_04 + Mfg_Year + KM + Weight + Guarantee_Period,
data = car_resale)
Coefficients:
(Intercept) Age_08_04 Mfg_Year KM
-2.637e+06 -1.409e+01 1.315e+03 -2.323e-02
Weight Guarantee_Period
1.903e+01 2.770e+01 Using check_collinearity() from the performance package.
check_collinearity(model)# Check for Multicollinearity
Low Correlation
Term VIF VIF 95% CI Increased SE Tolerance Tolerance 95% CI
Guarantee_Period 1.04 [1.01, 1.17] 1.02 0.97 [0.86, 0.99]
Age_08_04 31.07 [28.08, 34.38] 5.57 0.03 [0.03, 0.04]
Mfg_Year 31.16 [28.16, 34.48] 5.58 0.03 [0.03, 0.04]
High Correlation
Term VIF VIF 95% CI Increased SE Tolerance Tolerance 95% CI
KM 1.46 [1.37, 1.57] 1.21 0.68 [0.64, 0.73]
Weight 1.41 [1.32, 1.51] 1.19 0.71 [0.66, 0.76]check_c <- check_collinearity(model)
plot(check_c)Variable `Component` is not in your data frame :/
Using check_normality() from the performance package.
model1 <- lm(Price ~ Age_08_04 + KM + Weight + Guarantee_Period,
data = car_resale)
check_n <- check_normality(model1)
plot(check_n)
Using check_heteroscedasticity() from the performance package.
check_h <- check_heteroscedasticity(model1)
plot(check_h)
Using check_model().
check_model(model1)Variable `Component` is not in your data frame :/
Using plot() of see package and parameters() of parameters package to visualise the parameters of a regression model.
plot(parameters(model1))
Using ggcoefstats() of ggstatsplot package to visualise the parameters of a regression model.
ggcoefstats(model1, output = "plot")