# cov.lambda4: Compute Covariance Maximized Lambda4 In JackStat/Lambda4: Collection of Internal Consistency Reliability Coefficients.

## Description

This code estimates maximized lambda4, a split-half reliability estimate. The function splits the halves by specifying a two column list of paired inter-item covariances in descending order. It then calculates Guttman's lambda4 on every possible split-half while preserving the inter-item pairings. The function then returns a list of the Lambda4s and then takes the minimum, maximum, median, and mean of the list. This calculation is most appropiately applied to tests with multiple factors.

## Usage

 ```1 2 3``` ``` cov.lambda4(x, method = "Hunt", missing = "complete", show.lambda4s = FALSE, show.splits = FALSE, standardize = FALSE) ```

## Arguments

 `x` Can be either a data matrix or a covariance matrix. `method` Can specify either "Hunt" or "Osburn". `missing` How to handle missing values. `show.lambda4s` If TRUE then the estimates for each split are included in the output. `show.splits` If TRUE then a binary matrix is exported that describes the ways the items were split. `standardize` When TRUE results are standardized by using the correlation matrix instead of the covariance matrix for computation.

## Value

 `estimates` The mean, median, max, and min of the split-half reliabilities. `lambda4s` A vector of maximized split-half reliabilities. `method` The method chosen. Either "Hunt" or "Osburn". `Analysis.Details` Returns the number of variables and the number of split-half reliabilities. `Splits` The binary indicators of the splits for the min, max, and median split-half reliability. `show.splits` Logical argument selected to show the splits. `show.lambdas4s` Logical argument selected to show the split-half reliabilities.

## Author(s)

Tyler Hunt [email protected]

## Examples

 ```1 2``` ```cov.lambda4(Rosenberg, method="Hunt") cov.lambda4(Rosenberg, method="Osburn") ```

JackStat/Lambda4 documentation built on May 7, 2019, 10:16 a.m.