Checks whether a vector has more than two unique values

Description

Checks whether a vector has more than two unique values

Usage

check_for_two_levels(x)

Arguments

Compute the standardized mean difference

Description

This function is for internal package use only. See smd for usage.

Usage

compute_smd_pairwise(smd_parts)

compute_smd(D, S)

Arguments

Details

Computes:

d = \sqrt{D' S^{-1} D}

where D is a vector of differences between group 1 and 2 and S is the covariance matrix of these differences. If D is length 1, the result is multplied by sign(D).

In the case of a numeric or integer variable, this is equivalent to:

d = \frac{\bar{x}_1 - \bar{x}_2}{\sqrt{(s^2_1 + s^2_2)/2}}

where \bar{x}_g is the sample mean for group g and s^2_g is the sample variance.

For a logical or factor with only two levels, the equation above is \bar{x}_g = \hat{p}_g, i.e. the sample proportion and s^2_g = \hat{p}_g(1 - \hat{p}_g) (NOTE: interally smd uses the var function, which uses n-1 as the denominator. Hence, in small samples, s^2_g will not be precisely \hat{p}_g(1 - \hat{p}_g)).

Value

a single numeric value

References

Yang, D., & Dalton, J. E. (2012, April). A unified approach to measuring the effect size between two groups using SAS®. In SAS Global Forum (Vol. 335, pp. 1-6)

See Also

smd

Compute components of SMD

Description

Computes D and S for use within compute_smd.

Usage

compute_smd_parts(.x, .g, .w, .na, .ref, .unwgt, applyFUN = n_mean_var)

Arguments

Computes SMD variance

Description

Calculates the variance of a standardized mean difference using the method of Hedges and Olkin (1985):

Usage

compute_smd_var(d, smd_parts)

Arguments

Details

\sqrt{\frac{n_1 + n_2}{n_1n_2} + \frac{d^2}{2(n_1 + n_2)}}

Apply a function pairwise along a list

Description

Applies a function f(ref, y) where y is an element of a list and ref is a reference element.

Usage

lapplyFUNpairwise(x, f, ref)

Arguments

Compute n, mean and variance

Description

Available for numeric, integer, and factor objects. character objects are handled by first converting to a factor.

Usage

n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'numeric,missing'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'numeric,numeric'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'numeric,ANY'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'integer,missing'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'integer,numeric'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'integer,ANY'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'logical,missing'
n_mean_var(x, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'logical,numeric'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'logical,ANY'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'factor,missing'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'factor,numeric'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'factor,ANY'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'character,missing'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

## S4 method for signature 'character,numeric'
n_mean_var(x, w = NULL, na.rm = TRUE, unwgt.var = TRUE)

## S4 method for signature 'character,ANY'
n_mean_var(x, w = NULL, na.rm = FALSE, unwgt.var = TRUE)

Arguments

Value

a list containing mean and var

Compute Standardized Mean Difference

Description

Computes the standardized mean differnce (SMD) between two groups.

d = \sqrt{D' S^{-1} D}

where D is a vector of differences between group 1 and 2 and S is the covariance matrix of these differences. If D is length 1, the result is multplied by sign(D).

In the case of a numeric or integer variable, this is equivalent to:

d = \frac{\bar{x}_1 - \bar{x}_2}{\sqrt{(s^2_1 + s^2_2)/2}}

where \bar{x}_g is the sample mean for group g and s^2_g is the sample variance.

For a logical or factor with only two levels, the equation above is \bar{x}_g = \hat{p}_g, i.e. the sample proportion and s^2_g = \hat{p}_g(1 - \hat{p}_g).

When using the SMD to evaluate the effectiveness of weighting in achieving covariate balance, it is important to isolate the change in SMD before and after weighting to the change in mean difference, so the denominator (covariance matrix) must be held constant (Stuart 2008, doi:10.1002/sim.3207). By default, the unweighted covariance matrix is used to compute SMD in both the unweighted and weighted case. If the weights are not being used to adjust for covariate imbalance (e.g. case weights), the unwgt.var argument can be set to FALSE to use the weighted covariance matrix as the denominator.

Usage

smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'character,ANY,missing'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'character,ANY,numeric'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'logical,ANY,missing'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'logical,ANY,numeric'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'matrix,ANY,missing'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'matrix,ANY,numeric'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'list,ANY,missing'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'list,ANY,numeric'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'data.frame,ANY,missing'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

## S4 method for signature 'data.frame,ANY,numeric'
smd(x, g, w, std.error = FALSE, na.rm = FALSE, gref = 1L, unwgt.var = TRUE)

Arguments

Value

a data.frame containing standardized mean differences between levels of g for values of x. The data.frame contains the columns:

• term: the level being comparing to the reference level

• estimate: SMD estimates

• std.error: (if std.error = TRUE) SMD standard error estimates

Examples

x <- rnorm(100)
g <- rep(1:2, each = 50)
smd(x, g)

Helper to clean up smd output

Description

Helper to clean up smd output

Usage

tidy_smd_singlevar(smd_res)

tidy_smd_multiplevar(smd_res)

Arguments

Value

a data.frame

Variance computations

Description

Variance computations

Usage

multinom_var(p)

Arguments

Value

a covariance matrix