table_continuous() summarizes continuous variables
either overall or by a categorical grouping variable. It is designed for
readable summary tables in the console and for publication-ready outputs
in rendered documents. When by is supplied, it can also add
group-comparison tests, test statistics, and effect sizes. Formatting
follows APA conventions by default; style = "jama" (or
"nejm", "lancet", "annals",
"aer") switches the whole table to that journal’s published
rules — the House styles section of Summary tables for
reporting shows each style and the guideline sentence behind
every rule.
Basic usage
Use select to choose the continuous variables you want
to summarize:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health)
)
#> Descriptive statistics
#>
#> Variable │ M SD Min Max 95% CI LL
#> ────────────────────────────────┼────────────────────────────────────────
#> Body mass index │ 25.93 3.72 16.00 38.90 25.72
#> WHO-5 wellbeing index (0-100) │ 69.04 15.62 18.70 100.00 68.16
#> Satisfaction with health (1-5) │ 3.55 1.25 1.00 5.00 3.48
#>
#> Variable │ 95% CI UL n
#> ────────────────────────────────┼─────────────────
#> Body mass index │ 26.14 1188
#> WHO-5 wellbeing index (0-100) │ 69.93 1200
#> Satisfaction with health (1-5) │ 3.62 1192
#>
#> Missing values removed: bmi (12), life_sat_health (8).If you omit select, table_continuous()
scans the data frame and keeps numeric columns. Non-numeric columns are
dropped silently; set verbose = TRUE to list them in a
message:
table_continuous(sochealth)
#> Descriptive statistics
#>
#> Variable │ M SD Min
#> ────────────────────────────────────────────┼───────────────────────────
#> Age (years) │ 49.26 14.70 25.00
#> Monthly household income (CHF) │ 3833.00 1394.58 1000.00
#> WHO-5 wellbeing index (0-100) │ 69.04 15.62 18.70
#> Body mass index │ 25.93 3.72 16.00
#> Political position (0 = left, 10 = right) │ 5.48 2.03 0.00
#> Satisfaction with health (1-5) │ 3.55 1.25 1.00
#> Satisfaction with work (1-5) │ 3.38 1.18 1.00
#> Satisfaction with relationships (1-5) │ 3.72 1.10 1.00
#> Satisfaction with standard of living (1-5) │ 3.40 1.16 1.00
#> Survey design weight │ 1.00 0.41 0.29
#>
#> Variable │ Max 95% CI LL 95% CI UL
#> ────────────────────────────────────────────┼───────────────────────────────
#> Age (years) │ 75.00 48.43 50.10
#> Monthly household income (CHF) │ 7388.00 3754.01 3911.98
#> WHO-5 wellbeing index (0-100) │ 100.00 68.16 69.93
#> Body mass index │ 38.90 25.72 26.14
#> Political position (0 = left, 10 = right) │ 10.00 5.36 5.60
#> Satisfaction with health (1-5) │ 5.00 3.48 3.62
#> Satisfaction with work (1-5) │ 5.00 3.31 3.45
#> Satisfaction with relationships (1-5) │ 5.00 3.66 3.79
#> Satisfaction with standard of living (1-5) │ 5.00 3.33 3.46
#> Survey design weight │ 3.45 0.97 1.02
#>
#> Variable │ n
#> ────────────────────────────────────────────┼──────
#> Age (years) │ 1200
#> Monthly household income (CHF) │ 1200
#> WHO-5 wellbeing index (0-100) │ 1200
#> Body mass index │ 1188
#> Political position (0 = left, 10 = right) │ 1185
#> Satisfaction with health (1-5) │ 1192
#> Satisfaction with work (1-5) │ 1192
#> Satisfaction with relationships (1-5) │ 1192
#> Satisfaction with standard of living (1-5) │ 1192
#> Survey design weight │ 1200
#>
#> Missing values removed: bmi (12), political_position (15), life_sat_health (8), life_sat_work (8), life_sat_relationships (8), life_sat_standard (8).Grouped summaries
Add by to summarize the same variables across
categories. When by is supplied, a Welch-test
p-value column is added automatically:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health),
by = education
)
#> Descriptive statistics by Highest education level
#>
#> Variable │ Group M SD Min Max
#> ────────────────────────────────┼──────────────────────────────────────────────
#> Body mass index │ Lower secondary 28.09 3.47 18.20 38.90
#> │ Upper secondary 26.02 3.43 16.00 37.10
#> │ Tertiary 24.39 3.52 16.00 33.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary 57.22 15.44 18.70 97.90
#> │ Upper secondary 68.97 13.62 26.70 100.00
#> │ Tertiary 76.85 13.23 40.40 100.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Lower secondary 2.71 1.20 1.00 5.00
#> │ Upper secondary 3.53 1.19 1.00 5.00
#> │ Tertiary 4.11 1.04 1.00 5.00
#>
#> Variable │ Group 95% CI LL 95% CI UL n
#> ────────────────────────────────┼────────────────────────────────────────────
#> Body mass index │ Lower secondary 27.66 28.51 260
#> │ Upper secondary 25.73 26.31 534
#> │ Tertiary 24.04 24.74 394
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary 55.33 59.10 261
#> │ Upper secondary 67.82 70.12 539
#> │ Tertiary 75.55 78.15 400
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Lower secondary 2.57 2.86 259
#> │ Upper secondary 3.43 3.63 534
#> │ Tertiary 4.01 4.21 399
#>
#> Variable │ Group p
#> ────────────────────────────────┼────────────────────────
#> Body mass index │ Lower secondary <.001
#> │ Upper secondary
#> │ Tertiary
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary <.001
#> │ Upper secondary
#> │ Tertiary
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Lower secondary <.001
#> │ Upper secondary
#> │ Tertiary
#>
#> Missing values removed: bmi (12), life_sat_health (8).This is the main pattern for reporting continuous variables across
groups such as education, sex, treatment arm, or survey wave. Pass
p_value = FALSE to suppress the test column and keep the
output strictly descriptive.
If you want the same outcomes reported in a linear-model workflow,
with heteroskedasticity-consistent or cluster-robust standard errors,
case weights, or additive covariate adjustment, use
table_continuous_lm() instead:
table_continuous_lm(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health),
by = education,
vcov = "HC3"
)
#> Continuous outcomes by Highest education level
#>
#> Variable │ M (Lower secondary) M (Upper secondary)
#> ────────────────────────────────┼──────────────────────────────────────────
#> Body mass index │ 28.09 26.02
#> WHO-5 wellbeing index (0-100) │ 57.22 68.97
#> Satisfaction with health (1-5) │ 2.71 3.53
#>
#> Variable │ M (Tertiary) p R² n
#> ────────────────────────────────┼─────────────────────────────────
#> Body mass index │ 24.39 <.001 0.13 1188
#> WHO-5 wellbeing index (0-100) │ 76.85 <.001 0.21 1200
#> Satisfaction with health (1-5) │ 4.11 <.001 0.16 1192
#>
#> Note. Std. errors: heteroskedasticity-robust (HC3).
#> Missing values removed: bmi (12), life_sat_health (8).Add test statistics and effect sizes
Grouped tables can also report the test statistic and an effect size alongside the default p-value column:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health),
by = education,
statistic = TRUE,
effect_size = "auto",
effect_size_ci = TRUE
)
#> Descriptive statistics by Highest education level
#>
#> Variable │ Group M SD Min Max
#> ────────────────────────────────┼──────────────────────────────────────────────
#> Body mass index │ Lower secondary 28.09 3.47 18.20 38.90
#> │ Upper secondary 26.02 3.43 16.00 37.10
#> │ Tertiary 24.39 3.52 16.00 33.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary 57.22 15.44 18.70 97.90
#> │ Upper secondary 68.97 13.62 26.70 100.00
#> │ Tertiary 76.85 13.23 40.40 100.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Lower secondary 2.71 1.20 1.00 5.00
#> │ Upper secondary 3.53 1.19 1.00 5.00
#> │ Tertiary 4.11 1.04 1.00 5.00
#>
#> Variable │ Group 95% CI LL 95% CI UL n
#> ────────────────────────────────┼────────────────────────────────────────────
#> Body mass index │ Lower secondary 27.66 28.51 260
#> │ Upper secondary 25.73 26.31 534
#> │ Tertiary 24.04 24.74 394
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary 55.33 59.10 261
#> │ Upper secondary 67.82 70.12 539
#> │ Tertiary 75.55 78.15 400
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Lower secondary 2.57 2.86 259
#> │ Upper secondary 3.43 3.63 534
#> │ Tertiary 4.01 4.21 399
#>
#> Variable │ Group Test p
#> ────────────────────────────────┼───────────────────────────────────────────────
#> Body mass index │ Lower secondary F(2, 654.48) = 87.96 <.001
#> │ Upper secondary
#> │ Tertiary
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary F(2, 638.59) = 144.35 <.001
#> │ Upper secondary
#> │ Tertiary
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Lower secondary F(2, 652.08) = 118.74 <.001
#> │ Upper secondary
#> │ Tertiary
#>
#> Variable │ Group ES
#> ────────────────────────────────┼─────────────────────────────────────────
#> Body mass index │ Lower secondary η² = 0.13 [0.10, 0.17]
#> │ Upper secondary
#> │ Tertiary
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary η² = 0.21 [0.17, 0.25]
#> │ Upper secondary
#> │ Tertiary
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Lower secondary η² = 0.16 [0.13, 0.20]
#> │ Upper secondary
#> │ Tertiary
#>
#> Missing values removed: bmi (12), life_sat_health (8).Use test = "student" for equal-variance parametric tests
or test = "nonparametric" for rank-based comparisons:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score),
by = education,
test = "nonparametric",
statistic = TRUE,
effect_size = "auto"
)
#> Descriptive statistics by Highest education level
#>
#> Variable │ Group M SD Min Max
#> ───────────────────────────────┼──────────────────────────────────────────────
#> Body mass index │ Lower secondary 28.09 3.47 18.20 38.90
#> │ Upper secondary 26.02 3.43 16.00 37.10
#> │ Tertiary 24.39 3.52 16.00 33.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary 57.22 15.44 18.70 97.90
#> │ Upper secondary 68.97 13.62 26.70 100.00
#> │ Tertiary 76.85 13.23 40.40 100.00
#>
#> Variable │ Group 95% CI LL 95% CI UL n
#> ───────────────────────────────┼────────────────────────────────────────────
#> Body mass index │ Lower secondary 27.66 28.51 260
#> │ Upper secondary 25.73 26.31 534
#> │ Tertiary 24.04 24.74 394
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary 55.33 59.10 261
#> │ Upper secondary 67.82 70.12 539
#> │ Tertiary 75.55 78.15 400
#>
#> Variable │ Group Test p
#> ───────────────────────────────┼───────────────────────────────────────
#> Body mass index │ Lower secondary H(2) = 144.63 <.001
#> │ Upper secondary
#> │ Tertiary
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary H(2) = 233.53 <.001
#> │ Upper secondary
#> │ Tertiary
#>
#> Variable │ Group ES
#> ───────────────────────────────┼────────────────────────────
#> Body mass index │ Lower secondary ε² = 0.12
#> │ Upper secondary
#> │ Tertiary
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Lower secondary ε² = 0.19
#> │ Upper secondary
#> │ Tertiary
#>
#> Missing values removed: bmi (12).effect_size = "auto" selects the canonical measure for
the chosen test and number of groups: Hedges’ g
(parametric, 2 groups), eta-squared (parametric, 3+ groups),
rank-biserial r (nonparametric, 2 groups), or epsilon-squared
(nonparametric, 3+ groups). To pick a specific measure explicitly, pass
its character name:
table_continuous(
sochealth,
select = wellbeing_score,
by = sex,
effect_size = "hedges_g",
effect_size_ci = TRUE
)
#> Descriptive statistics by Sex
#>
#> Variable │ Group M SD Min Max 95% CI LL
#> ───────────────────────────────┼────────────────────────────────────────────────
#> WHO-5 wellbeing index (0-100) │ Female 67.16 14.80 19.60 100.00 65.99
#> │ Male 71.05 16.23 18.70 100.00 69.73
#>
#> Variable │ Group 95% CI UL n p
#> ───────────────────────────────┼───────────────────────────────
#> WHO-5 wellbeing index (0-100) │ Female 68.33 620 <.001
#> │ Male 72.37 580
#>
#> Variable │ Group ES
#> ───────────────────────────────┼──────────────────────────────────
#> WHO-5 wellbeing index (0-100) │ Female g = -0.25 [-0.36, -0.14]
#> │ MaleAllowed values are "none" (default), "auto"
(= legacy TRUE), "hedges_g",
"eta_sq", "r_rb", and
"epsilon_sq". Incompatible explicit choices
(e.g. "eta_sq" with two groups, or "hedges_g"
with test = "nonparametric") trigger an actionable
error.
When you need the underlying columns for further processing, use
output = "data.frame":
table_continuous(
sochealth,
select = c(bmi, wellbeing_score),
by = education,
statistic = TRUE,
effect_size = "auto",
output = "data.frame"
)
#> variable label group mean
#> 1 bmi Body mass index Lower secondary 28.08731
#> 2 bmi Body mass index Upper secondary 26.01891
#> 3 bmi Body mass index Tertiary 24.39036
#> 4 wellbeing_score WHO-5 wellbeing index (0-100) Lower secondary 57.21571
#> 5 wellbeing_score WHO-5 wellbeing index (0-100) Upper secondary 68.96920
#> 6 wellbeing_score WHO-5 wellbeing index (0-100) Tertiary 76.85250
#> sd min max ci_lower ci_upper median q1 q3 iqr
#> 1 3.471744 18.2 38.9 27.66333 28.51129 28.2 25.70 29.900 4.200
#> 2 3.434736 16.0 37.1 25.72693 26.31090 26.1 23.50 28.500 5.000
#> 3 3.520150 16.0 33.0 24.04170 24.73901 24.5 22.00 26.775 4.775
#> 4 15.444587 18.7 97.9 55.33323 59.09819 57.9 45.40 68.500 23.100
#> 5 13.621193 26.7 100.0 67.81669 70.12172 69.5 60.85 77.300 16.450
#> 6 13.226818 40.4 100.0 75.55235 78.15265 77.2 68.60 86.150 17.550
#> med_ci_lower med_ci_upper n weighted_n test_type statistic df1 df2
#> 1 27.6 28.7 260 NA welch_anova 87.95902 2 654.4758
#> 2 25.7 26.5 534 NA <NA> NA NA NA
#> 3 24.1 24.9 394 NA <NA> NA NA NA
#> 4 55.5 60.2 261 NA welch_anova 144.35083 2 638.5873
#> 5 68.1 70.9 539 NA <NA> NA NA NA
#> 6 76.2 78.5 400 NA <NA> NA NA NA
#> p.value es_type es_value es_ci_lower es_ci_upper smd_type smd_value
#> 1 1.467916e-34 eta_sq 0.1307679 0.09667861 0.1654516 <NA> NA
#> 2 NA <NA> NA NA NA <NA> NA
#> 3 NA <NA> NA NA NA <NA> NA
#> 4 1.888362e-52 eta_sq 0.2081970 0.16901207 0.2461732 <NA> NA
#> 5 NA <NA> NA NA NA <NA> NA
#> 6 NA <NA> NA NA NA <NA> NABalance: the standardized mean difference
A baseline table comparing two arms is usually read for
balance, not for significance. smd = TRUE adds the
standardized mean difference of the Table 1 literature, and the
idiomatic balance table drops the p column at the same
time:
table_continuous(
sochealth,
select = c(age, bmi, wellbeing_score),
by = sex,
smd = TRUE,
p_value = FALSE
)
#> Descriptive statistics by Sex
#>
#> Variable │ Group M SD Min Max 95% CI LL
#> ───────────────────────────────┼────────────────────────────────────────────────
#> Age (years) │ Female 49.38 14.91 25.00 75.00 48.20
#> │ Male 49.14 14.50 25.00 75.00 47.96
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Body mass index │ Female 25.69 3.78 16.00 38.90 25.39
#> │ Male 26.20 3.64 16.00 37.70 25.90
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Female 67.16 14.80 19.60 100.00 65.99
#> │ Male 71.05 16.23 18.70 100.00 69.73
#>
#> Variable │ Group 95% CI UL n SMD
#> ───────────────────────────────┼───────────────────────────────
#> Age (years) │ Female 50.55 620 0.02
#> │ Male 50.32 580
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Body mass index │ Female 25.98 616 -0.14
#> │ Male 26.50 572
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Female 68.33 620 -0.25
#> │ Male 72.37 580
#>
#> Missing values removed: bmi (12). SMD = standardized mean difference (Female - Male); |SMD| > 0.1 is the usual imbalance threshold.The two arguments are independent — turning the SMD on turns nothing else off, so you have to write both. The rule of thumb the table note quotes is |SMD| > 0.1; spicy prints the number and never highlights it.
The column is signed, group 1 minus group 2 in the
order the table displays the groups, so the direction of an imbalance is
readable without going back to the two means. It requires exactly two
groups: a by with three or more is refused rather than
averaged over pairs, because an average over pairs has no published
reading and can sit under 0.1 while one pair sits well over it.
It is not the effect size
The SMD and Hedges’ g look alike and are never the same
number. On sochealth the two agree to two decimals, which
hides the point, so here they are on a small unbalanced sample where
they cannot hide:
small <- sochealth[c(1:6, 601:604), c("sex", "bmi")]
table_continuous(
small,
select = bmi,
by = sex,
smd = TRUE,
effect_size = "hedges_g",
effect_size_digits = 4
)
#> Descriptive statistics by Sex
#>
#> Variable │ Group M SD Min Max 95% CI LL 95% CI UL n
#> ─────────────────┼────────────────────────────────────────────────────────────
#> Body mass index │ Female 25.03 3.74 19.50 29.10 21.57 28.49 7
#> │ Male 30.20 3.03 27.80 33.60 22.68 37.72 3
#>
#> Variable │ Group p ES SMD
#> ─────────────────┼────────────────────────────────────
#> Body mass index │ Female .072 g = -1.3057 -1.5194
#> │ Male
#>
#> SMD = standardized mean difference (Female - Male); |SMD| > 0.1 is the usual imbalance threshold.Both standardize a mean difference, but by different denominators. Austin’s SMD divides by the root mean of the two group variances; g divides by the degrees-of-freedom pooled SD and then multiplies by the small-sample correction J. Two consequences, both worth knowing:
- At equal group sizes the two denominators coincide, so the SMD is Cohen’s d. At unequal sizes it is not.
- g is never the SMD, at any sample size. With equal groups the ratio g / SMD is exactly J: 0.80 at n = 3 per group, 0.96 at n = 10, approaching 1 only as the sample grows. Reading one for the other costs 20% on a small trial.
Read each for what it is: the SMD is a balance diagnostic, g is an effect size. It also follows that the SMD carries no confidence interval and no p-value — attaching one would put back the test reasoning the balance literature asks the reader to drop.
Selecting variables
select supports tidyselect helpers:
table_continuous(
sochealth,
select = starts_with("life_sat"),
by = sex
)
#> Descriptive statistics by Sex
#>
#> Variable │ Group M SD Min Max
#> ────────────────────────────────────────────┼────────────────────────────────
#> Satisfaction with health (1-5) │ Female 3.51 1.25 1.00 5.00
#> │ Male 3.59 1.25 1.00 5.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with work (1-5) │ Female 3.32 1.17 1.00 5.00
#> │ Male 3.44 1.20 1.00 5.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with relationships (1-5) │ Female 3.71 1.09 1.00 5.00
#> │ Male 3.74 1.10 1.00 5.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with standard of living (1-5) │ Female 3.37 1.16 1.00 5.00
#> │ Male 3.42 1.17 1.00 5.00
#>
#> Variable │ Group 95% CI LL 95% CI UL n
#> ────────────────────────────────────────────┼───────────────────────────────────
#> Satisfaction with health (1-5) │ Female 3.41 3.61 616
#> │ Male 3.49 3.69 576
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with work (1-5) │ Female 3.23 3.41 615
#> │ Male 3.34 3.54 577
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with relationships (1-5) │ Female 3.62 3.79 615
#> │ Male 3.65 3.83 577
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with standard of living (1-5) │ Female 3.28 3.46 615
#> │ Male 3.33 3.52 577
#>
#> Variable │ Group p
#> ────────────────────────────────────────────┼──────────────
#> Satisfaction with health (1-5) │ Female .267
#> │ Male
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with work (1-5) │ Female .073
#> │ Male
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with relationships (1-5) │ Female .570
#> │ Male
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with standard of living (1-5) │ Female .453
#> │ Male
#>
#> Missing values removed: life_sat_health (8), life_sat_work (8), life_sat_relationships (8), life_sat_standard (8).For more programmatic selection, set regex = TRUE:
table_continuous(
sochealth,
select = "^life_sat",
regex = TRUE,
by = education,
output = "data.frame"
)
#> variable label
#> 1 life_sat_health Satisfaction with health (1-5)
#> 2 life_sat_health Satisfaction with health (1-5)
#> 3 life_sat_health Satisfaction with health (1-5)
#> 4 life_sat_work Satisfaction with work (1-5)
#> 5 life_sat_work Satisfaction with work (1-5)
#> 6 life_sat_work Satisfaction with work (1-5)
#> 7 life_sat_relationships Satisfaction with relationships (1-5)
#> 8 life_sat_relationships Satisfaction with relationships (1-5)
#> 9 life_sat_relationships Satisfaction with relationships (1-5)
#> 10 life_sat_standard Satisfaction with standard of living (1-5)
#> 11 life_sat_standard Satisfaction with standard of living (1-5)
#> 12 life_sat_standard Satisfaction with standard of living (1-5)
#> group mean sd min max ci_lower ci_upper median q1 q3
#> 1 Lower secondary 2.714286 1.2021575 1 5 2.567189 2.861382 3 2 3.5
#> 2 Upper secondary 3.533708 1.1853493 1 5 3.432943 3.634473 4 3 5.0
#> 3 Tertiary 4.110276 1.0432216 1 5 4.007602 4.212950 4 3 5.0
#> 4 Lower secondary 2.570881 1.1467994 1 5 2.431102 2.710660 3 2 3.0
#> 5 Upper secondary 3.422430 1.1037312 1 5 3.328691 3.516169 4 3 4.0
#> 6 Tertiary 3.851010 1.0314174 1 5 3.749112 3.952909 4 3 5.0
#> 7 Lower secondary 3.023077 1.2268891 1 5 2.873246 3.172908 3 2 4.0
#> 8 Upper secondary 3.743446 0.9645227 1 5 3.661453 3.825439 4 3 5.0
#> 9 Tertiary 4.158291 0.9322485 1 5 4.066423 4.250159 4 4 5.0
#> 10 Lower secondary 2.666667 1.1635489 1 5 2.524846 2.808487 3 2 3.0
#> 11 Upper secondary 3.387218 1.1065913 1 5 3.292970 3.481466 4 3 4.0
#> 12 Tertiary 3.887218 0.9588582 1 5 3.792847 3.981589 4 3 5.0
#> iqr med_ci_lower med_ci_upper n weighted_n test_type statistic df1
#> 1 1.5 3 3 259 NA welch_anova 118.73585 2
#> 2 2.0 3 4 534 NA <NA> NA NA
#> 3 2.0 4 5 399 NA <NA> NA NA
#> 4 1.0 2 3 261 NA welch_anova 105.98821 2
#> 5 1.0 3 4 535 NA <NA> NA NA
#> 6 2.0 4 4 396 NA <NA> NA NA
#> 7 2.0 3 3 260 NA welch_anova 82.35074 2
#> 8 2.0 4 4 534 NA <NA> NA NA
#> 9 1.0 4 5 398 NA <NA> NA NA
#> 10 1.0 2 3 261 NA welch_anova 101.31672 2
#> 11 1.0 3 4 532 NA <NA> NA NA
#> 12 2.0 4 4 399 NA <NA> NA NA
#> df2 p.value smd_type smd_value
#> 1 652.0775 1.063917e-44 <NA> NA
#> 2 NA NA <NA> NA
#> 3 NA NA <NA> NA
#> 4 651.9434 1.398117e-40 <NA> NA
#> 5 NA NA <NA> NA
#> 6 NA NA <NA> NA
#> 7 617.9668 1.969764e-32 <NA> NA
#> 8 NA NA <NA> NA
#> 9 NA NA <NA> NA
#> 10 648.7723 5.105889e-39 <NA> NA
#> 11 NA NA <NA> NA
#> 12 NA NA <NA> NAUse exclude when you want a broad selection with one or
two explicit removals:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health, life_sat_work),
exclude = "life_sat_work",
by = sex
)
#> Descriptive statistics by Sex
#>
#> Variable │ Group M SD Min Max
#> ────────────────────────────────┼─────────────────────────────────────
#> Body mass index │ Female 25.69 3.78 16.00 38.90
#> │ Male 26.20 3.64 16.00 37.70
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Female 67.16 14.80 19.60 100.00
#> │ Male 71.05 16.23 18.70 100.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Female 3.51 1.25 1.00 5.00
#> │ Male 3.59 1.25 1.00 5.00
#>
#> Variable │ Group 95% CI LL 95% CI UL n p
#> ────────────────────────────────┼──────────────────────────────────────────
#> Body mass index │ Female 25.39 25.98 616 .018
#> │ Male 25.90 26.50 572
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Female 65.99 68.33 620 <.001
#> │ Male 69.73 72.37 580
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Female 3.41 3.61 616 .267
#> │ Male 3.49 3.69 576
#>
#> Missing values removed: bmi (12), life_sat_health (8).Handling missing values
Missing values can never enter a mean, so they are always excluded from each variable’s statistics. The table discloses the exclusion in a note rather than staying silent:
table_continuous(
sochealth,
select = c(bmi, life_sat_health)
)
#> Descriptive statistics
#>
#> Variable │ M SD Min Max 95% CI LL
#> ────────────────────────────────┼──────────────────────────────────────
#> Body mass index │ 25.93 3.72 16.00 38.90 25.72
#> Satisfaction with health (1-5) │ 3.55 1.25 1.00 5.00 3.48
#>
#> Variable │ 95% CI UL n
#> ────────────────────────────────┼─────────────────
#> Body mass index │ 26.14 1188
#> Satisfaction with health (1-5) │ 3.62 1192
#>
#> Missing values removed: bmi (12), life_sat_health (8).Missing values in by are removed by default
(drop_na = TRUE), and the removal is again disclosed rather
than silent – here in the note (“Rows with missing income_group
removed”) and in a warning:
table_continuous(
sochealth,
select = bmi,
by = income_group
)
#> Warning: 18 observation(s) with NA in `income_group` were excluded.
#> Descriptive statistics by Household income group
#>
#> Variable │ Group M SD Min Max 95% CI LL
#> ─────────────────┼────────────────────────────────────────────────────
#> Body mass index │ Low 26.58 3.94 16.00 38.90 26.08
#> │ Lower middle 26.19 3.47 16.00 37.30 25.84
#> │ Upper middle 25.66 3.89 16.00 37.70 25.24
#> │ High 25.15 3.43 16.00 35.00 24.68
#>
#> Variable │ Group 95% CI UL n p
#> ─────────────────┼─────────────────────────────────────
#> Body mass index │ Low 27.07 246 <.001
#> │ Lower middle 26.53 385
#> │ Upper middle 26.09 325
#> │ High 25.61 214
#>
#> Missing values removed: bmi (12). Rows with missing income_group removed: 18.Set drop_na = FALSE to display those rows as a dedicated
“(Missing)” group instead. The group-comparison test and effect size
still cover the observed groups only, matching
table_categorical():
table_continuous(
sochealth,
select = bmi,
by = income_group,
drop_na = FALSE
)
#> Descriptive statistics by Household income group
#>
#> Variable │ Group M SD Min Max 95% CI LL
#> ─────────────────┼────────────────────────────────────────────────────
#> Body mass index │ Low 26.58 3.94 16.00 38.90 26.08
#> │ Lower middle 26.19 3.47 16.00 37.30 25.84
#> │ Upper middle 25.66 3.89 16.00 37.70 25.24
#> │ High 25.15 3.43 16.00 35.00 24.68
#> │ (Missing) 25.83 4.08 18.50 31.80 23.80
#>
#> Variable │ Group 95% CI UL n p
#> ─────────────────┼─────────────────────────────────────
#> Body mass index │ Low 27.07 246 <.001
#> │ Lower middle 26.53 385
#> │ Upper middle 26.09 325
#> │ High 25.61 214
#> │ (Missing) 27.86 18
#>
#> Missing values removed: bmi (12).Weights
Survey data usually comes with case weights, and
sochealth carries one. Passing it weights every displayed
statistic — mean, SD, quantiles, extremes, and the CI of the mean — and
the table says so in its note:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score),
weights = weight,
rescale = TRUE
)
#> Descriptive statistics
#>
#> Variable │ M SD Min Max 95% CI LL
#> ───────────────────────────────┼────────────────────────────────────────
#> Body mass index │ 25.72 3.69 16.00 38.90 25.51
#> WHO-5 wellbeing index (0-100) │ 68.78 15.54 18.70 100.00 67.90
#>
#> Variable │ 95% CI UL n
#> ───────────────────────────────┼─────────────────
#> Body mass index │ 25.94 1188
#> WHO-5 wellbeing index (0-100) │ 69.66 1200
#>
#> Statistics weighted by weight. Missing values removed: bmi (12).Two conventions coexist for weighted statistics, and spicy makes the
choice explicit instead of silent. Without rescale, weights
are taken as frequencies: integer weights reproduce, exactly,
the statistics of the data with each row repeated w times —
the reading of SPSS’s WEIGHT BY and Stata’s
fweight. With rescale = TRUE, weights are
first normalised to sum to the number of observations — the
sampling-weights reading, invariant to the scale of the
weights, whose SD matches Stata’s aweight and
survey::svyvar(). For a survey weight like this one,
rescale = TRUE is the reading you want. The mean is the
same under both (it is a ratio); the SD and the weighted_n
column differ. The exact formulas and the cross-software correspondence
are in the Weights section of ?table_continuous.
Two things are deliberately refused under weights rather than
silently wrong: the median confidence interval (an order-statistic
interval with no weighted version), and the group tests and effect sizes
— a t-test printed next to weighted descriptives would itself
be unweighted. For weighted group comparisons,
table_continuous_lm() takes the same weights
argument and fits them properly:
# Weighted descriptives by group: turn the test columns off
table_continuous(
sochealth,
select = bmi,
by = sex,
weights = weight,
rescale = TRUE,
p_value = FALSE
)
# Weighted group comparison: the model-based tool
table_continuous_lm(sochealth, select = bmi, by = sex, weights = weight)The standardized mean difference is the exception, and passes under weights:
table_continuous(
sochealth,
select = c(age, bmi),
by = sex,
weights = weight,
rescale = TRUE,
smd = TRUE,
p_value = FALSE
)
#> Descriptive statistics by Sex
#>
#> Variable │ Group M SD Min Max 95% CI LL 95% CI UL
#> ─────────────────┼──────────────────────────────────────────────────────────
#> Age (years) │ Female 45.14 14.48 25.00 75.00 44.03 46.25
#> │ Male 44.86 13.96 25.00 75.00 43.68 46.03
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Body mass index │ Female 25.51 3.75 16.00 38.90 25.22 25.80
#> │ Male 25.98 3.61 16.00 37.70 25.67 26.29
#>
#> Variable │ Group n SMD
#> ─────────────────┼────────────────────
#> Age (years) │ Female 620 0.02
#> │ Male 580
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Body mass index │ Female 616 -0.13
#> │ Male 572
#>
#> Statistics weighted by weight. Missing values removed: bmi (12). SMD = standardized mean difference (Female - Male); |SMD| > 0.1 is the usual imbalance threshold.It is a descriptive balance diagnostic with no p and no
interval — which is precisely why the balance literature substitutes it
for the test — and it is computed from the same weighted means and
variances the M and SD columns display, so it cannot be unweighted
inference sitting next to weighted descriptives. One consequence of that
shared producer: without rescale, the weighted SMD inherits
the frequency reading and is not invariant to the scale of the
weights, exactly as the SD column is not. With
rescale = TRUE it is. For a survey weight, use
rescale = TRUE.
Custom labels
By default, table_continuous() labels each variable with
its label attribute when one is present (e.g. data imported with
haven), and with the column name otherwise – that is why
the tables above read “Body mass index” rather than bmi.
Use the labels argument, a named character vector keyed by
column name, to override either. Only the listed columns are relabelled;
the others keep their attribute label or column name:
table_continuous(
sochealth,
select = c(wellbeing_score, life_sat_health),
by = sex,
labels = c(wellbeing_score = "Well-being score (0-100)")
)
#> Descriptive statistics by Sex
#>
#> Variable │ Group M SD Min Max
#> ────────────────────────────────┼─────────────────────────────────────
#> Well-being score (0-100) │ Female 67.16 14.80 19.60 100.00
#> │ Male 71.05 16.23 18.70 100.00
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Female 3.51 1.25 1.00 5.00
#> │ Male 3.59 1.25 1.00 5.00
#>
#> Variable │ Group 95% CI LL 95% CI UL n p
#> ────────────────────────────────┼──────────────────────────────────────────
#> Well-being score (0-100) │ Female 65.99 68.33 620 <.001
#> │ Male 69.73 72.37 580
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> Satisfaction with health (1-5) │ Female 3.41 3.61 616 .267
#> │ Male 3.49 3.69 576
#>
#> Missing values removed: life_sat_health (8).Display options
The printed ASCII table and every rendered output share the same
formatting vocabulary as table_continuous_lm();
align, p_digits, and decimal_mark
are also shared with table_categorical():
-
align = "decimal"(default) aligns numeric columns on the decimal mark, matching SPSS / SAS / LaTeXsiunitxconventions."center"and"right"are the alternatives. -
p_digits = 3(default, the APA standard) drives both the displayed precision of thepcolumn and the small-p threshold: withp_digits = 4, the chunk below shows.0176for BMI and<.0001for the well-being score. -
show_n = FALSEandci = FALSEdrop the corresponding columns (and the CI spanner / borders) structurally from every output; the underlyingnandci_lower/ci_upperare always present inoutput = "data.frame"/"long"for downstream code.
table_continuous(
sochealth,
select = c(bmi, wellbeing_score),
by = sex,
ci = FALSE,
show_n = FALSE,
p_digits = 4
)
#> Descriptive statistics by Sex
#>
#> Variable │ Group M SD Min Max p
#> ───────────────────────────────┼─────────────────────────────────────────────
#> Body mass index │ Female 25.69 3.78 16.00 38.90 .0176
#> │ Male 26.20 3.64 16.00 37.70
#> ╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌
#> WHO-5 wellbeing index (0-100) │ Female 67.16 14.80 19.60 100.00 <.0001
#> │ Male 71.05 16.23 18.70 100.00
#>
#> Missing values removed: bmi (12).Tidying for downstream pipelines
table_continuous() returns an object that can be coerced
to a plain data.frame / tbl_df (stripping the
spicy formatting attributes) or piped into broom::tidy() /
broom::glance() for any downstream tidyverse stats
workflow:
out <- table_continuous(
sochealth,
select = c(bmi, wellbeing_score),
by = sex
)
# Long descriptive rows: one per (variable x group) with broom-style
# columns (outcome, label, group, estimate = mean, std.error,
# conf.low / conf.high, n, min, max, sd).
broom::tidy(out)
#> # A tibble: 4 × 11
#> outcome label group estimate std.error conf.low conf.high n min max
#> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <int> <dbl> <dbl>
#> 1 bmi Body… Fema… 25.7 0.152 25.4 26.0 616 16 38.9
#> 2 bmi Body… Male 26.2 0.152 25.9 26.5 572 16 37.7
#> 3 wellbeing… WHO-… Fema… 67.2 0.594 66.0 68.3 620 19.6 100
#> 4 wellbeing… WHO-… Male 71.0 0.674 69.7 72.4 580 18.7 100
#> # ℹ 1 more variable: sd <dbl>
# One row per outcome with the omnibus test + effect-size summary
# (test_type, statistic, df, df.residual, p.value, es_type, es_value,
# es_ci_lower / es_ci_upper, n_total).
broom::glance(out)
#> # A tibble: 2 × 14
#> outcome label test_type statistic df df.residual p.value es_type es_value
#> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <chr> <dbl>
#> 1 bmi Body… welch_t -2.38 1184. NA 1.76e-2 NA NA
#> 2 wellbein… WHO-… welch_t -4.33 1169. NA 1.65e-5 NA NA
#> # ℹ 5 more variables: es_ci_lower <dbl>, es_ci_upper <dbl>, smd_type <chr>,
#> # smd_value <dbl>, n_total <int>
# Or just unbox to a plain data.frame (long-format underlying data)
head(as.data.frame(out))
#> variable label group mean sd min
#> 1 bmi Body mass index Female 25.68506 3.781113 16.0
#> 2 bmi Body mass index Male 26.19685 3.638092 16.0
#> 3 wellbeing_score WHO-5 wellbeing index (0-100) Female 67.16194 14.798488 19.6
#> 4 wellbeing_score WHO-5 wellbeing index (0-100) Male 71.04879 16.227304 18.7
#> max ci_lower ci_upper median q1 q3 iqr med_ci_lower med_ci_upper
#> 1 38.9 25.38588 25.98425 25.7 23.100 28.600 5.500 25.4 26.1
#> 2 37.7 25.89808 26.49563 26.1 23.875 28.625 4.750 25.8 26.6
#> 3 100.0 65.99480 68.32907 68.2 57.300 77.525 20.225 66.6 69.7
#> 4 100.0 69.72540 72.37219 72.3 61.275 81.575 20.300 70.8 73.2
#> n weighted_n test_type statistic df1 df2 p.value smd_type
#> 1 616 NA welch_t -2.377237 1184.497 NA 1.760093e-02 <NA>
#> 2 572 NA <NA> NA NA NA NA <NA>
#> 3 620 NA welch_t -4.326141 1168.700 NA 1.647005e-05 <NA>
#> 4 580 NA <NA> NA NA NA NA <NA>
#> smd_value
#> 1 NA
#> 2 NA
#> 3 NA
#> 4 NAOutput formats
table_continuous() supports the same reporting-oriented
outputs as table_categorical():
output value |
Returned object |
|---|---|
"default" |
Styled ASCII console table |
"data.frame" / "long"
|
Plain data.frame with the underlying
long-format rows (synonyms; pick whichever reads better in your
code) |
"tinytable" |
Formatted tinytable |
"gt" |
Formatted gt table |
"flextable" |
Formatted flextable |
"excel" |
Written .xlsx file |
"clipboard" |
Copied text table |
"word" |
Written .docx file |
output = "gt" produces a formatted gt table with
APA-style borders and column spanners:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health),
by = education,
output = "gt"
)| Descriptive statistics by Highest education level | |||||||||
|
Variable
|
Group
|
M
|
SD
|
Min
|
Max
|
95% CI
|
n
|
p
|
|
|---|---|---|---|---|---|---|---|---|---|
| LL | UL | ||||||||
| Body mass index | Lower secondary | 28.09 | 3.47 | 18.20 | 38.90 | 27.66 | 28.51 | 260 | <.001 |
| Upper secondary | 26.02 | 3.43 | 16.00 | 37.10 | 25.73 | 26.31 | 534 | ||
| Tertiary | 24.39 | 3.52 | 16.00 | 33.00 | 24.04 | 24.74 | 394 | ||
| WHO-5 wellbeing index (0-100) | Lower secondary | 57.22 | 15.44 | 18.70 | 97.90 | 55.33 | 59.10 | 261 | <.001 |
| Upper secondary | 68.97 | 13.62 | 26.70 | 100.00 | 67.82 | 70.12 | 539 | ||
| Tertiary | 76.85 | 13.23 | 40.40 | 100.00 | 75.55 | 78.15 | 400 | ||
| Satisfaction with health (1-5) | Lower secondary | 2.71 | 1.20 | 1.00 | 5.00 | 2.57 | 2.86 | 259 | <.001 |
| Upper secondary | 3.53 | 1.19 | 1.00 | 5.00 | 3.43 | 3.63 | 534 | ||
| Tertiary | 4.11 | 1.04 | 1.00 | 5.00 | 4.01 | 4.21 | 399 | ||
Missing values removed: bmi (12), life_sat_health (8).
output = "tinytable" works well in Quarto and R Markdown
documents:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health),
by = education,
output = "tinytable"
)| Variable | Group | M | SD | Min | Max | 95% CI | n | p | |
|---|---|---|---|---|---|---|---|---|---|
| LL | UL | ||||||||
| Missing values removed: bmi (12), life_sat_health (8). | |||||||||
| Body mass index | Lower secondary | 28.09 | 3.47 | 18.20 | 38.90 | 27.66 | 28.51 | 260 | <.001 |
| Upper secondary | 26.02 | 3.43 | 16.00 | 37.10 | 25.73 | 26.31 | 534 | ||
| Tertiary | 24.39 | 3.52 | 16.00 | 33.00 | 24.04 | 24.74 | 394 | ||
| WHO-5 wellbeing index (0-100) | Lower secondary | 57.22 | 15.44 | 18.70 | 97.90 | 55.33 | 59.10 | 261 | <.001 |
| Upper secondary | 68.97 | 13.62 | 26.70 | 100.00 | 67.82 | 70.12 | 539 | ||
| Tertiary | 76.85 | 13.23 | 40.40 | 100.00 | 75.55 | 78.15 | 400 | ||
| Satisfaction with health (1-5) | Lower secondary | 2.71 | 1.20 | 1.00 | 5.00 | 2.57 | 2.86 | 259 | <.001 |
| Upper secondary | 3.53 | 1.19 | 1.00 | 5.00 | 3.43 | 3.63 | 534 | ||
| Tertiary | 4.11 | 1.04 | 1.00 | 5.00 | 4.01 | 4.21 | 399 | ||
Export to Excel or Word
Use the same function to export the table directly:
table_continuous(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health),
by = education,
output = "excel",
excel_path = "table_continuous.xlsx"
)
table_continuous(
sochealth,
select = c(bmi, wellbeing_score, life_sat_health),
by = education,
output = "word",
word_path = "table_continuous.docx"
)See also
- See Categorical summary tables for grouped tables of categorical variables.
- See One outcome across several groupings for the transposed shape: ONE continuous outcome described across the levels of SEVERAL groupings, one block of rows per grouping. Several outcomes across one grouping is this article; one outcome across one or more groupings is that one.
- See Model-based continuous summary tables for model-based continuous summary tables with robust standard errors or case weights.
- See Publication-ready regression tables for full regression tables from one or more fitted models (APA Table 3).
- See Summary tables for reporting for a cross-function reporting workflow that ties the four summary-table helpers together along the APA Table 1 / 2 / 3 sequence.