FAQ and Gallery showing various tables possible with the {gtsummary} package.


Frequently Asked Questions

Summary Tables

Add a spanning header over the group columns for increased clarity, and modify column headers. Using bold_labels() formats the labels as bold, but labels can also be italicized using italicize_labels(), or combined to format with both bold and italics.

trial %>%
  select(trt, age, grade) %>%
  tbl_summary(
    by = trt,
    missing = "no",
    statistic = all_continuous() ~ "{median} ({p25}, {p75})"
  ) %>%
  modify_header(all_stat_cols() ~ "**{level}**<br>N = {n} ({style_percent(p)}%)") %>%
  add_n() %>%
  bold_labels() %>%
  modify_spanning_header(all_stat_cols() ~ "**Chemotherapy Treatment**")
Characteristic N Chemotherapy Treatment
Drug A
N = 98 (49%)1
Drug B
N = 102 (51%)1
Age 189 46 (37, 59) 48 (39, 56)
Grade 200
    I 35 (36%) 33 (32%)
    II 32 (33%) 36 (35%)
    III 31 (32%) 33 (32%)
1 Median (IQR); n (%)

Show continuous summary statistics on multiple lines. Levels are italicized here using the italicize_levels() function, but the bold_levels() function can be used instead to create bold text, or both functions can be used together to get text that is both bold and in italics.

trial %>%
  select(trt, age, marker) %>%
  tbl_summary(
    by = trt,
    type = all_continuous() ~ "continuous2",
    statistic = all_continuous() ~ c(
      "{N_nonmiss}",
      "{mean} ({sd})",
      "{median} ({p25}, {p75})",
      "{min}, {max}"
    ),
    missing = "no"
  ) %>%
  italicize_levels()
Characteristic Drug A, N = 98 Drug B, N = 102
Age
    N 91 98
    Mean (SD) 47 (15) 47 (14)
    Median (IQR) 46 (37, 59) 48 (39, 56)
    Range 6, 78 9, 83
Marker Level (ng/mL)
    N 92 98
    Mean (SD) 1.02 (0.89) 0.82 (0.83)
    Median (IQR) 0.84 (0.24, 1.57) 0.52 (0.19, 1.20)
    Range 0.00, 3.87 0.01, 3.64

Modify the function that formats the p-values, change variable labels, updating tumor response header, and add a correction for multiple testing.

trial %>%
  select(response, age, grade) %>%
  mutate(response = factor(response, labels = c("No Tumor Response", "Tumor Responded"))) %>%
  tbl_summary(
    by = response,
    missing = "no",
    label = list(age ~ "Patient Age", grade ~ "Tumor Grade")
  ) %>%
  add_p(pvalue_fun = ~ style_pvalue(.x, digits = 2)) %>%
  add_q()
Characteristic No Tumor Response, N = 1321 Tumor Responded, N = 611 p-value2 q-value3
Patient Age 46 (36, 55) 49 (43, 59) 0.091 0.18
Tumor Grade 0.93 0.93
    I 46 (35%) 21 (34%)
    II 44 (33%) 19 (31%)
    III 42 (32%) 21 (34%)
1 Median (IQR); n (%)
2 Wilcoxon rank sum test; Pearson’s Chi-squared test
3 False discovery rate correction for multiple testing

Include missing tumor response as column using fct_explicit_na().

trial %>%
  select(response, age, grade) %>%
  mutate(
    response = factor(response, labels = c("No Tumor Response", "Tumor Responded")) %>%
      fct_explicit_na(na_level = "Missing Response Status")
  ) %>%
  tbl_summary(
    by = response,
    label = list(age ~ "Patient Age", grade ~ "Tumor Grade")
  )
Characteristic No Tumor Response, N = 1321 Tumor Responded, N = 611 Missing Response Status, N = 71
Patient Age 46 (36, 55) 49 (43, 59) 52 (44, 57)
    Unknown 7 3 1
Tumor Grade
    I 46 (35%) 21 (34%) 1 (14%)
    II 44 (33%) 19 (31%) 5 (71%)
    III 42 (32%) 21 (34%) 1 (14%)
1 Median (IQR); n (%)

Report treatment differences between two groups. This is often needed in randomized trials. In this example, we report the difference in tumor response and marker level between two chemotherapy treatments.

trial %>%
  select(response, marker, trt) %>%
  tbl_summary(
    by = trt,
    statistic = list(
      all_continuous() ~ "{mean} ({sd})",
      all_categorical() ~ "{p}%"
    ),
    missing = "no"
  ) %>%
  add_difference() %>%
  add_n() %>%
  modify_header(all_stat_cols() ~ "**{level}**") %>%
  modify_footnote(all_stat_cols() ~ NA)
Characteristic N Drug A Drug B Difference1 95% CI1,2 p-value1
Tumor Response 193 29% 34% -4.2% -18%, 9.9% 0.6
Marker Level (ng/mL) 190 1.02 (0.89) 0.82 (0.83) 0.20 -0.05, 0.44 0.12
1 Two sample test for equality of proportions; Welch Two Sample t-test
2 CI = Confidence Interval

Paired t-test and McNemar’s test. The data is expected in a long format with 2 rows per participant.

# imagine that each patient received Drug A and Drug B (adding ID showing their paired measurements)
trial_paired <-
  trial %>%
  select(trt, marker, response) %>%
  group_by(trt) %>%
  mutate(id = row_number()) %>%
  ungroup()

# you must first delete incomplete pairs from the data, then you can build the table
trial_paired %>%
  # delete missing values
  filter(complete.cases(.)) %>%
  # keep IDs with both measurements
  group_by(id) %>%
  filter(n() == 2) %>%
  ungroup() %>%
  # summarize data
  tbl_summary(by = trt, include = -id) %>%
  add_p(
    test = list(
      marker ~ "paired.t.test",
      response ~ "mcnemar.test"
    ),
    group = id
  )
Characteristic Drug A, N = 831 Drug B, N = 831 p-value2
Marker Level (ng/mL) 0.82 (0.22, 1.63) 0.53 (0.18, 1.26) 0.2
Tumor Response 21 (25%) 28 (34%) 0.3
1 Median (IQR); n (%)
2 Paired t-test; McNemar’s Chi-squared test with continuity correction

Include p-values comparing all groups to a single reference group.

# table summarizing data with no p-values
small_trial <- trial %>% select(grade, age, response)
t0 <- small_trial %>%
  tbl_summary(by = grade, missing = "no") %>%
  modify_header(all_stat_cols() ~ "**{level}**")

# table comparing grade I and II
t1 <- small_trial %>%
  filter(grade %in% c("I", "II")) %>%
  tbl_summary(by = grade, missing = "no") %>%
  add_p() %>%
  modify_header(p.value ~ md("**I vs. II**")) %>%
  # hide summary stat columns
  modify_column_hide(all_stat_cols())

# table comparing grade I and II
t2 <- small_trial %>%
  filter(grade %in% c("I", "III")) %>%
  tbl_summary(by = grade, missing = "no") %>%
  add_p() %>%
  modify_header(p.value ~ md("**I vs. III**")) %>%
  # hide summary stat columns
  modify_column_hide(all_stat_cols())

# merging the 3 tables together, and adding additional gt formatting
tbl_merge(list(t0, t1, t2)) %>%
  modify_spanning_header(
    list(
      all_stat_cols() ~ "**Tumor Grade**",
      starts_with("p.value") ~ "**p-values**"
    )
  )
Characteristic Tumor Grade p-values
I1 II1 III1 I vs. II2 I vs. III2
Age 47 (37, 56) 49 (37, 57) 47 (38, 58) 0.7 0.5
Tumor Response 21 (31%) 19 (30%) 21 (33%) >0.9 0.9
1 Median (IQR); n (%)
2 Wilcoxon rank sum test; Fisher’s exact test

Add 95% confidence interval around the mean as an additional column


trial %>%
  select(age, marker) %>%
  tbl_summary(statistic = all_continuous() ~ "{mean} ({sd})", missing = "no") %>%
  modify_header(stat_0 ~ "**Mean (SD)**") %>%
  add_ci()
Characteristic Mean (SD)1 95% CI2
Age 47 (14) 45, 49
Marker Level (ng/mL) 0.92 (0.86) 0.79, 1.0
1 Mean (SD)
2 CI = Confidence Interval

It’s often needed to summarize a continuous variable by one, two, or more categorical variables. The example below shows a table summarizing a continuous variable by two categorical variables. To summarize by more than two categorical variables, use tbl_continuous in conjunction with tbl_strata (see an example of tbl_strata here).

trial %>%
  select(trt, grade, marker) %>%
  tbl_continuous(variable = marker, by = trt) %>%
  modify_spanning_header(all_stat_cols() ~ "**Treatment Assignment**")
Characteristic Treatment Assignment
Drug A, N = 981 Drug B, N = 1021
Grade
    I 0.96 (0.24, 1.70) 1.05 (0.29, 1.49)
    II 0.66 (0.31, 1.23) 0.21 (0.10, 0.94)
    III 0.84 (0.17, 1.91) 0.58 (0.35, 1.36)
1 Marker Level (ng/mL): Median (IQR)

Build a summary table stratified by more than one variable.

trial %>%
  select(trt, grade, age, stage) %>%
  mutate(grade = paste("Grade", grade)) %>%
  tbl_strata(
    strata = grade,
    ~ .x %>%
      tbl_summary(by = trt, missing = "no") %>%
      modify_header(all_stat_cols() ~ "**{level}**")
  )
Characteristic Grade I Grade II Grade III
Drug A1 Drug B1 Drug A1 Drug B1 Drug A1 Drug B1
Age 46 (36, 60) 48 (42, 55) 45 (31, 55) 51 (43, 57) 52 (42, 60) 45 (36, 52)
T Stage
    T1 8 (23%) 9 (27%) 14 (44%) 9 (25%) 6 (19%) 7 (21%)
    T2 8 (23%) 10 (30%) 8 (25%) 9 (25%) 9 (29%) 10 (30%)
    T3 11 (31%) 7 (21%) 5 (16%) 6 (17%) 6 (19%) 8 (24%)
    T4 8 (23%) 7 (21%) 5 (16%) 12 (33%) 10 (32%) 8 (24%)
1 Median (IQR); n (%)

Regression Tables

Include number of observations and the number of events in a univariate regression table.

trial %>%
  select(response, age, grade) %>%
  tbl_uvregression(
    method = glm,
    y = response,
    method.args = list(family = binomial),
    exponentiate = TRUE
  ) %>%
  add_nevent()
Characteristic N Event N OR1 95% CI1 p-value
Age 183 58 1.02 1.00, 1.04 0.10
Grade 193 61
    I
    II 0.95 0.45, 2.00 0.9
    III 1.10 0.52, 2.29 0.8
1 OR = Odds Ratio, CI = Confidence Interval

Include two related models side-by-side with descriptive statistics. We also use the compact table theme that reduces cell padding and font size.

gt_r1 <- glm(response ~ trt + grade, trial, family = binomial) %>%
  tbl_regression(exponentiate = TRUE)
gt_r2 <- coxph(Surv(ttdeath, death) ~ trt + grade, trial) %>%
  tbl_regression(exponentiate = TRUE)
gt_t1 <- trial[c("trt", "grade")] %>%
  tbl_summary(missing = "no") %>%
  add_n() %>%
  modify_header(stat_0 ~ "**n (%)**") %>%
  modify_footnote(stat_0 ~ NA_character_)

theme_gtsummary_compact()
#> Setting theme `Compact`
tbl_merge(
  list(gt_t1, gt_r1, gt_r2),
  tab_spanner = c(NA_character_, "**Tumor Response**", "**Time to Death**")
)
Characteristic N n (%) Tumor Response Time to Death
OR1 95% CI1 p-value HR1 95% CI1 p-value
Chemotherapy Treatment 200
    Drug A 98 (49%)
    Drug B 102 (51%) 1.21 0.66, 2.24 0.5 1.25 0.86, 1.81 0.2
Grade 200
    I 68 (34%)
    II 68 (34%) 0.94 0.44, 1.98 0.9 1.28 0.80, 2.06 0.3
    III 64 (32%) 1.09 0.52, 2.27 0.8 1.69 1.07, 2.66 0.024
1 OR = Odds Ratio, CI = Confidence Interval, HR = Hazard Ratio

Include the number of events at each level of a categorical predictor.

trial %>%
  select(ttdeath, death, stage, grade) %>%
  tbl_uvregression(
    method = coxph,
    y = Surv(ttdeath, death),
    exponentiate = TRUE,
    hide_n = TRUE
  ) %>%
  add_nevent(location = "level")
Characteristic Event N HR1 95% CI1 p-value
T Stage
    T1 24
    T2 27 1.18 0.68, 2.04 0.6
    T3 22 1.23 0.69, 2.20 0.5
    T4 39 2.48 1.49, 4.14
Grade
    I 33
    II 36 1.28 0.80, 2.05 0.3
    III 43 1.69 1.07, 2.66 0.024
1 HR = Hazard Ratio, CI = Confidence Interval

Regression model where the covariate remains the same, and the outcome changes.

trial %>%
  select(age, marker, trt) %>%
  tbl_uvregression(
    method = lm,
    x = trt,
    show_single_row = "trt",
    hide_n = TRUE
  ) %>%
  modify_header(list(
    label ~ "**Model Outcome**",
    estimate ~ "**Treatment Coef.**"
  )) %>%
  modify_footnote(estimate ~ "Values larger than 0 indicate larger values in the Drug B group.")
Model Outcome Treatment Coef.1 95% CI2 p-value
Age 0.44 -3.7, 4.6 0.8
Marker Level (ng/mL) -0.20 -0.44, 0.05 0.12
1 Values larger than 0 indicate larger values in the Drug B group.
2 CI = Confidence Interval

Implement a custom tidier to report Wald confidence intervals. The Wald confidence intervals are calculated using confint.default().

my_tidy <- function(x, exponentiate = FALSE, conf.level = 0.95, ...) {
  dplyr::bind_cols(
    broom::tidy(x, exponentiate = exponentiate, conf.int = FALSE),
    # calculate the confidence intervals, and save them in a tibble
    stats::confint.default(x) %>%
      tibble::as_tibble() %>%
      rlang::set_names(c("conf.low", "conf.high"))
  )
}

lm(age ~ grade + marker, trial) %>%
  tbl_regression(tidy_fun = my_tidy)
Characteristic Beta 95% CI1 p-value
Grade
    I
    II 0.64 -4.6, 5.9 0.8
    III 2.4 -2.8, 7.6 0.4
Marker Level (ng/mL) -0.04 -2.6, 2.5 >0.9
1 CI = Confidence Interval

Use significance stars on estimates with low p-values.

trial %>%
  select(ttdeath, death, stage, grade) %>%
  tbl_uvregression(
    method = coxph,
    y = Surv(ttdeath, death),
    exponentiate = TRUE,
  ) %>%
  add_significance_stars()
Characteristic N HR1,2 SE2
T Stage 200
    T1
    T2 1.18 0.281
    T3 1.23 0.295
    T4 2.48*** 0.260
Grade 200
    I
    II 1.28 0.241
    III 1.69* 0.232
1 *p<0.05; **p<0.01; ***p<0.001
2 HR = Hazard Ratio, SE = Standard Error