Purpose
Translate the code from session 1 to R.
Read in data
-- Attaching packages --------------------------------------- tidyverse 1.3.1 --
v ggplot2 3.3.5 v purrr 0.3.4
v tibble 3.1.6 v dplyr 1.0.7
v tidyr 1.1.4 v stringr 1.4.0
v readr 2.1.1 v forcats 0.5.1
Warning: package 'tibble' was built under R version 4.1.2
Warning: package 'readr' was built under R version 4.1.2
-- Conflicts ------------------------------------------ tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag() masks stats::lag()
theme_set(theme_light())
df <- readxl::read_excel(here::here("course-content/Class 1/Okun's Law.xlsx"), range = "A1:E45")
df <- df %>%
janitor::clean_names()
EDA
df %>%
ggplot(aes(x = change_in_unemployment_rate_pp, y = real_gdp_growth_percent)) +
geom_point() +
geom_smooth(method = "lm") +
scale_x_continuous(labels = scales::percent_format(scale = 1)) +
scale_y_continuous(labels = scales::percent_format(scale = 1)) +
geom_vline(xintercept = 0, lty = 2) +
geom_hline(yintercept = 0, lty = 2) +
labs(
x = "Change in unemployment rate",
y = "Real GDP Growth",
title = "Okun's Law in the UK",
subtitle = "1871-1913"
)
`geom_smooth()` using formula 'y ~ x'
Warning: Removed 1 rows containing non-finite values (stat_smooth).
Warning: Removed 1 rows containing missing values (geom_point).
Regression
lm <- lm(real_gdp_growth_percent ~ change_in_unemployment_rate_pp, data = df)
lm %>%
broom::tidy()
# A tibble: 2 x 5
term estimate std.error statistic p.value
<chr> <dbl> <dbl> <dbl> <dbl>
1 (Intercept) 1.83 0.251 7.30 0.00000000631
2 change_in_unemployment_rate_pp -1.36 0.218 -6.25 0.000000193
lm %>%
gtsummary::tbl_regression(intercept = T)
| Characteristic |
Beta |
95% CI |
p-value |
| (Intercept) |
1.8 |
1.3, 2.3 |
<0.001 |
| change_in_unemployment_rate_pp |
-1.4 |
-1.8, -0.92 |
<0.001 |
