5 Simple and Stratified Descriptive Tables
Using the furniture::table1() function
The table1() function in the furniture package returns a much smaller listing of summary statistics (Barrett, Brignone, and Laxman 2020).
- Categorical Variables: count (percentage) within each category
- Continuous Variables: mean (standard deviation)
5.1 For a Single Categorical Variable
---------------------------------
Mean/Count (SD/%)
n = 100
majorF
Psychology 29 (29%)
Premed 25 (25%)
Biology 21 (21%)
Sociology 15 (15%)
Economics 10 (10%)
---------------------------------5.2 For a Single Continuous Variable
----------------------------
Mean/Count (SD/%)
n = 100
statquiz
6.9 (1.7)
----------------------------5.3 For a Subset of Variables
The variables desired can also be listed inside the function (selarate with commas).
----------------------------
Mean/Count (SD/%)
n = 25
age
59.6 (12.9)
weighin
178.3 (32.0)
stage
0 1 (4%)
1 12 (48%)
2 6 (24%)
3 1 (4%)
4 5 (20%)
totalcin
6.5 (1.5)
----------------------------
---------------------------------------------
Mean/Count (SD/%)
n = 100
majorF
Psychology 29 (29%)
Premed 25 (25%)
Biology 21 (21%)
Sociology 15 (15%)
Economics 10 (10%)
reasonF
Program requirement 41 (41%)
Personal interest 29 (29%)
Advisor recommendation 30 (30%)
statquiz
6.9 (1.7)
---------------------------------------------5.4 Customize the Variable Labels
cancer_clean %>%
furniture::table1("Age, years" = age,
"Weight, pounds" = weighin,
"Cancer Stage" = stage,
"Oral Condition" = totalcin)
----------------------------------
Mean/Count (SD/%)
n = 25
Age, years
59.6 (12.9)
Weight, pounds
178.3 (32.0)
Cancer Stage
0 1 (4%)
1 12 (48%)
2 6 (24%)
3 1 (4%)
4 5 (20%)
Oral Condition
6.5 (1.5)
----------------------------------data_ihno %>%
furniture::table1("Reason For Enrolling" = reasonF,
"Coffee Drinker" = coffeeF,
"Math Phobia" = phobia,
"Statistics Quiz" = statquiz,
"Mathematics Quiz" = mathquiz)
---------------------------------------------------
Mean/Count (SD/%)
n = 85
Reason For Enrolling
Program requirement 33 (38.8%)
Personal interest 27 (31.8%)
Advisor recommendation 25 (29.4%)
Coffee Drinker
Not a regular coffee drinker 50 (58.8%)
Regularly drinks coffee 35 (41.2%)
Math Phobia
3.2 (2.5)
Statistics Quiz
6.8 (1.7)
Mathematics Quiz
29.1 (9.5)
---------------------------------------------------5.5 Stratify -by- a categorical factor
You may use a dplyr::group_by(grouping_var) step before the furniture::table1() step to create summary statistics for different subgroups.
cancer_clean %>%
dplyr::group_by(trt) %>%
furniture::table1("Age, years" = age,
"Weight, pounds" = weighin,
"Cancer Stage" = stage,
"Oral Condition" = totalcin)
------------------------------------------
trt
Placebo Aloe Juice
n = 14 n = 11
Age, years
59.8 (9.0) 59.5 (17.2)
Weight, pounds
167.5 (23.0) 192.0 (37.4)
Cancer Stage
0 0 (0%) 1 (9.1%)
1 8 (57.1%) 4 (36.4%)
2 3 (21.4%) 3 (27.3%)
3 1 (7.1%) 0 (0%)
4 2 (14.3%) 3 (27.3%)
Oral Condition
6.6 (0.9) 6.5 (2.1)
------------------------------------------data_ihno %>%
dplyr::group_by(genderF) %>%
furniture::table1("College Major" = majorF,
"Reason Enrolled" = reasonF,
"Statistics Quiz" = statquiz)
-------------------------------------------------
genderF
Female Male
n = 57 n = 43
College Major
Psychology 19 (33.3%) 10 (23.3%)
Premed 11 (19.3%) 14 (32.6%)
Biology 11 (19.3%) 10 (23.3%)
Sociology 12 (21.1%) 3 (7%)
Economics 4 (7%) 6 (14%)
Reason Enrolled
Program requirement 23 (40.4%) 18 (41.9%)
Personal interest 16 (28.1%) 13 (30.2%)
Advisor recommendation 18 (31.6%) 12 (27.9%)
Statistics Quiz
6.8 (1.7) 6.9 (1.7)
-------------------------------------------------data_ihno %>%
dplyr::mutate(phobia_cut3 = cut(phobia,
breaks = c(0, 2, 4, 10),
include.lowest = TRUE)) %>%
dplyr::group_by(phobia_cut3) %>%
furniture::table1("College Major" = majorF,
"Reason Enrolled" = reasonF,
"Statistics Quiz" = statquiz)
------------------------------------------------------------
phobia_cut3
[0,2] (2,4] (4,10]
n = 39 n = 37 n = 24
College Major
Psychology 7 (17.9%) 12 (32.4%) 10 (41.7%)
Premed 11 (28.2%) 9 (24.3%) 5 (20.8%)
Biology 7 (17.9%) 10 (27%) 4 (16.7%)
Sociology 7 (17.9%) 4 (10.8%) 4 (16.7%)
Economics 7 (17.9%) 2 (5.4%) 1 (4.2%)
Reason Enrolled
Program requirement 4 (10.3%) 23 (62.2%) 14 (58.3%)
Personal interest 25 (64.1%) 3 (8.1%) 1 (4.2%)
Advisor recommendation 10 (25.6%) 11 (29.7%) 9 (37.5%)
Statistics Quiz
7.6 (1.3) 6.6 (1.6) 6.1 (2.0)
------------------------------------------------------------5.6 Add a TOTAL Column
cancer_clean %>%
dplyr::group_by(trt) %>%
furniture::table1("Age, years" = age,
"Weight, pounds" = weighin,
"Cancer Stage" = stage,
"Oral Condition" = totalcin,
total = TRUE)
-------------------------------------------------------
trt
Total Placebo Aloe Juice
n = 25 n = 14 n = 11
Age, years
59.6 (12.9) 59.8 (9.0) 59.5 (17.2)
Weight, pounds
178.3 (32.0) 167.5 (23.0) 192.0 (37.4)
Cancer Stage
0 1 (4%) 0 (0%) 1 (9.1%)
1 12 (48%) 8 (57.1%) 4 (36.4%)
2 6 (24%) 3 (21.4%) 3 (27.3%)
3 1 (4%) 1 (7.1%) 0 (0%)
4 5 (20%) 2 (14.3%) 3 (27.3%)
Oral Condition
6.5 (1.5) 6.6 (0.9) 6.5 (2.1)
-------------------------------------------------------data_ihno %>%
dplyr::group_by(genderF) %>%
furniture::table1("College Major" = majorF,
"Reason Enrolled" = reasonF,
"Statistics Quiz" = statquiz,
total = TRUE)
-----------------------------------------------------------
genderF
Total Female Male
n = 100 n = 57 n = 43
College Major
Psychology 29 (29%) 19 (33.3%) 10 (23.3%)
Premed 25 (25%) 11 (19.3%) 14 (32.6%)
Biology 21 (21%) 11 (19.3%) 10 (23.3%)
Sociology 15 (15%) 12 (21.1%) 3 (7%)
Economics 10 (10%) 4 (7%) 6 (14%)
Reason Enrolled
Program requirement 41 (41%) 23 (40.4%) 18 (41.9%)
Personal interest 29 (29%) 16 (28.1%) 13 (30.2%)
Advisor recommendation 30 (30%) 18 (31.6%) 12 (27.9%)
Statistics Quiz
6.9 (1.7) 6.8 (1.7) 6.9 (1.7)
-----------------------------------------------------------