### Install meta Package from GitHub (without vignettes)

Source: https://github.com/guido-s/meta/blob/develop/README.md

Install the development version of the 'meta' package from GitHub without building the vignettes for a faster installation.

```r
remotes::install_github("guido-s/meta")
```

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

### Install meta Package from GitHub

Source: https://github.com/guido-s/meta/blob/develop/README.md

Install the development version of the 'meta' package directly from GitHub using the 'remotes' package. Set 'build_vignettes = TRUE' to include package vignettes.

```r
install.packages("remotes")
remotes::install_github("guido-s/meta", build_vignettes = TRUE)
```

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

### Install meta Package from CRAN

Source: https://github.com/guido-s/meta/blob/develop/README.md

Use this command to install the latest stable release of the 'meta' package from the Comprehensive R Archive Network (CRAN).

```r
install.packages("meta")
```

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

### Standard Meta-Analysis Result Object Creation

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/README.md

Demonstrates how to create a standard meta-analysis result object using the `metagen` function and provides examples of accessing key results.

```r
m <- metagen(TE, seTE, studlab = study, data = data)
```

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

### Simple Meta-analysis with metagen

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-metaanalysis-functions.md

Example of using the `metagen` function with pre-calculated log hazard ratios and their standard errors. Shows how to perform the analysis and access key results like the random effects estimate, between-study variance, and heterogeneity index.

```r
# Simple example with pre-calculated log hazard ratios
data <- data.frame(
  study = c("Study A", "Study B", "Study C"),
  TE = c(0.15, 0.22, 0.18),
  seTE = c(0.10, 0.12, 0.08)
)

m <- metagen(TE = TE, seTE = seTE, studlab = study,
             data = data, 
             sm = "logHR",
             method.tau = "DL")
print(m)

# Access results
m$TE.random        # Random effects estimate
m$tau2             # Between-study variance
m$I2               # Heterogeneity index

```

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

### Retrieve Specific Meta-Analysis Setting

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/quick-reference.md

Use `gs()` (get setting) with the setting name as a string argument to retrieve a specific configuration value, such as the method for estimating tau.

```r
# Get specific setting
method <- gs("method.tau")
```

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

### Get Global Setting Value

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Use this low-level function to retrieve a specific global setting value by its keyword. Provide a default value if the setting might not exist.

```r
default.tau.method <- gs("method.tau")
```

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

### Get Current Meta-Analysis Settings

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Retrieve all current global settings or a specific setting using gs().

```r
# Get all settings
settings <- settings.meta()

# Get specific setting
common_default <- gs("common")
```

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

### Plot Customization in R

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/quick-reference.md

Examples of customizing forest plots by controlling displayed elements and appearance, and saving plots to files. Ensure 'm' is a valid meta-analysis object.

```r
# Control what's displayed
forest(m,
  common = TRUE,        # Show common effect
  random = TRUE,        # Show random effects
  prediction = TRUE,    # Show prediction interval
  subgroup = TRUE,      # Show subgroups
  study.results = TRUE  # Show individual studies
)
```

```r
# Customize appearance
forest(m,
  col.common = "blue",
  col.random = "red",
  text.common = "Fixed Effect",
  text.random = "Random Effects"
)
```

```r
# Save to file
forest(m, filename = "plot.png", path = "/output")
forest(m, filename = "plot.pdf", width = 10, height = 12)
```

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

### Rerun Analysis with Different Tau Estimation Method

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/quick-reference.md

Use the `update` function to rerun a meta-analysis with modified parameters. This example changes the method used for estimating the between-study variance (tau).

```r
# Change analysis method
m2 <- update(m, method.tau = "ML")
```

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

### Configure Default Meta-Analysis Settings

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/quick-reference.md

Use `settings.meta()` with named arguments to set multiple default analysis parameters at once. These defaults will be used in subsequent `metagen` or other meta-analysis function calls unless overridden.

```r
# Set multiple defaults at once
settings.meta(
  common = TRUE,
  random = TRUE,
  method.tau = "REML",
  method.random.ci = "HK",
  level = 0.95,
  prediction = TRUE
)
```

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

### Basic Meta-Analysis Workflow

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/quick-reference.md

Perform a basic meta-analysis by preparing data, running the analysis, displaying results, and visualizing the forest plot. Assumes continuous data with 'MD' as the summary measure.

```r
# 1. Prepare data
data <- read.csv("meta_data.csv")

# 2. Run analysis
m <- metagen(TE = TE, seTE = seTE, studlab = study,
             data = data, sm = "MD")

# 3. Display results
print(m)
summary(m)

# 4. Visualize
forest(m)
funnel(m)
```

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

### Get meta Package Citation

Source: https://github.com/guido-s/meta/blob/develop/README.md

Retrieve the citation information for the 'meta' R package in a format suitable for inclusion in publications.

```r
citation(package = "meta")
```

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

### Set Common Effect Label

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Customize the label used for the common effect estimate in the output. For example, change from 'Common effect' to 'Fixed effect'.

```r
settings.meta(text.common = "Fixed effect")
```

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

### Retrieve All Meta-Analysis Settings

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/quick-reference.md

Call `settings.meta()` without arguments to retrieve all currently configured default settings for meta-analysis functions.

```r
# Get all current settings
all_settings <- settings.meta()
```

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

### gs() - Get global settings

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Low-level function to retrieve a specific global setting value. It takes a keyword and an optional default value if the setting is not found.

```APIDOC
## gs() - Get global settings

### Description
Low-level function to retrieve a specific global setting value.

### Signature
```r
gs(keyword, NULL.value = NULL)
```

### Parameters
#### Path Parameters
- **keyword** (character) - Required - Setting name to retrieve
- **NULL.value** (any) - Optional - Value if setting not found (Default: NULL)

### Return Value
**Type:** The value of the requested setting

### Example
```r
default.tau.method <- gs("method.tau")
```
```

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

### Set Random Effects Label

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Customize the label used for the random effects estimate in the output. For example, change from 'Random effects' to 'DL random effects'.

```r
settings.meta(text.random = "DL random effects")
```

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

### asin2p() - Back-transform from arcsine to proportion

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Inverse arcsine transformation to convert back to proportion scale.

```APIDOC
## asin2p()

### Description
Inverse arcsine transformation to convert back to proportion scale.

### Parameters
#### Path Parameters
- None
#### Query Parameters
- None
#### Request Body
- **x** (numeric vector) - Required - Arcsine-transformed values

### Response
#### Success Response (200)
- **Type:** numeric vector of proportions

### Formula
p = sin²(x)
```

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

### Save Custom Defaults in .Rprofile

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Persist custom meta-analysis settings by defining them in the .Rprofile or a startup script using .First().

```r
# In .Rprofile or startup script
.First <- function() {
  library(meta)
  settings.meta(
    method.tau = "DL",
    method.random.ci = "HK",
    common = FALSE,
    random = TRUE
  )
}
```

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

### Configure Publication-Ready Output

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Adjust settings for publication-ready meta-analysis output, including number of digits, text labels, and forest plot layout.

```r
settings.meta(
  digits = 2,
  digits.se = 2,
  digits.I2 = 1,
  text.common = "Fixed Effect",
  text.random = "Random Effects",
  forest.layout = "JAMA"          # Publication style
)
```

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

### settings.meta()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Query existing or set new global default settings for meta-analysis functions. Settings are stored in package environment and inherited by all subsequent analyses unless overridden.

```APIDOC
## settings.meta()

### Description
Query existing or set new global default settings for meta-analysis functions. Settings are stored in package environment and inherited by all subsequent analyses unless overridden.

### Signature
```r
settings.meta(common = NULL, random = NULL,
              method.tau = NULL, method.tau.ci = NULL,
              method.I2 = NULL,
              method.common.ci = NULL, method.random.ci = NULL,
              prediction = NULL, method.predict = NULL,
              level = NULL, level.ma = NULL,
              adhoc.hakn.ci = NULL, adhoc.hakn.pi = NULL,
              sm = NULL, ...)
```

### Parameters

#### Parameters
- **common** (logical) - No - NULL - Default common effect setting
- **random** (logical) - No - NULL - Default random effects setting
- **method.tau** (character) - No - NULL - Default tau² estimation
- **method.tau.ci** (character) - No - NULL - Default tau² CI method
- **method.I2** (character) - No - NULL - Default I² method
- **method.common.ci** (character) - No - NULL - Default common effect CI
- **method.random.ci** (character) - No - NULL - Default random effects CI
- **prediction** (logical) - No - NULL - Default prediction interval
- **method.predict** (character) - No - NULL - Default prediction method
- **level** (numeric) - No - NULL - Default individual CI level
- **level.ma** (numeric) - No - NULL - Default pooled estimate CI level
- **adhoc.hakn.ci** (character) - No - NULL - Hartung-Knapp ad-hoc adjustment
- **adhoc.hakn.pi** (character) - No - NULL - Hartung-Knapp for PI adjustment
- **sm** (character) - No - NULL - Default summary measure

### Return Value

**Type:** Invisibly returns list of all current settings

### Example

```r
# Query current settings
current <- settings.meta()
print(current)

# Set new defaults
settings.meta(
  common = FALSE,
  random = TRUE,
  method.tau = "REML",
  method.random.ci = "HK",
  level = 0.95
)

# All subsequent meta-analysis calls use these settings
m <- metagen(TE, seTE, studlab = study, data = data)
```
```

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

### Configure Cochrane Recommended Settings

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Set meta-analysis defaults according to Cochrane recommendations, including DL method for tau, Hartung-Knapp for random effects CI, and Egger's test for bias.

```r
settings.meta(
  method.tau = "DL",              # DerSimonian-Laird
  method.random.ci = "HK",        # Hartung-Knapp
  method.bias = "Egger",          # Egger regression test
  common = TRUE,
  random = TRUE,
  prediction = TRUE
)
```

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

### Sensitivity and Influence Analysis

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/quick-reference.md

Examine study influence using meta-inf, visualize influence using a forest plot, and perform a leave-one-out comparison. Includes an example of subsetting to exclude outliers.

```r
# Examine study influence
mi <- metainf(m, pooled = "random")
forest(mi)

# Leave-one-out comparison
print(mi)

# Exclude outliers and rerun
m_clean <- subset(m, abs(TE - m$TE.random) < 2*m$seTE.random)
print(m_clean)
```

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

### Set Heterogeneity Index (I²) Calculation Method

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Choose the method for calculating the heterogeneity index (I²). The 'Q' method, based on the Q statistic, is the default.

```r
settings.meta(method.I2 = "Q")
```

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

### read.cdir()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Imports meta-analysis data from Cochrane Collaboration data files. Supports various Cochrane-specific data formats and specifications.

```APIDOC
## read.cdir()

### Description

Imports meta-analysis data from Cochrane Collaboration data files. Supports various Cochrane-specific data formats and specifications.

### Signature

```r
read.cdir(file, studlab.import = "author", ...)
```

### Parameters

#### Path Parameters

- **file** (character) - Yes - Description: Path to .cdir file
- **studlab.import** (character) - No - Default: "author" - Description: Field to use as study labels

#### Other Parameters

- **...** (—) - — - Description: Additional arguments

### Return Value

**Type:** cdir object containing imported data
```

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

### Manipulating Meta-Analysis Results

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/README.md

Provides examples of how to manipulate the meta-analysis result object, including subsetting studies, filtering by year, extracting weights and labels, converting to a data frame, and rerunning the analysis with updated settings.

```r
# Manipulate:
m[1:5]                 # Subset first 5 studies
subset(m, year >= 2010)
weights(m)             # Study weights
labels(m)              # Study labels
as.data.frame(m)       # Convert to data frame
update(m, method.tau = "DL")  # Rerun with different settings
```

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

### Publication Bias Assessment

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/quick-reference.md

Assess publication bias using asymmetry tests like Begg's and Egger's. Visualizes potential bias with a funnel plot and includes an example of adjusting for bias using trimfill.

```r
# Asymmetry tests
b1 <- metabias(m, method = "Begg")
b2 <- metabias(m, method = "Egger")

# Visualize
funnel(m, contour = c(0.95, 0.99))

# Adjust for bias (if detected)
tf <- trimfill(m)
print(tf)
```

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

### Printing and Summarizing Meta-Analysis Results

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/README.md

Illustrates how to print the meta-analysis object for a concise overview, obtain a detailed summary, and generate a forest plot for visualization.

```r
# Print and summarize:
print(m)
summary(m)
forest(m)              # Visualization
```

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

### Heterogeneity Estimation Parameters

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/README.md

Configure how heterogeneity variance (tau²) and the I² index are estimated. Options include different estimation methods for tau² and specifying a fixed tau² value.

```r
method.tau = "REML"     # Tau² estimation (DL, REML, ML, EB, PM, etc.)
tau.preset = NULL       # Fixed tau² (if not estimated)
tau.common = TRUE       # Same tau across subgroups
method.I2 = "Q"         # I² from Q statistic or tau²
```

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

### p2logit() - Logit transformation for proportions

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Applies logit transformation to proportions. Maps p ∈ [0, 1] to logit(p) ∈ (-∞, ∞).

```APIDOC
## p2logit()

### Description
Applies logit transformation to proportions. Maps p ∈ [0, 1] to logit(p) ∈ (-∞, ∞).

### Parameters
#### Path Parameters
- None
#### Query Parameters
- None
#### Request Body
- **x** (numeric vector) - Required - Proportions (0 ≤ p ≤ 1)

### Response
#### Success Response (200)
- **Type:** numeric vector of logit-transformed values

### Formula
logit(p) = ln(p / (1 - p))
```

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

### print.metareg()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Displays meta-regression coefficients, tests, and model statistics.

```APIDOC
## print.metareg()

### Description
Displays meta-regression coefficients, tests, and model statistics.
```

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

### pairwise()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Converts arm-level data into pairwise contrasts, suitable for input into meta-analysis functions.

```APIDOC
## pairwise()

### Description
Transforms network meta-analysis arm-level data into pairwise study contrasts. Critical for facilitating arm-level input to meta-analysis functions.

### Signature
```r
pairwise(treatment, event = NULL, n, studlab, data = NULL, sm = "", method = NA, ...)
```

### Parameters
#### Path Parameters
- **treatment** (character/factor) - Required - Treatment arm labels
- **event** (numeric vector) - Optional - Events (for binary data)
- **n** (numeric vector) - Required - Sample size per arm
- **studlab** (character vector) - Required - Study identifier
- **data** (data.frame) - Optional - Data frame containing variables
- **sm** (character) - Optional - Summary measure
- **method** (character) - Optional - Pooling method

### Return Value
**Type:** `pairwise` object (S3 class) convertible to standard data format

### Example
```r
# Convert network trial data to pairwise format
data_nma <- data.frame(
  study = c("Study1", "Study1", "Study1", "Study2", "Study2"),
  treatment = c("A", "B", "C", "A", "B"),
  event = c(10, 15, 12, 8, 14),
  n = c(100, 100, 100, 90, 90)
)

pw <- pairwise(treatment, event = event, n = n, 
               studlab = study, data = data_nma)
```
```

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

### update() Method

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Reruns a meta-analysis with modified parameters, allowing for sensitivity analyses and parameter exploration without re-initializing the analysis.

```APIDOC
## update() Method

### Description

Modifies one or more parameters and reruns the meta-analysis without needing to call the original function. Useful for sensitivity analyses and parameter exploration.

### Parameters

- **object** (meta object) - Required - The original meta-analysis object.
- **TE** (numeric vector) - Optional - New effect estimates.
- **seTE** (numeric vector) - Optional - New standard errors.
- **studlab** (character vector) - Optional - New study labels.
- **common** (logical) - Optional - Change common effect setting.
- **random** (logical) - Optional - Change random effects setting.
- **method.tau** (character) - Optional - Change heterogeneity method.
- **method.common.ci** (character) - Optional - Change common CI method.
- **method.random.ci** (character) - Optional - Change random CI method.

### Return Value

Updated meta object.

### Example

```r
m <- metagen(TE, seTE, studlab = study, data = data, method.tau = "DL")

# Rerun with different heterogeneity method
m_reml <- update(m, method.tau = "REML")

# Change to random effects only
m_random <- update(m, common = FALSE, random = TRUE)
```
```

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

### Query Meta-Analysis Settings

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/README.md

Retrieve current meta-analysis settings. Use `settings.meta()` to view all settings or `gs("setting.name")` to query a specific parameter.

```r
settings.meta()         # All settings
```

```r
gs("method.tau")        # Specific setting
```

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

### summary.meta()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Creates a summary object containing key results from a meta-analysis. The print method for this object displays results.

```APIDOC
## summary.meta()

### Description
Creates a summary object containing key results. The print method for this object displays results.

### Signature
```r
summary(object, common = object$common, random = object$random,
        prediction = object$prediction, ...)
```

### Return Value
**Type:** `summary.meta` object with components:
- `common` - Common effect results
- `random` - Random effects results
- `heterogeneity` - I², Q, tau²
- `prediction` - Prediction interval
```

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

### logit2p() - Back-transform from logit to proportion

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Inverse logit transformation (expit/logistic function) to convert logit values back to [0, 1].

```APIDOC
## logit2p()

### Description
Inverse logit transformation (expit/logistic function) to convert logit values back to [0, 1].

### Parameters
#### Path Parameters
- None
#### Query Parameters
- None
#### Request Body
- **x** (numeric vector) - Required - Logit-transformed values

### Response
#### Success Response (200)
- **Type:** numeric vector of proportions in [0, 1]

### Formula
p = exp(x) / (1 + exp(x))
```

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

### print.meta()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Prints a formatted summary of meta-analysis results, including pooled estimates, confidence intervals, heterogeneity statistics, and prediction intervals.

```APIDOC
## print.meta()

### Description
Displays a formatted summary of meta-analysis results including pooled estimates, confidence intervals, heterogeneity statistics, and prediction intervals.

### Parameters
- **x** (meta object) - Required - The meta-analysis result object.
- **digits** (numeric) - Optional - Decimal places for estimates. Defaults to global setting.
- **digits.se** (numeric) - Optional - Decimal places for standard errors. Defaults to global setting.
- **common** (logical) - Optional - Whether to show common effect estimates. Defaults to `x$common`.
- **random** (logical) - Optional - Whether to show random effects estimates. Defaults to `x$random`.
- **prediction** (logical) - Optional - Whether to show prediction interval. Defaults to `x$prediction`.
- **test** (logical) - Optional - Test for overall effect. Defaults to NULL.

### Return Value
NULL (invisibly). Prints output as a side effect.

### Example
```r
m <- metagen(TE, seTE, studlab = study, data = data)
print(m)  # Display results

# Control output detail
print(m, common = TRUE, random = TRUE, prediction = FALSE)
```
```

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

### Access Meta-Analysis Object Attributes

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/README.md

Demonstrates how to access key attributes of a meta-analysis object using the '$' notation. This is useful for retrieving specific results like pooled estimates, heterogeneity measures, or original data.

```r
m$TE.random          # Random effects estimate
m$I2                 # Heterogeneity index
m$tau2               # Between-study variance
m$data               # Original input data
```

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

### Enable Prediction Intervals

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Use `settings.meta()` to enable the calculation and display of prediction intervals by default. This setting influences whether prediction intervals are automatically generated.

```r
settings.meta(prediction = TRUE)
```

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

### print.summary.meta()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Displays summary statistics from a meta-analysis object, typically called by the summary() method.

```APIDOC
## print.summary.meta()

### Description
Displays summary statistics from a meta-analysis object. Called by `summary()` method.
```

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

### drapery()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-visualization.md

Creates a drapery plot to visualize the density of effect estimates across the range of observed values, offering insight into the distribution of study effects.

```APIDOC
## drapery()

### Description

Drapery plot shows the density of effect estimates across the range of observed values, visualizing the distribution of study effects.

### Return Value

**Type:** NULL (invisibly)
```

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

### Enable Random Effects Meta-Analysis

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/configuration.md

Use `settings.meta()` to ensure random effects meta-analysis is enabled by default. This is the default behavior but can be explicitly set.

```r
settings.meta(random = TRUE)
```

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

### Utility Functions

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/overview.md

A collection of utility functions for managing settings, transformations, and formatting related to meta-analysis.

```APIDOC
## Utility Functions

### Description
A collection of utility functions for managing settings, transformations, and formatting related to meta-analysis.

### Functions
- **`settings.meta()`**: Queries or sets global meta-analysis defaults.
- **`setvals(meta_object, ...)`**: Sets options within a meta object.
- **`transf(data, transformation_function)`**: Applies a transformation function with metadata.
- **`backtransf(transformed_data)`**: Back-transforms estimates.
- **`gs()`**: Gets global settings.
- **`traffic_light(rob_data)`**: Creates RoB traffic light plots.
- **`rob(rob_data)`**: Performs Risk of Bias assessment.
- **`JAMAlabels()`**: Formats labels for JAMA-style tables.
- **`cilayout()`**: Configures confidence interval display options.
- **`units2inches(value, unit)` / `inches2units(value, unit)`**: Converts between units and inches.
- **`.forestArgs()`**: Accesses forest plot arguments (internal helper).
```

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

### API Data Import Methods

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/MANIFEST.md

Handles data import from various formats and provides S3 method implementations for meta-analysis objects.

```APIDOC
## API Data Import Methods

### Description
Handles data import from various formats and provides S3 method implementations for meta-analysis objects, including printing, summarizing, plotting, and data manipulation.

### Data Import Functions

- `read.rm5()` - RevMan 5 XML format
- `read.mtv()` - RevMan 5 data export
- `read.cdir()` - Cochrane collaboration format

### S3 Methods

- **Print methods:** `print.meta()`, `print.metabias()`, etc.
- **Summary:** `summary.meta()`
- **Plotting:** `plot.meta()`, `plot.cidprop()`
- **Data frame conversion:** `as.data.frame.meta()`
- **Subsetting:** `[.meta()`, `subset.meta()`, `[.pairwise()`, `[.longarm()`
- **Extraction:** `weights.meta()`, `labels.meta()`
- **Modification:** `update.meta()`
- **Regression:** `coef()`, `fitted()`, `residuals()`
```

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

### Query and Set Meta-Analysis Defaults

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Use this function to retrieve current meta-analysis settings or establish new defaults for common effect, random effects, estimation methods, and confidence interval levels. Settings persist for subsequent analyses unless overridden.

```r
# Query current settings
current <- settings.meta()
print(current)

# Set new defaults
settings.meta(
  common = FALSE,
  random = TRUE,
  method.tau = "REML",
  method.random.ci = "HK",
  level = 0.95
)

# All subsequent meta-analysis calls use these settings
m <- metagen(TE, seTE, studlab = study, data = data)
```

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

### read.mtv()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Imports meta-analysis data from RevMan 5 data export files (.mtv or .csv). These are simpler text-based exports containing study-level summary data.

```APIDOC
## read.mtv()

### Description

Imports meta-analysis data from RevMan 5 data export files (.mtv or .csv). These are simpler text-based exports containing study-level summary data.

### Signature

```r
read.mtv(file, sep = ";", ...)
```

### Parameters

#### Path Parameters

- **file** (character) - Yes - Description: Path to .mtv or .csv file
- **sep** (character) - No - Default: ";" - Description: Field separator (typically ";" for mtv)

#### Other Parameters

- **...** (—) - — - Description: Additional arguments passed to read.csv

### Return Value

**Type:** data.frame containing:
- Study identifiers and characteristics
- Outcome data (events, totals, means, SDs as applicable)
- Analysis specifications if included
```

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

### weights() Method

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Extracts study-level weights from meta-analysis for common and/or random effects models. Weights are returned as percentages summing to 100 across studies.

```APIDOC
## weights() Method

### Description

Extracts study-level weights from meta-analysis for common effect and/or random effects models.

### Parameters

- **object** (meta object) - Required - The meta-analysis result object.
- **common** (logical) - Optional - Defaults to `object$common`. Whether to extract common effect weights.
- **random** (logical) - Optional - Defaults to `object$random`. Whether to extract random effects weights.

### Return Value

Numeric matrix with columns `w.common` (if common=TRUE) and `w.random` (if random=TRUE). Weights are percentages (0-100) summing to 100 across studies.

### Example

```r
m <- metagen(TE, seTE, studlab = study, data = data)

# Get all weights
w <- weights(m)

# Get only random effects weights
w_random <- weights(m, common = FALSE, random = TRUE)
```
```

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

### read.rm5()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Imports meta-analysis data from RevMan 5 XML format (.rm5 files). Parses the XML structure and extracts study data, outcome definitions, and meta-analysis specifications.

```APIDOC
## read.rm5()

### Description
Imports meta-analysis data from RevMan 5 XML format (.rm5 files). Parses the XML structure and extracts study data, outcome definitions, and meta-analysis specifications.

### Signature
```r
read.rm5(file, ...)
```

### Parameters
#### Path Parameters
- **file** (character) - Required - Path to .rm5 file
- **...** (-) - - Additional arguments

### Return Value
**Type:** `rm5` object (S3 list) containing:
- `data` - Data frame with extracted study data
- `studies` - Study identifiers
- `outcomes` - Outcome definitions
- `comparisons` - Comparison specifications
- Metadata about analyses present in the file

### Example
```r
# Import RevMan 5 file
review_data <- read.rm5("cochrane_review.rm5")

# Access study data
head(review_data$data)

# Examine available outcomes
names(review_data$outcomes)

# Use in meta-analysis
m <- metabin(event.e = event.e, n.e = n.e,
             event.c = event.c, n.c = n.c,
             studlab = study,
             data = review_data$data)
```
```

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

### plot.cidprop()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-data-import-methods.md

Visualizes confidence intervals for proportions.

```APIDOC
## plot.cidprop()

### Description
Visualizes confidence intervals for proportions.
```

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

### cilayout()

Source: https://github.com/guido-s/meta/blob/develop/_autodocs/api-transformation-utilities.md

Controls display of confidence interval labels in forest plots and tables.

```APIDOC
## cilayout()

### Description
Controls display of confidence interval labels in forest plots and tables.

### Signature
```r
cilayout(show.ci.label, ...)
```

### Method
Not specified (R function)

### Endpoint
Not applicable (R function)

### Parameters
* **show.ci.label**: Controls whether confidence interval labels are shown.
* **...**: Additional arguments.

### Request Example
`cilayout(show.ci.label = TRUE)`

### Response
Returns settings for confidence interval label display.
```