Description Usage Arguments Details Author(s) References
View source: R/rif_decomposite.R
This function decomposite the RIF regression result
1 |
formula |
formula of RIF regression |
data |
data with varibales |
flag |
variable denotes the decompositing group, flag is the column name of the variable |
idx |
value of the grouping variable. idx should be a vector with two dimensions. for example idx = c(1, 2); idx = c(3, 5). |
method |
the distrubiton statistic to calculate recentered influence funciton, which can be choose from "mean", "quantle", "variance","gini". |
tau |
quantile when using quantile method |
kernel |
kernel used for kernel estimating of the dependent variable, selecting from "gaussian", "epanechnikov", "rectangular", "triangular", "biweight", "cosine", "optcosine". Used in quantile method |
Given are two groups, A and B; an outcome variable, Y; and a set of predictors. For example, think of a group of males and a group of females, (log) wages are the outcome variable, and human capital indicators such as education and work experience as predictors. the distribution statistics (ν) difference of outcome is,
R = v(Y_A)-v(Y_B)
where v(Y) denotes the distribution statistics of the outcome variable, such as mean, quantile, variance, gini. Based on the linear model
RIF(Y_l) = X_{l}^{'}β_l+ε_l, l \in (A, B)
where X is a vector containing the predictors and a constant, β contains the slope parameters and the intercept, and ε is the error. The outcome difference can be expressed as:
R = v(Y_A)-v(Y_B) = E(X_A)^{'}β_A-E(X_B)^{'}β_B
R = (E(X_A)-E(X_B))^{'}β^{*}+ (E(X_A)^{'}(β_A-β^{*})+E(X_B)^{'}(β{*}-β_B))
now we have a twofold decomposition.
Wenjing Wang Wenjingwang1990@gmail.com
Firpo S, Fortin N M, Lemieux T(2009). Unconditional quantile regressions. Econometrica, 77(3): 953-973.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.