This analysis explores the Longley dataset with summary statistics using gtsummary.
# Load required libraries
library(gtsummary)
library(dplyr)
# Load dataset
data("longley")
head(longley)## GNP.deflator GNP Unemployed Armed.Forces Population Year Employed
## 1947 83.0 234.289 235.6 159.0 107.608 1947 60.323
## 1948 88.5 259.426 232.5 145.6 108.632 1948 61.122
## 1949 88.2 258.054 368.2 161.6 109.773 1949 60.171
## 1950 89.5 284.599 335.1 165.0 110.929 1950 61.187
## 1951 96.2 328.975 209.9 309.9 112.075 1951 63.221
## 1952 98.1 346.999 193.2 359.4 113.270 1952 63.639# Add Year groups
df <- longley
df$y_group <- cut(df$Year, breaks = 3, labels = c("Group 1", "Group 2", "Group 3"))
head(df)## GNP.deflator GNP Unemployed Armed.Forces Population Year Employed
## 1947 83.0 234.289 235.6 159.0 107.608 1947 60.323
## 1948 88.5 259.426 232.5 145.6 108.632 1948 61.122
## 1949 88.2 258.054 368.2 161.6 109.773 1949 60.171
## 1950 89.5 284.599 335.1 165.0 110.929 1950 61.187
## 1951 96.2 328.975 209.9 309.9 112.075 1951 63.221
## 1952 98.1 346.999 193.2 359.4 113.270 1952 63.639
## y_group
## 1947 Group 1
## 1948 Group 1
## 1949 Group 1
## 1950 Group 1
## 1951 Group 1
## 1952 Group 1# Summary without grouping
df %>%
select(GNP.deflator, GNP, Armed.Forces, Population, Year, Employed) %>%
tbl_summary()| Characteristic | N = 161 |
|---|---|
| GNP.deflator | 101 (93, 112) |
| GNP | 381 (307, 464) |
| Armed.Forces | 272 (208, 307) |
| Population | 117 (112, 123) |
| Year | 1,955 (1,951, 1,959) |
| Employed | 65.50 (62.20, 68.41) |
| 1 Median (Q1, Q3) | |
# Summary by y_group
df %>%
select(GNP.deflator, GNP, Armed.Forces, Population, Year, Employed, y_group) %>%
tbl_summary(by = y_group)| Characteristic | Group 1 N = 61 |
Group 2 N = 51 |
Group 3 N = 51 |
|---|---|---|---|
| GNP.deflator | 89 (88, 96) | 101 (100, 105) | 114 (113, 116) |
| GNP | 272 (258, 329) | 397 (365, 419) | 503 (483, 518) |
| Armed.Forces | 163 (159, 310) | 305 (286, 335) | 257 (255, 264) |
| Population | 110 (109, 112) | 117 (116, 119) | 125 (123, 128) |
| Year | 1,950 (1,948, 1,951) | 1,955 (1,954, 1,956) | 1,960 (1,959, 1,961) |
| Employed | 61.15 (60.32, 63.22) | 66.02 (64.99, 67.86) | 69.33 (68.66, 69.56) |
| 1 Median (Q1, Q3) | |||
# Summary with p-values
df %>%
select(GNP.deflator, GNP, Armed.Forces, Population, Year, Employed, y_group) %>%
tbl_summary(by = y_group) %>%
add_p()| Characteristic | Group 1 N = 61 |
Group 2 N = 51 |
Group 3 N = 51 |
p-value2 |
|---|---|---|---|---|
| GNP.deflator | 89 (88, 96) | 101 (100, 105) | 114 (113, 116) | 0.001 |
| GNP | 272 (258, 329) | 397 (365, 419) | 503 (483, 518) | 0.001 |
| Armed.Forces | 163 (159, 310) | 305 (286, 335) | 257 (255, 264) | 0.11 |
| Population | 110 (109, 112) | 117 (116, 119) | 125 (123, 128) | 0.001 |
| Year | 1,950 (1,948, 1,951) | 1,955 (1,954, 1,956) | 1,960 (1,959, 1,961) | 0.001 |
| Employed | 61.15 (60.32, 63.22) | 66.02 (64.99, 67.86) | 69.33 (68.66, 69.56) | 0.002 |
| 1 Median (Q1, Q3) | ||||
| 2 Kruskal-Wallis rank sum test | ||||