### Enable Interactive Mode

Source: https://context7.com/cran/regplot/llms.txt

Basic setup for enabling interactive nomogram exploration.

```r
library(regplot)

model <- lm(mpg ~ wt + hp + cyl, data = mtcars)
```

--------------------------------

### Create Regression Nomograms

Source: https://context7.com/cran/regplot/llms.txt

Examples of generating nomograms for linear, Cox survival, and logistic regression models.

```r
library(regplot)
library(survival)

# Example 1: Linear Model Nomogram
n <- 500
X <- cbind(rnorm(n, sd = 1), rnorm(n, sd = 0.5))
Y <- 10 + X %*% c(0.2, 0.1) + rnorm(n, sd = 1)
D <- as.data.frame(cbind(Y, X))
colnames(D) <- c("Y", "x1", "x2")

model <- lm(Y ~ x1 + x2, data = D)

# Basic nomogram with confidence interval for first observation
regplot(model, observation = D[1,], interval = "confidence")

# Example 2: Cox Survival Model Nomogram
data(pbc)
pbccox <- coxph(
  formula = Surv(time, status == 2) ~ age +
    cut(bili, breaks = c(-Inf, 2, 4, Inf)) + sex +
    copper + as.factor(stage),
  data = pbc
)

# Interactive nomogram with points scale and multiple failure times
regplot(
  pbccox,
  observation = pbc[1,],
  clickable = TRUE,        # Enable mouse interaction
  points = TRUE,           # Use 0-100 points scale
  rank = "sd",             # Order variables by importance
  failtime = c(730, 1825)  # Survival probability at 2 and 5 years
)

# Example 3: Logistic Regression Nomogram
data(mtcars)
logit_model <- glm(am ~ mpg + hp + wt, data = mtcars, family = binomial)

regplot(
  logit_model,
  observation = mtcars[1,],
  plots = c("density", "boxes"),  # Density for numeric, boxes for factors
  center = TRUE,                   # Align at mean values
  showP = TRUE,                    # Show p-value asterisks
  subticks = TRUE                  # Add minor tick marks
)
```

--------------------------------

### Configure Survival Model Features

Source: https://context7.com/cran/regplot/llms.txt

Advanced configuration for survival analysis, including failure probabilities and survival quantiles.

```r
library(regplot)
library(survival)
data(pbc)

# Cox model with strata
cox_model <- coxph(
  Surv(time, status == 2) ~ age + sex + strata(edema) + bili + albumin,
  data = pbc,
  x = TRUE, y = TRUE  # Required for rms models
)

# Probability of survival at specific times
regplot(
  cox_model,
  observation = pbc[1,],
  failtime = c(365, 730, 1825),  # 1, 2, and 5 years
  prfail = FALSE                  # Show survival (not failure) probability
)

# Show failure probability instead
regplot(
  cox_model,
  observation = pbc[1,],
  failtime = c(1825),
  prfail = TRUE  # Probability of death before failtime
)

# Survival quantiles (median survival time)
regplot(
  cox_model,
  observation = pbc[1,],
  failtime = c("50%", "25%")  # Median and 25th percentile survival
)

# Parametric survival (Weibull)
survreg_model <- survreg(
  Surv(time, status == 2) ~ age + sex + bili,
  data = pbc,
  dist = "weibull"
)

regplot(
  survreg_model,
  observation = pbc[1,],
  failtime = 1825,
  prfail = TRUE
)
```

--------------------------------

### Configure Distribution Plot Types

Source: https://context7.com/cran/regplot/llms.txt

Demonstrates various visualization styles for covariate distributions using the plots parameter.

```r
library(regplot)

# Create sample model
model <- lm(mpg ~ wt + hp + cyl, data = mtcars)

# Different distribution visualizations
# Density plots for continuous, boxes for factors (default)
regplot(model, plots = c("density", "boxes"))

# Spikes showing frequency
regplot(model, plots = c("spikes", "spikes"))

# Violin plots for continuous variables
regplot(model, plots = c("violin", "boxes"))

# Bean plots (requires beanplot package)
regplot(model, plots = c("bean", "boxes"))

# Boxplots for continuous variables
regplot(model, plots = c("boxplot", "boxes"))

# Empirical CDF
regplot(model, plots = c("ecdf", "boxes"))

# Bar histogram
regplot(model, plots = c("bars", "bars"))

# No distribution plots (just scales)
regplot(model, plots = c("no plot", "no plot"))
```

--------------------------------

### Display Confidence Intervals

Source: https://context7.com/cran/regplot/llms.txt

Use the `interval` argument to display uncertainty bounds on predictions. Options include 'confidence' for the mean prediction and 'prediction' for new observations.

```r
library(regplot)

# Linear model with intervals
model <- lm(mpg ~ wt + hp, data = mtcars)

# Confidence interval on mean prediction
regplot(
  model,
  observation = mtcars[1,],
  interval = "confidence"  # 95% CI for E[Y|X]
)
```

```r
# Prediction interval for new observation
regplot(
  model,
  observation = mtcars[1,],
  interval = "prediction"  # 95% PI for Y_new
)
```

```r
# Confidence intervals on coefficient contributions
regplot(
  model,
  observation = mtcars[1,],
  interval = "coefficients"  # Shows CI on beta*X for each variable
)
```

```r
# Logistic model confidence interval
logit_model <- glm(am ~ mpg + hp + wt, data = mtcars, family = binomial)
regplot(
  logit_model,
  observation = mtcars[1,],
  interval = "confidence"  # CI on probability scale
)
```

--------------------------------

### Enable Interactive Mode in Regplot

Source: https://context7.com/cran/regplot/llms.txt

Use `clickable = TRUE` to enable mouse interaction with the nomogram. Press ESC to exit interactive mode.

```r
regplot(
  model,
  observation = mtcars[1,],
  clickable = TRUE  # Enables mouse interaction
)
```

--------------------------------

### Customize Regplot Appearance

Source: https://context7.com/cran/regplot/llms.txt

Customize colors, fonts, and layout using parameters like `dencol`, `boxcol`, `obscol`, `spkcol`, `cexscales`, `cexvars`, `cexcats`, `droplines`, and `leftlabel`.

```r
regplot(
  model,
  observation = mtcars[1,],
  clickable = TRUE,
  dencol = "#CCCCFF",     # Density fill color
  boxcol = "#FFCCCC",     # Factor box color
  obscol = "#FF0000",     # Observation highlight color
  spkcol = "#0000FF",     # Spike color
  cexscales = 0.9,        # Scale font size
  cexvars = 1.0,          # Variable name font size
  cexcats = 0.8,          # Category label font size
  droplines = TRUE,       # Show vertical droplines
  leftlabel = TRUE        # Labels on left side
)
```

--------------------------------

### Visualize Mixed Effects Models

Source: https://context7.com/cran/regplot/llms.txt

Regplot supports `lmer` and `glmer` models from the `lme4` package, displaying both fixed and random effects. For `glmer`, specify plots using `plots = c("density", "boxes")`.

```r
library(regplot)
library(lme4)

# Linear mixed model
data(sleepstudy)
lmer_model <- lmer(Reaction ~ Days + (1|Subject), data = sleepstudy)

regplot(
  lmer_model,
  observation = sleepstudy[1,],
  clickable = TRUE
)
# Note: An additional random effects scale is shown at top
```

```r
# Generalized linear mixed model
data(cbpp)
glmer_model <- glmer(
  cbind(incidence, size - incidence) ~ period + (1|herd),
  data = cbpp,
  family = binomial
)

regplot(
  glmer_model,
  observation = cbpp[1,],
  plots = c("density", "boxes")
)
# Shows fixed effects nomogram with random effect contribution
```

--------------------------------

### Generate Points Scale Tables

Source: https://context7.com/cran/regplot/llms.txt

Set `points = TRUE` to convert a nomogram into a points-based scoring system. The function returns a list of dataframes for covariate points and total points to probability mapping.

```r
library(regplot)

model <- glm(am ~ mpg + hp + wt, data = mtcars, family = binomial)

# Use points scale (0-100) instead of raw beta*X
points_table <- regplot(
  model,
  observation = mtcars[1,],
  points = TRUE  # Returns points lookup tables
)

# points_table is a list of dataframes:
# - One dataframe per covariate showing variable values and points
# - Final dataframe shows total points to probability mapping

# Access the scoring tables
print(points_table)
# Each element contains:
# - Variable name column with values
# - Points column with corresponding score (0-100)

# Example output structure:
# [[1]] mpg Points
#       15     45
#       20     52
#       25     60
# ...
# [[n]] Total Points  Pr(am)
#       100           0.05
#       200           0.25
#       300           0.75
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.