SurrogateRegression (version 0.5.0)

Test.BNR: Test Bivariate Normal Regression Model.

Description

Performs a test of the null hypothesis that a subset of the regression parameters for the target outcome are zero in the bivariate normal regression model.

Usage

Test.BNR(t, s, X, Z = NULL, is_zero, test = "Wald", ...)

Value

A numeric vector containing the test statistic, the degrees of freedom, and a p-value.

Arguments

t

Target outcome vector.

s

Surrogate outcome vector.

X

Target model matrix.

Z

Surrogate model matrix.

is_zero

Logical vector, with as many entires as columns in the target model matrix, indicating which columns have coefficient zero under the null.

test

Either Score or Wald. Only Wald is available for LS.

...

Additional arguments accepted if fitting via EM. See Fit.BNEM.

Examples

# Generate data.
set.seed(100)
n <- 1e3
X <- cbind(1, rnorm(n))
Z <- cbind(1, rnorm(n))
data <- rBNR(X = X, Z = Z, b = c(1, 0), a = c(-1, 0), t_miss = 0.1, s_miss = 0.1)

# Test 1st coefficient.
wald_test1 <- Test.BNR(
  t = data[, 1], 
  s = data[, 2], 
  X = X, 
  Z = Z,
  is_zero = c(TRUE, FALSE),
  test = "Wald"
)

score_test1 <- Test.BNR(
  t = data[, 1], 
  s = data[, 2], 
  X = X, 
  Z = Z,
  is_zero = c(TRUE, FALSE),
  test = "Score"
)

# Test 2nd coefficient.
wald_test2 <- Test.BNR(
  t = data[, 1], 
  s = data[, 2], 
  X = X, 
  Z = Z,
  is_zero = c(FALSE, TRUE),
  test = "Wald"
)

score_test2 <- Test.BNR(
  t = data[, 1], 
  s = data[, 2], 
  X = X, 
  Z = Z,
  is_zero = c(FALSE, TRUE),
  test = "Score"
)