An "all-in-one" function that takes a single dependent variable with a vector of explanatory variable names (continuous or categorical variables) to produce a final table for publication including summary statistics. The appropriate model is selected on the basis of dependent variable and whether a random effect is specified.
finalfit.lm method (not called directly)
finalfit.glm method (not called directly)
finalfit.coxph method (not called directly)
finalfit(
.data,
dependent = NULL,
explanatory = NULL,
explanatory_multi = NULL,
random_effect = NULL,
formula = NULL,
model_args = list(),
weights = NULL,
cont_cut = 5,
column = NULL,
keep_models = FALSE,
metrics = FALSE,
add_dependent_label = TRUE,
dependent_label_prefix = "Dependent: ",
dependent_label_suffix = "",
keep_fit_id = FALSE,
...
)
finalfit.lm(
.data,
dependent,
explanatory,
explanatory_multi = NULL,
random_effect = NULL,
model_args = NULL,
weights = NULL,
cont_cut = 5,
column = FALSE,
keep_models = FALSE,
metrics = FALSE,
add_dependent_label = TRUE,
dependent_label_prefix = "Dependent: ",
dependent_label_suffix = "",
keep_fit_id = FALSE,
...
)
finalfit.glm(
.data,
dependent,
explanatory,
explanatory_multi = NULL,
random_effect = NULL,
model_args = NULL,
weights = NULL,
cont_cut = 5,
column = FALSE,
keep_models = FALSE,
metrics = FALSE,
add_dependent_label = TRUE,
dependent_label_prefix = "Dependent: ",
dependent_label_suffix = "",
keep_fit_id = FALSE,
...
)
finalfit.coxph(
.data,
dependent,
explanatory,
explanatory_multi = NULL,
random_effect = NULL,
model_args = NULL,
column = TRUE,
cont_cut = 5,
keep_models = FALSE,
metrics = FALSE,
add_dependent_label = TRUE,
dependent_label_prefix = "Dependent: ",
dependent_label_suffix = "",
keep_fit_id = FALSE,
...
)Data frame or tibble.
Character vector of length 1: quoted name of dependent
variable. Can be continuous, a binary factor, or a survival object of form
Surv(time, status).
Character vector of any length: quoted name(s) of explanatory variables.
Character vector of any length: quoted name(s) of a
subset of explanatory variables to generate reduced multivariable model
(must only contain variables contained in explanatory).
Character vector of length 1, either, (1) name of random
intercept variable, e.g. "var1", (automatically convered to "(1 | var1)");
or, (2) the full lme4 specification, e.g. "(var1 | var2)". Note
parenthesis MUST be included in (2) but NOT included in (1).
an object of class "formula" (or one that can be coerced to that class). Optional instead of standard dependent/explanatory format. Do not include if using dependent/explanatory.
Character vector of length 1: quoted name of weights variable.
Passed to summary_factorlist, lm, and glm
to provide weighted summary table and regression (e.g. IPTW). If wish weighted regression
and non-weighted summary table, pass weights argument within model_args.
Not available with surival dependent variable.
Numeric: number of unique values in continuous variable at which to consider it a factor.
Logical: Compute margins by column rather than row.
Logical: include full multivariable model in output when
working with reduced multivariable model (explanatory_multi) and/or
mixed effect models (random_effect).
Logical: include useful model metrics in output in publication format.
Add the name of the dependent label to the top left of table.
Add text before dependent label.
Add text after dependent label.
Keep original model output coefficient label (internal).
Other arguments to pass to fit2df:
estimate_name, digits, confint_type, confint_level,
confint_sep.
Returns a data frame with the final model table.
library(finalfit)
library(dplyr)
# Summary, univariable and multivariable analyses of the form:
# glm(depdendent ~ explanatory, family="binomial")
# lmuni(), lmmulti(), lmmixed(), glmuni(), glmmulti(), glmmixed(), glmmultiboot(),
# coxphuni(), coxphmulti()
data(colon_s) # Modified from survival::colon
explanatory = c("age.factor", "sex.factor", "obstruct.factor", "perfor.factor")
dependent = 'mort_5yr'
colon_s %>%
finalfit(dependent, explanatory)
#> Note: dependent includes missing data. These are dropped.
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Dependent: Mortality 5 year Alive Died
#> Age <40 years 31 (46.3) 36 (53.7)
#> 40-59 years 208 (61.4) 131 (38.6)
#> 60+ years 272 (53.4) 237 (46.6)
#> Sex Female 243 (55.6) 194 (44.4)
#> Male 268 (56.1) 210 (43.9)
#> Obstruction No 408 (56.7) 312 (43.3)
#> Yes 89 (51.1) 85 (48.9)
#> Perforation No 497 (56.0) 391 (44.0)
#> Yes 14 (51.9) 13 (48.1)
#> OR (univariable) OR (multivariable)
#> - -
#> 0.54 (0.32-0.92, p=0.023) 0.57 (0.34-0.98, p=0.041)
#> 0.75 (0.45-1.25, p=0.270) 0.81 (0.48-1.36, p=0.426)
#> - -
#> 0.98 (0.76-1.27, p=0.889) 0.98 (0.75-1.28, p=0.902)
#> - -
#> 1.25 (0.90-1.74, p=0.189) 1.25 (0.90-1.76, p=0.186)
#> - -
#> 1.18 (0.54-2.55, p=0.672) 1.12 (0.51-2.44, p=0.770)
# Multivariable analysis with subset of explanatory
# variable set used in univariable analysis
explanatory = c("age.factor", "sex.factor", "obstruct.factor", "perfor.factor")
explanatory_multi = c("age.factor", "obstruct.factor")
dependent = "mort_5yr"
colon_s %>%
finalfit(dependent, explanatory, explanatory_multi)
#> Note: dependent includes missing data. These are dropped.
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Dependent: Mortality 5 year Alive Died
#> Age <40 years 31 (46.3) 36 (53.7)
#> 40-59 years 208 (61.4) 131 (38.6)
#> 60+ years 272 (53.4) 237 (46.6)
#> Sex Female 243 (55.6) 194 (44.4)
#> Male 268 (56.1) 210 (43.9)
#> Obstruction No 408 (56.7) 312 (43.3)
#> Yes 89 (51.1) 85 (48.9)
#> Perforation No 497 (56.0) 391 (44.0)
#> Yes 14 (51.9) 13 (48.1)
#> OR (univariable) OR (multivariable)
#> - -
#> 0.54 (0.32-0.92, p=0.023) 0.57 (0.34-0.98, p=0.041)
#> 0.75 (0.45-1.25, p=0.270) 0.81 (0.48-1.36, p=0.424)
#> - -
#> 0.98 (0.76-1.27, p=0.889) -
#> - -
#> 1.25 (0.90-1.74, p=0.189) 1.26 (0.90-1.76, p=0.176)
#> - -
#> 1.18 (0.54-2.55, p=0.672) -
# Summary, univariable and multivariable analyses of the form:
# lme4::glmer(dependent ~ explanatory + (1 | random_effect), family="binomial")
explanatory = c("age.factor", "sex.factor", "obstruct.factor", "perfor.factor")
explanatory_multi = c("age.factor", "obstruct.factor")
random_effect = "hospital"
dependent = "mort_5yr"
# colon_s %>%
# finalfit(dependent, explanatory, explanatory_multi, random_effect)
# Include model metrics:
colon_s %>%
finalfit(dependent, explanatory, explanatory_multi, metrics=TRUE)
#> Note: dependent includes missing data. These are dropped.
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Setting levels: control = 0, case = 1
#> Setting direction: controls < cases
#> [[1]]
#> Dependent: Mortality 5 year Alive Died
#> Age <40 years 31 (46.3) 36 (53.7)
#> 40-59 years 208 (61.4) 131 (38.6)
#> 60+ years 272 (53.4) 237 (46.6)
#> Sex Female 243 (55.6) 194 (44.4)
#> Male 268 (56.1) 210 (43.9)
#> Obstruction No 408 (56.7) 312 (43.3)
#> Yes 89 (51.1) 85 (48.9)
#> Perforation No 497 (56.0) 391 (44.0)
#> Yes 14 (51.9) 13 (48.1)
#> OR (univariable) OR (multivariable)
#> - -
#> 0.54 (0.32-0.92, p=0.023) 0.57 (0.34-0.98, p=0.041)
#> 0.75 (0.45-1.25, p=0.270) 0.81 (0.48-1.36, p=0.424)
#> - -
#> 0.98 (0.76-1.27, p=0.889) -
#> - -
#> 1.25 (0.90-1.74, p=0.189) 1.26 (0.90-1.76, p=0.176)
#> - -
#> 1.18 (0.54-2.55, p=0.672) -
#>
#> [[2]]
#>
#> Number in dataframe = 929, Number in model = 894, Missing = 35, AIC = 1226.8, C-statistic = 0.555, H&L = Chi-sq(8) 0.06 (p=1.000)
#>
# Summary, univariable and multivariable analyses of the form:
# survival::coxph(dependent ~ explanatory)
explanatory = c("age.factor", "sex.factor", "obstruct.factor", "perfor.factor")
dependent = "Surv(time, status)"
colon_s %>%
finalfit(dependent, explanatory)
#> Dependent: Surv(time, status) all HR (univariable)
#> Age <40 years 70 (7.5) -
#> 40-59 years 344 (37.0) 0.76 (0.53-1.09, p=0.132)
#> 60+ years 515 (55.4) 0.93 (0.66-1.31, p=0.668)
#> Sex Female 445 (47.9) -
#> Male 484 (52.1) 1.01 (0.84-1.22, p=0.888)
#> Obstruction No 732 (80.6) -
#> Yes 176 (19.4) 1.29 (1.03-1.62, p=0.028)
#> Perforation No 902 (97.1) -
#> Yes 27 (2.9) 1.17 (0.70-1.95, p=0.556)
#> HR (multivariable)
#> -
#> 0.79 (0.55-1.13, p=0.196)
#> 0.98 (0.69-1.40, p=0.926)
#> -
#> 1.02 (0.85-1.23, p=0.812)
#> -
#> 1.30 (1.03-1.64, p=0.026)
#> -
#> 1.08 (0.64-1.81, p=0.785)
# Rather than going all-in-one, any number of subset models can
# be manually added on to a summary_factorlist() table using finalfit.merge().
# This is particularly useful when models take a long-time to run or are complicated.
# Note requirement for fit_id=TRUE.
# `fit2df` is a subfunction extracting most common models to a dataframe.
explanatory = c("age.factor", "sex.factor", "obstruct.factor", "perfor.factor")
dependent = 'mort_5yr'
colon_s %>%
finalfit(dependent, explanatory, metrics=TRUE)
#> Note: dependent includes missing data. These are dropped.
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Setting levels: control = 0, case = 1
#> Setting direction: controls < cases
#> [[1]]
#> Dependent: Mortality 5 year Alive Died
#> Age <40 years 31 (46.3) 36 (53.7)
#> 40-59 years 208 (61.4) 131 (38.6)
#> 60+ years 272 (53.4) 237 (46.6)
#> Sex Female 243 (55.6) 194 (44.4)
#> Male 268 (56.1) 210 (43.9)
#> Obstruction No 408 (56.7) 312 (43.3)
#> Yes 89 (51.1) 85 (48.9)
#> Perforation No 497 (56.0) 391 (44.0)
#> Yes 14 (51.9) 13 (48.1)
#> OR (univariable) OR (multivariable)
#> - -
#> 0.54 (0.32-0.92, p=0.023) 0.57 (0.34-0.98, p=0.041)
#> 0.75 (0.45-1.25, p=0.270) 0.81 (0.48-1.36, p=0.426)
#> - -
#> 0.98 (0.76-1.27, p=0.889) 0.98 (0.75-1.28, p=0.902)
#> - -
#> 1.25 (0.90-1.74, p=0.189) 1.25 (0.90-1.76, p=0.186)
#> - -
#> 1.18 (0.54-2.55, p=0.672) 1.12 (0.51-2.44, p=0.770)
#>
#> [[2]]
#>
#> Number in dataframe = 929, Number in model = 894, Missing = 35, AIC = 1230.7, C-statistic = 0.56, H&L = Chi-sq(8) 5.69 (p=0.682)
#>
explanatory = c("age.factor", "sex.factor", "obstruct.factor", "perfor.factor")
explanatory_multi = c("age.factor", "obstruct.factor")
random_effect = "hospital"
dependent = 'mort_5yr'
# Separate tables
colon_s %>%
summary_factorlist(dependent, explanatory, fit_id=TRUE) -> example.summary
#> Note: dependent includes missing data. These are dropped.
colon_s %>%
glmuni(dependent, explanatory) %>%
fit2df(estimate_suffix=" (univariable)") -> example.univariable
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
#> Waiting for profiling to be done...
colon_s %>%
glmmulti(dependent, explanatory) %>%
fit2df(estimate_suffix=" (multivariable)") -> example.multivariable
#> Waiting for profiling to be done...
# Edited as CRAN slow to run these
# colon_s %>%
# glmmixed(dependent, explanatory, random_effect) %>%
# fit2df(estimate_suffix=" (multilevel") -> example.multilevel
# Pipe together
example.summary %>%
finalfit_merge(example.univariable) %>%
finalfit_merge(example.multivariable, last_merge = TRUE)
#> label levels Alive Died OR (univariable)
#> 3 Age <40 years 31 (6.1) 36 (8.9) -
#> 1 40-59 years 208 (40.7) 131 (32.4) 0.54 (0.32-0.92, p=0.023)
#> 2 60+ years 272 (53.2) 237 (58.7) 0.75 (0.45-1.25, p=0.270)
#> 8 Sex Female 243 (47.6) 194 (48.0) -
#> 9 Male 268 (52.4) 210 (52.0) 0.98 (0.76-1.27, p=0.889)
#> 4 Obstruction No 408 (82.1) 312 (78.6) -
#> 5 Yes 89 (17.9) 85 (21.4) 1.25 (0.90-1.74, p=0.189)
#> 6 Perforation No 497 (97.3) 391 (96.8) -
#> 7 Yes 14 (2.7) 13 (3.2) 1.18 (0.54-2.55, p=0.672)
#> OR (multivariable)
#> 3 -
#> 1 0.57 (0.34-0.98, p=0.041)
#> 2 0.81 (0.48-1.36, p=0.426)
#> 8 -
#> 9 0.98 (0.75-1.28, p=0.902)
#> 4 -
#> 5 1.25 (0.90-1.76, p=0.186)
#> 6 -
#> 7 1.12 (0.51-2.44, p=0.770)
# finalfit_merge(example.multilevel)