Targeted sampling of sharp null hypotheses

Description

Fills in missingness in \vec{y}(z;α_{s}) for z,s=0,1 based on targeted sampling algorithm described in Section 4.2 of Rigdon and Hudgens (2014)

Usage

1
sample.n(eff, y0.a0, y1.a0, y0.a1, y1.a1, p00, p10, p01, p11, n, m.a0, m.a1)

Arguments

eff

treatment effect of interest; either “DEa0”, “DEa1”, “IE”, “TE”, or “OE”

y0.a0

Observed \vec{y}(0;α_{0}); includes NAs where missing

y1.a0

Observed \vec{y}(1;α_{0}); includes NAs where missing

y0.a1

Observed \vec{y}(0;α_{1}); includes NAs where missing

y1.a1

Observed \vec{y}(1;α_{1}); includes NAs where missing

p00

Missingness in \vec{y}(0;α_{0}) is filled in by sampling from a Bernoulli distribution with mean p_{00}

p10

Missingness in \vec{y}(1;α_{0}) is filled in by sampling from a Bernoulli distribution with mean p_{10}

p01

Missingness in \vec{y}(0;α_{1}) is filled in by sampling from a Bernoulli distribution with mean p_{01}

p11

Missingness in \vec{y}(1;α_{0}) is filled in by sampling from a Bernoulli distribution with mean p_{11}

n

group size vector where element i=1,…,k is equal to the number of subjects in group i

m.a0

α_{0} randomization vector where element i=1,…,k is equal to the number of subjects in group i who would receive treatment if group i was randomized to strategy α_{0}

m.a1

α_{1} randomization vector where element i=1,…,k is equal to the number of subjects in group i who would receive treatment if group i was randomized to strategy α_{1}

Value

y0.a0

value of \vec{y}(0;α_{0}) after missingness has been filled in using targeted sampling

y1.a0

value of \vec{y}(1;α_{0}) after missingness has been filled in using targeted sampling

y0.a1

value of \vec{y}(0;α_{1}) after missingness has been filled in using targeted sampling

y1.a1

value of \vec{y}(1;α_{1}) after missingness has been filled in using targeted sampling

effect

value of treatment effect of interested under sharp null after missingness filled in using targeted sampling

Author(s)

Joseph Rigdon jrigdon@bios.unc.edu

References

Rigdon, J. and Hudgens, M.G. “Exact confidence intervals in the presence of interference.” Submitted to Statistics and Probability Letters 2014.

See Also

exactCI