Package: finalfit 1.1.1

1 Odds ratio plots | 1.01 Standard odds ratio plot (forest plot) | 1.02 Mixed effects odds ratio plot (forest plot) | 1.03 Plotting a subset of variables from a full model | 1.04 Plotting from model object | 1.05 Plotting univariable models | 1.06 Confidence interval type | 1.07 Remove reference levels | 1.08 Manually specifiy x-axis breaks | 1.09 Adjust table column spacing | 1.10 Adjust or remove dependent variable label | 1.11 Add dependent variable label prefix | 1.12 Adjust or remove dependent variable label suffix | 1.13 Adjust table text size | 1.14 Adjust title text size | 1.15 Add plot options | 1.16 Add other options | 2 Hazard ratio plots | 2.01 Standard hazard ratio plot | 3 Coefficient plots | 3.01 Standard coefficient plots | 4 Wrapper for all plot types | 5 Kaplan Meier plots | 5.1 Standard KM plot | 5.2 Adjust using options | 6 Missing data plots

1 Cross tables | 1.01 Default | 1.02 Add or edit variable labels | 1.03 P-value for hypothesis test | 1.04 With Fisher's exact test | 1.05 Parametric explanatory variables | 1.06 Non-parametric explanatory variables | 1.07 Select specific non-parametric variables | 1.08 Missing values for the explanatory variables | 1.09 Pass missing values to statistical tests | 1.10 Row proportions (rather than column) | 1.11 Total column | 1.12 Row totals with missing | 1.13 Row totals without missing | 1.14 Row totals with user-specified column names | 1.15 Order a variable by total | 1.17 Add column totals | 1.18 Add column totals without proportion. | 1.19 Add column totals with user-specified row name and prefix. | 1.20 Label with dependent name | 1.21 Dependent variable with any number of factor levels supported | 1.22 Missing data in the dependent | 1.23 Directly include missing data in dependent | 1.24 Summarise complete cases | 1.25 Actively dropping missing data (and tidyverse functions that strip attributes) | 1.26 Explanatory variable defaults to factor when ≤5 distinct values | 1.27 Keep as continous variable when ≤5 distinct values | 1.28 Stratified crosstables | 1.29 Digits / decimal places | 1.30 Weighted tables | 2 Model tables with finalfit() | 2.01 Default | 2.02 Hide reference levels | 2.03 Model metrics | 2.04 Model metrics can be applied to all supported base models | 2.05 Reduced model | 2.06 Include all models | 2.06 Interactions | 2.07 Interactions: create interaction variable with two factors | 2.08 Dependent name | 2.09 Estimate name | 2.10 Digits / decimal places | 2.11 Confidence interval type | 2.12 Confidence interval level | 2.13 Confidence interval separation | 2.14 Robust standard errors / confidence intervals | 2.15 Remove p-value | 2.16 Mixed effects random-intercept model | 2.16b Mixed effects random-intercept model with univariable estimates including random effects | 2.17 Mixed effects random-slope model | 2.18 Mixed effects random-slope model directly from lme4 | 2.19 Exclude all missing data in final model from univariable analyses | 2.20 Linear regression | 2.21 Mixed effects random-intercept linear regression | 2.22 Mixed effects random-slope linear regression | 2.23 Cox proportional hazards model (survival / time to event) | 2.24 Cox proportional hazards model: change dependent label | 3 Model tables manually using ff_merge() | 3.1 Basic table | 3.2 Complex table (all in single pipe) | 3.3 Other GLM models | Poisson | Gamma | 3.4 Weighted regression | 3.5 Using base R functions | 3.6 Edit table rows | 3.7 Base model + individual explanatory variables | 4 Support for complex survey structures via library(survey) | 4.1 Linear regression | 4.2 Binomial example

Create new dataframe of explanatory variable levels | ff_expand() for creating new data frame | Run bootstrap simulations of model predictions | Output to Word, PDF, and html via RMarkdown | Make comparisons | What is not included? | Plotting

Some confusing terminology | Missing completely at random (MCAR) | Missing at random (MAR) | Missing not at random (MNAR) | 1. Ensure your data are coded correctly: ff_glimpse | Example scenario | 2. Identify missing values in each variable: missing_plot | 3. Look for patterns of missingness: missing_pattern | Make sure you include missing data in demographics tables | 4. Check for associations between missing and observed data: missing_pairs | missing_compare | For those who like an omnibus test | 5. Decide how to handle missing data | MCAR, MAR, or MNAR | MCAR vs MAR | Common solution | Other considerations | MNAR vs MAR | Where to next

Installation and Documentation | Main Features | 1. Summarise variables/factors by a categorical variable | 2. Summarise regression model results in final table format | Logistic regression: glm() | Logistic regression with reduced model: glm() | Mixed effects logistic regression: lme4::glmer() | Cox proportional hazards: survival::coxph() | Add common model metrics to output | Combine multiple models into single table | Bayesian logistic regression: with stan | 3. Summarise regression model results in plot | OR plot | HR plot | Kaplan-Meier survival plots | Notes

Background | Installation | Dataset | Get data and check | Death status | Time and censoring | Recode | Kaplan-Meier survival estimator | KM analysis for whole cohort | Model | Life table | Kaplan Meier plot | Cox-proportional hazards regression | Univariable and multivariable models | Reduced model | Testing for proportional hazards | Stratified models | Correlated groups of observations | Hazard ratio plot | Competing risks regression | Summary

Explore data | Demographics table | Logistic regression table | Odds ratio plot | MS Word via knitr/R Markdown | Create Word template file | PDF via knitr/R Markdown

Read data | Column types | Continuous data | Categorical data | Dates and times | Check data | Specify factors