mariposa (version 0.7.3)

w_mean: Calculate Population-Representative Averages

Description

w_mean() calculates averages that accurately represent your population by using survey weights. This ensures that groups who were over- or under-sampled contribute appropriately to the final average.

Usage

w_mean(data, ..., weights = NULL, na.rm = TRUE)

Value

Population-weighted average(s) with sample size information

Arguments

data

Your survey data (a data frame or tibble)

...

The numeric variables you want to average. You can list multiple variables or use helpers like starts_with("income")

weights

Survey weights to make the average representative of your population. Without weights, you get the simple sample average.

na.rm

Remove missing values before calculating? (Default: TRUE)

Details

When to Use This

Use w_mean() when your survey uses sampling weights and you need population-representative averages. Weights correct for:

• Oversampling of certain groups (weights < 1)

• Undersampling of other groups (weights > 1)

• Non-response patterns

• Complex survey designs

Understanding the Results

• Weighted Mean: The population-representative average

• Effective N: How many independent observations your weighted data represents

• N: Actual number of observations used

Formula

\(\bar{x}_w = \frac{\sum w_i \cdot x_i}{\sum w_i}\)

The effective sample size is: \(n_{eff} = (\sum w_i)^2 / \sum w_i^2\)

References

IBM Corp. (2023). IBM SPSS Statistics 29 Algorithms. IBM Corporation.

See Also

weighted.mean for the base R weighted mean function.

w_sd for weighted standard deviation.

w_median for weighted median.

describe for comprehensive descriptive statistics.

Other weighted_statistics: w_iqr(), w_kurtosis(), w_median(), w_modus(), w_quantile(), w_range(), w_sd(), w_se(), w_skew(), w_var()

Examples

# Load required packages and data
library(dplyr)
data(survey_data)

# Basic weighted usage
survey_data %>% w_mean(age, weights = sampling_weight)

# Multiple variables
survey_data %>% w_mean(age, income, life_satisfaction, weights = sampling_weight)

# Grouped data
survey_data %>% group_by(region) %>% w_mean(age, weights = sampling_weight)

# In summarise context
survey_data %>% summarise(mean_age = w_mean(age, weights = sampling_weight))

# Unweighted (for comparison)
survey_data %>% w_mean(age)