### Install and Load meta Package

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Install the 'meta' package from CRAN and load it into your R session. You can also check the installed version.

```r
# Install from CRAN
install.packages("meta")

# Load the package
library(meta)

# Check version
packageVersion("meta")
```

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

### Examples of metabias usage

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metabias.md

Illustrates how to use the metabias function with different test methods and data inputs, including plotting.

```APIDOC
## Examples

```r
# Generic Begg test
data(Fleiss1993bin)
m1 <- metabin(event.e, n.e, event.c, n.c, study,
              data = Fleiss1993bin, sm = "RR")
bias1 <- metabias(m1, method.bias = "Begg")
print(bias1)

# Egger test
bias2 <- metabias(m1, method.bias = "Egger")
print(bias2)

# Thompson test (with between-study variance)
bias3 <- metabias(m1, method.bias = "Thompson")
print(bias3)

# Harbord test (specific for binary outcomes)
bias4 <- metabias(m1, method.bias = "Harbord")
print(bias4)

# Using vectors directly
bias5 <- metabias.default(TE = c(0.3, 0.5, 0.2, 0.4),
                          seTE = c(0.1, 0.15, 0.12, 0.11),
                          method.bias = "Egger")
print(bias5)

# With continuity correction
bias6 <- metabias(m1, method.bias = "Begg", correct = TRUE)
print(bias6)

# Produce plot
bias7 <- metabias(m1, method.bias = "Egger", plotit = TRUE)
```
```

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

### Create Meta-Regression and Bubble Plot

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/bubble.md

This example demonstrates how to prepare data, perform a meta-regression, and generate a basic bubble plot. It requires the `metagen` package and sample data.

```r
data(Fleiss1993cont)
Fleiss1993cont$age <- c(55, 65, 55, 65, 55)
Fleiss1993cont$region <- c("Europe", "Europe", "Asia", "Asia", "Europe")

ma1 <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
                data = Fleiss1993cont, sm = "SMD")

# Meta-regression on age
reg1 <- metareg(ma1, ~age)
bubble(reg1)
```

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

### Meta-Regression with Subgroups

Source: https://github.com/cran/meta/blob/master/_autodocs/README.md

Illustrates how to perform a stratified meta-analysis and then a meta-regression using a covariate. This example uses a binary outcome and adds an 'age' covariate.

```r
# Add covariate to data
Fleiss1993bin$age <- c(55, 65, 55, 65, 55)

# Conduct stratified meta-analysis
m <- metabin(event.e, n.e, event.c, n.c, study,
             data = Fleiss1993bin, subgroup = age)

# Meta-regression
reg <- metareg(m, ~age)
bubble(reg)
```

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

### Get and Set Global Meta-Analysis Settings

Source: https://github.com/cran/meta/blob/master/_autodocs/configuration.md

Retrieve current global settings or specific settings by name. Assign new default values to global settings.

```r
settings.meta(value = NULL, assign = TRUE)
setvals(x, mxchar = 80)
```

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

# Get specific setting
common_default <- settings.meta("common")

# Set global default
settings.meta("common", assign = TRUE)

# Use settings in function call
meta_result <- metagen(TE, seTE, 
                       common = settings.meta()$common,
                       random = settings.meta()$random)
```

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

### R Workflow for Meta-Analysis using 'meta' package

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

This script demonstrates a common workflow for meta-analysis in R, covering data loading, basic analysis, result visualization, bias testing, and data export. Ensure the 'meta' package is installed and loaded.

```r
library(meta)

# Load or create data
data(Fleiss1993bin)

# 1. Basic meta-analysis
m <- metabin(event.e, n.e, event.c, n.c, study,
             data = Fleiss1993bin, sm = "RR",
             common = TRUE, random = TRUE)

# 2. View results
print(m)
summary(m)

# 3. Forest plot
forest(m, layout = "JAMA")

# 4. Funnel plot
funnel(m, type = "contour")

# 5. Check bias
metabias(m)

# 6. Meta-regression if data available
# reg <- metareg(m, ~age)
# bubble(reg)

# 7. Leave-one-out analysis
inf <- metainf(m)
forest(inf)

# 8. Export results
summary_data <- data.frame(
  Study = m$studlab,
  TE = m$TE,
  seTE = m$seTE,
  CI_lower = m$lower,
  CI_upper = m$upper
)
# write.csv(summary_data, "results.csv")
```

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

### Example 3: Meta-Regression

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Conduct a meta-regression analysis on continuous outcome data from Fleiss1993cont, including age as a covariate. Visualize the regression with a bubble plot.

```r
data(Fleiss1993cont)
Fleiss1993cont$age <- c(55, 65, 55, 65, 55)
m <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
              data = Fleiss1993cont)
reg <- metareg(m, ~age)
bubble(reg)
```

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

### Example 2: Continuous Outcome with Subgroups

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Perform a meta-analysis for continuous outcomes with subgroup analysis using the Fleiss1993cont dataset. Results are visualized with a forest plot.

```r
data(Fleiss1993cont)
Fleiss1993cont$group <- c("A", "A", "B", "B", "B")
m <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
              data = Fleiss1993cont, sm = "SMD",
              subgroup = group, tau.common = TRUE)
forest(m)
```

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

### Example 1: Binary Outcome Meta-Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Conduct a meta-analysis for binary outcomes using the Fleiss1993bin dataset, visualize results with a forest plot, funnel plot, and assess bias.

```r
data(Fleiss1993bin)
m <- metabin(event.e, n.e, event.c, n.c, study,
             data = Fleiss1993bin, sm = "RR")
forest(m)
funnel(m)
metabias(m)
```

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

### Appending Original Variables to Contrast-Based Data

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/pairwise.md

This example demonstrates how to use the `append = TRUE` argument in the `pairwise` function to include the original variables from the input data frame in the resulting contrast-based data frame.

```r
pw4 <- pairwise(treat, event, n,
                data = study_data,
                sm = "OR",
                append = TRUE)
```

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

### Raw Scale Proportion Meta-Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metaprop.md

Performs a meta-analysis of proportions directly on the raw scale, scaling the results to percentages. This example uses the 'studies' data frame.

```r
m5 <- metaprop(events, n, study, data = studies,
               sm = "PRAW", pscale = 100)
print(m5)
```

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

### Long Format Continuous Outcome Data Transformation

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/pairwise.md

This example shows how to apply the `pairwise` function to continuous outcome data in a long format. It requires specifying the treatment, sample size, mean, and standard deviation for each arm, along with the study label.

```r
study_long <- data.frame(
  studlab = rep(c("Study A", "Study B"), each = 3),
  treat = rep(c("Control", "Drug A", "Drug B"), 2),
  n = c(50, 50, 50, 60, 60, 60),
  mean = c(10, 12, 14, 11, 13, 15),
  sd = c(2, 2.1, 2.2, 1.9, 2.0, 2.1)
)

pw2 <- pairwise(treat, n, mean, sd,
                data = study_long,
                studlab = studlab,
                sm = "MD")
```

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

### Freeman-Tukey Transformation Meta-Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metaprop.md

Performs a meta-analysis of proportions using the Freeman-Tukey transformation and Inverse pooling method. This example reuses the 'studies' data frame from a previous example.

```r
m3 <- metaprop(events, n, study, data = studies,
               sm = "PFT", method = "Inverse")
print(m3)
```

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

### Basic Meta-Analysis Workflow

Source: https://github.com/cran/meta/blob/master/_autodocs/README.md

Demonstrates a typical workflow for conducting a binary outcome meta-analysis, including data loading, analysis, result printing, and plot generation. Requires the 'meta' package.

```r
library(meta)

# 1. Load data
data(Fleiss1993bin)

# 2. Conduct meta-analysis
m <- metabin(event.e, n.e, event.c, n.c, study,
             data = Fleiss1993bin, sm = "RR")

# 3. Display results
print(m)

# 4. Create plots
forest(m)
funnel(m)

# 5. Assess bias
metabias(m)
```

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

### Prepare Study Data for Meta-Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Create a data frame to hold your study data or import it from a RevMan 5 XML file.

```r
# Create data frame with study data
my_data <- data.frame(
  study = c("Study A", "Study B", "Study C"),
  # Outcome-specific columns
)

# Or import from external format
data <- read.rm5("RevMan5_file.xml")
```

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

### View Meta-Analysis Results

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Print the meta-analysis results, get a detailed summary, or extract specific values like common/random effects estimates and heterogeneity measures.

```r
# Print results
print(m)

# Detailed summary
summary(m)

# Extract specific values
m$TE.common    # Common effect estimate
m$TE.random    # Random effects estimate
m$tau2         # Between-study variance
m$I2           # Heterogeneity index
m$pval.Q       # p-value for heterogeneity test
```

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

### Approximating Missing SDs in Meta-Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metamean.md

Demonstrates approximating missing standard deviations using the 'Wan' method with minimum and maximum values when SD is not directly available. Requires sample sizes, means, and range data.

```r
m2 <- metamean(n = c(50, 60),
               mean = c(10, 11),
               sd = c(2, NA),
               min = c(NA, 5),
               max = c(NA, 17),
               studlab = c("Study 1", "Study 2"),
               method.sd = "Wan")
print(m2)
```

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

### Accessing Meta-Analysis Results

Source: https://github.com/cran/meta/blob/master/_autodocs/types.md

Demonstrates common methods for interacting with a 'meta' object, including printing, summarizing, accessing specific components, and generating plots like forest and funnel plots.

```r
# Print overall results
print(meta_object)
```

```r
# Get summary statistics
summary(meta_object)
```

```r
# Access specific components
meta_object$TE.common
meta_object$TE.random
meta_object$tau2
meta_object$I2
```

```r
# Create forest plot
forest(meta_object)
```

```r
# Create funnel plot
funnel(meta_object)
```

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

### Cumulative meta-analysis with default ordering (binary data)

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metacum.md

Performs a cumulative meta-analysis using default ordering for binary data. Requires a `metabin` object as input. The results can be visualized using the `forest` function.

```r
data(Fleiss1993bin)
m1 <- metabin(event.e, n.e, event.c, n.c, study,
              data = Fleiss1993bin, sm = "RR")

cum1 <- metacum(m1)
forest(cum1)
```

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

### Address Studies with Zero Events

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

For studies with zero events, apply a continuity correction. This example uses the metabin function with incr = 0.5 and method.incr = "only0".

```r
m <- metabin(event.e, n.e, event.c, n.c, study, data = df,
             incr = 0.5, method.incr = "only0")
```

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

### Configure Meta-Analysis Parameters

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Control analysis options such as common/random effects models, τ² estimation methods, prediction intervals, and subgroup analysis.

```r
metagen(..., 
  common = TRUE,              # Conduct common effect meta-analysis
  random = TRUE,              # Conduct random effects meta-analysis
  method.tau = "DL",          # τ² estimation method
  prediction = FALSE,         # Include prediction interval
  subgroup = group_variable   # Subgroup analysis
)
```

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

### Handle Negative Tau-Squared Values

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Negative tau-squared (τ²) values can occur; they are often automatically set to 0 or can be addressed by trying a different estimator. This example uses method.tau = "SJ".

```r
m <- metagen(TE, seTE, method.tau = "SJ")
```

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

### Incidence Rate Difference Meta-Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metainc.md

Calculates the pooled incidence rate difference (IRD). This example demonstrates setting a scaling factor (irscale) and specifying the time unit (irunit) for the analysis. Use 'print(m2)' to view the results.

```r
m2 <- metainc(event.e, time.e, event.c, time.c, study,
              data = studies, sm = "IRD", irscale = 1000,
              irunit = "person-years")
print(m2)
```

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

### Enabling Debug Mode for Heterogeneity Estimation in R

Source: https://github.com/cran/meta/blob/master/_autodocs/errors.md

Activate detailed output for troubleshooting heterogeneity estimation by setting `detail.tau = TRUE` in meta-analysis functions. This provides step-by-step information on the calculation process, aiding in debugging complex models.

```r
# Enable detailed output for troubleshooting
m <- metagen(TE, seTE, detail.tau = TRUE)
print(m)  # Shows detailed heterogeneity estimation steps
```

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

### Configure Confidence Interval Parameters

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Set confidence interval levels for studies, meta-analyses, and prediction intervals, and specify methods for calculating these intervals.

```r
metagen(...,
  level = 0.95,               # CI level for studies
  level.ma = 0.95,            # CI level for meta-analysis
  level.predict = 0.95,       # CI level for prediction interval
  method.common.ci = "z",     # Common effect CI method
  method.random.ci = "t"      # Random effects CI method
)
```

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

### Simple Proportion Meta-Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metaprop.md

Performs a basic meta-analysis of proportions using the PLOGIT summary measure and Inverse pooling method. Requires study data with events and total observations.

```r
studies <- data.frame(
  study = c("Study A", "Study B", "Study C"),
  events = c(45, 52, 38),
  n = c(100, 110, 95)
)

m1 <- metaprop(events, n, study, data = studies,
               sm = "PLOGIT", method = "Inverse")
print(m1)
forest(m1)
```

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

### Trim-and-fill analysis using the rank-based method

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/trimfill.md

Performs a trim-and-fill analysis using the rank-based method. This alternative method can be used when the linear assumption of the standard trim-and-fill method is not met.

```r
tf3 <- trimfill(m1, type = "R")
print(tf3)
```

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

### Cumulative meta-analysis with continuous data

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metacum.md

Performs a cumulative meta-analysis for continuous data. Requires a `metacont` object as input. The results can be visualized using the `forest` function.

```r
data(Fleiss1993cont)
m3 <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
               data = Fleiss1993cont, sm = "SMD")

cum3 <- metacum(m3)
forest(cum3)
```

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

### Basic Meta-Regression with One Covariate

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metareg.md

Performs a basic meta-regression using a single covariate ('age'). Requires a meta-analysis object and a formula specifying the covariate. The results are printed to show the regression coefficients and model fit.

```r
data(Fleiss1993cont)
Fleiss1993cont$age <- c(55, 65, 55, 65, 55)
Fleiss1993cont$region <- c("Europe", "Europe", "Asia", "Asia", "Europe")

ma1 <- metacont(n.psyc, mean.psyc, sd.psyc, n.cont, mean.cont, sd.cont,
                data = Fleiss1993cont, sm = "SMD")

# Meta-regression on age
reg1 <- metareg(ma1, ~age)
print(reg1)
```

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

### Simple Means Meta-Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metamean.md

Performs a basic meta-analysis of means using provided study data. Requires study labels, sample sizes, means, and standard deviations.

```r
studies <- data.frame(
  study = c("Study A", "Study B", "Study C"),
  n = c(100, 120, 110),
  mean = c(10.5, 11.2, 10.8),
  sd = c(2.1, 2.3, 1.9)
)

m1 <- metamean(n, mean, sd, study, data = studies)
print(m1)
forest(m1)
```

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

### Trim-and-fill analysis with metabin object

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/trimfill.md

Performs a trim-and-fill analysis on a metabin object. This is the standard usage for adjusting meta-analysis results for publication bias.

```r
data(Fleiss1993bin)
m1 <- metabin(event.e, n.e, event.c, n.c, study,
              data = Fleiss1993bin, sm = "RR")

tf1 <- trimfill(m1)
print(tf1)
```

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

### Generate L'Abbé Plot from metabin Object

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/labbe.md

Creates a basic L'Abbé plot using a pre-existing 'metabin' object. Ensure the 'metabin' object is correctly computed before plotting.

```r
data(Fleiss1993bin)
m1 <- metabin(event.e, n.e, event.c, n.c, study,
              data = Fleiss1993bin, sm = "RR")
labbe(m1)
```

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

### Leave-One-Out and Cumulative Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/README.md

Shows how to perform leave-one-out influence analysis and cumulative meta-analysis, followed by visualizing the results using forest plots.

```r
# Assess study influence
inf <- metainf(m)
forest(inf)

# Cumulative analysis
cum <- metacum(m)
forest(cum)
```

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

### Printing and summarizing cumulative meta-analysis results

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metacum.md

Demonstrates how to print and summarize the results of a cumulative meta-analysis object. These functions provide a textual overview of the cumulative estimates and statistics.

```r
print(cum1)
summary(cum1)
```

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

### Handling Missing Standard Deviations

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metacont.md

Performs a meta-analysis for mean differences using approximated standard deviations from range for studies with missing SD values. Uses the Wan method for approximation. Displays the results.

```r
# Using data with missing SDs approximated from range
m3 <- metacont(n.e = c(20, 25), mean.e = c(10, 12),
               sd.e = c(2, NA), min.e = c(NA, 8), max.e = c(NA, 16),
               n.c = c(20, 25), mean.c = c(9, 11),
               sd.c = c(2.5, NA), min.c = c(NA, 7), max.c = c(NA, 15),
               studlab = c("Study 1", "Study 2"),
               sm = "MD", method.sd = "Wan")
print(m3)
```

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

### Cumulative meta-analysis sorted by publication year (binary data)

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metacum.md

Performs a cumulative meta-analysis sorted by a specified variable, such as publication year. This allows for observing how the pooled estimate changes over time. Requires a `metabin` object and a `sortvar`.

```r
Fleiss1993bin$year <- c(1989, 1992, 1985, 1990, 1994)
m2 <- metabin(event.e, n.e, event.c, n.c, study,
              data = Fleiss1993bin, sm = "RR")

cum2 <- metacum(m2, sortvar = year)
forest(cum2)
```

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

### Meta-Analysis Function Parameters

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metabin.md

This section details the parameters available for the meta-analysis function, covering data input, pooling methods, heterogeneity measures, subgroup analysis, and output formatting.

```APIDOC
## Meta-Analysis Function

### Description
This function performs meta-analysis calculations, allowing for various customization options.

### Parameters
#### Input Data Parameters
- **event.e** (numeric) - Number of events in experimental group or pairwise object
- **n.e** (numeric) - Number of observations in experimental group
- **event.c** (numeric) - Number of events in control group
- **n.c** (numeric) - Number of observations in control group
- **studlab** (character) - Optional vector with study labels
- **data** (data.frame) - Optional data frame containing the study information
- **subset** (logical/numeric) - Optional vector specifying subset of studies
- **exclude** (logical/numeric) - Optional vector specifying studies to exclude

#### Model and Method Parameters
- **cluster** (numeric) - Optional vector specifying cluster for three-level model
- **rho** (numeric) - Assumed correlation of estimates within cluster
- **weights** (numeric) - User-specified weights for studies
- **weights.common** (numeric) - User-specified weights for common effect model
- **weights.random** (numeric) - User-specified weights for random effects model
- **method** (character) - Pooling method: "Inverse", "MH", "Peto", "GLMM", "LRP", "SSW"
- **sm** (character) - Summary measure: "RR", "OR", "RD", "ASD", "DOR", "VE"
- **incr** (numeric) - Continuity correction for zero cell counts
- **method.incr** (character) - Continuity correction method: "only0", "if0all", "all", "user"
- **allstudies** (logical) - Include studies with zero/all events in both groups
- **incr.e** (numeric) - Continuity correction in experimental group
- **incr.c** (numeric) - Continuity correction in control group
- **MH.exact** (logical) - Use exact Mantel-Haenszel without continuity correction
- **RR.Cochrane** (logical) - Use 2*incr for risk ratio with zero cells (RevMan 5)
- **Q.Cochrane** (logical) - Use Mantel-Haenszel estimate in Q statistic (RevMan 5)
- **model.glmm** (character) - GLMM model: "UM.FS", "UM.RS", "CM.EL", "CM.AL"

#### Heterogeneity and Confidence Interval Parameters
- **level** (numeric) - Confidence level for individual studies
- **level.ma** (numeric) - Confidence level for meta-analysis estimates
- **common** (logical) - Conduct common effect meta-analysis
- **random** (logical) - Conduct random effects meta-analysis
- **overall** (logical) - Report overall summaries
- **overall.hetstat** (logical) - Print heterogeneity measures for overall comparisons
- **prediction** (logical) - Print prediction interval
- **method.tau** (character) - Method to estimate between-study variance
- **method.tau.ci** (character) - Method for confidence interval of τ²
- **level.hetstat** (numeric) - Confidence level for heterogeneity statistics
- **tau.preset** (numeric) - Prespecified value for √(τ²)
- **tau.common** (logical) - Same τ² across subgroups
- **detail.tau** (logical) - Detail on between-study variance estimate
- **method.I2** (character) - Method to estimate I²
- **level.predict** (numeric) - Confidence level for prediction interval
- **method.predict** (character) - Method to calculate prediction interval
- **adhoc.hakn.ci** (character) - Ad hoc variance correction for Hartung-Knapp CI
- **adhoc.hakn.pi** (character) - Ad hoc variance correction for prediction interval
- **seed.predict** (numeric) - Seed for bootstrap prediction interval

#### Output and Reporting Parameters
- **method.bias** (character) - Test for funnel plot asymmetry
- **backtransf** (logical) - Back-transform results in printouts and plots
- **pscale** (numeric) - Scaling factor for risk differences
- **title** (character) - Title of meta-analysis
- **complab** (character) - Comparison label
- **outclab** (character) - Outcome label
- **label.e** (character) - Label for experimental group
- **label.c** (character) - Label for control group
- **subgroup** (factor) - Vector for meta-analysis with subgroups
- **subgroup.name** (character) - Name for subgroup variable
- **print.subgroup.name** (logical) - Print subgroup variable name
- **sep.subgroup** (character) - Separator between name and level
- **test.subgroup** (logical) - Print test for subgroup differences
- **prediction.subgroup** (logical) - Print prediction intervals for subgroups
- **keepdata** (logical) - Keep original data in meta object
- **warn** (logical) - Print warnings
- **warn.deprecated** (logical) - Print warnings about deprecated arguments

### Return Value
Object of class `meta` containing:
- Pooled estimates for risk ratio, odds ratio, or other selected summary measure
- Confidence intervals for pooled estimates
- Test statistics and p-values
- Study weights for common and random effects models
- Heterogeneity statistics (Q, I², τ²)
- Subgroup analyses if requested
- Prediction intervals if requested
```

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

### Basic Binary Meta-Analysis with RR

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metabin.md

Performs a meta-analysis of binary outcomes using the Inverse Variance method to calculate the Risk Ratio (RR). Requires individual study event counts and sample sizes.

```R
data(Fleiss1993bin)
m1 <- metabin(event.e = Fleiss1993bin$event.e,
              n.e = Fleiss1993bin$n.e,
              event.c = Fleiss1993bin$event.c,
              n.c = Fleiss1993bin$n.c,
              studlab = Fleiss1993bin$study,
              sm = "RR", method = "Inverse")
print(m1)
forest(m1)
```

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

### Extend Meta-Analysis with Regression and Subgroup Analysis

Source: https://github.com/cran/meta/blob/master/_autodocs/quick-reference.md

Perform meta-regression to explore the impact of covariates, conduct cumulative meta-analysis, and perform leave-one-out analysis.

```r
# Meta-regression
reg <- metareg(m, ~covariate)
bubble(reg)

# Cumulative meta-analysis
cum <- metacum(m)
forest(cum)

# Leave-one-out analysis
inf <- metainf(m)
forest(inf)
```

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

### Meta-Analysis with GLMM Method

Source: https://github.com/cran/meta/blob/master/_autodocs/api-reference/metainc.md

Performs a meta-analysis using the Generalized Linear Mixed Model (GLMM) method for pooling. This approach can be suitable for complex data structures. Use 'print(m3)' to see the computed results.

```r
m3 <- metainc(event.e, time.e, event.c, time.c, study,
              data = studies, sm = "IRR", method = "GLMM")
print(m3)
```