mvnLinear: Inference for Normal Means after Aggregate Testing with a...
In ammeir2/PSAT: Inference after Selection with Aggregate Testing

Description Usage Arguments Details Value See Also

mvnLinear is used to estimate a normal means model that was selected based on a single linear aggregate test of the form:

a'y > u or a'y < l,

l < u.

mvnLinear(y, sigma, testVec, threshold = NULL, pval_threshold = 0.05,
  contrasts = NULL, test_direction = c("two-sided", "lower", "upper"),
  estimate_type = c("mle", "naive"), pvalue_type = c("hybrid", "polyhedral",
  "naive"), ci_type = c("switch", "polyhedral", "naive"),
  confidence_level = 0.95, verbose = TRUE, control = psatControl())

`y`	the observed normal vector.
`sigma`	the covariance matrix of `y`.
`testVec`	the test testVec a of size `length(y)` used in the aggregate test
`threshold`	the threshold used in the aggregate test, either a vector of size two for the lower and upper thresholds u, l, or a single number.
`pval_threshold`	the signficance level of the aggregate test. Overrided by `threshold` if both are provided.
`contrasts`	an optional matrix of contrasts to be tested: must have number of columns identical to the length of `y`. If left as `NULL`, the coorinates of `y` will be tested by default.
`test_direction`	whether the linear test is one-sided or two-sided. Will be used if the provided threshold is a scalar, if lower then the tests will be a'y < threshold and if upper then the test will be a'y > threshold.
`estimate_type`	see `mvnQuadratic` for details.
`pvalue_type`	see `mvnQuadratic` for details.
`ci_type`	see `mvnQuadratic` for details.
`confidence_level`	the confidence level for constructing confidencei intervals.
`verbose`	whether to report on the progress of the computation.
`control`	an object of type `psatControl`.

The function is used to perform inference for normal mean vectors that were selected based on a single linear aggregate test. To be exact, suppose that y ~ N(μ,Σ) and that we are interested in estimating μ only if we can determine that μ != 0 using an aggregate test of the form: a'y <l or a'y > u for some predetermined constants a, l, u.

The threshold parameter specifies the constants l<u which are used to threshold the aggregate test. If only a single number is provided, then the threshold will be set according to test_direction:

lower: a'y < threshold
upper: a'y > threshold
two-sided a'y < -threshold, or a'y > threshold

The threshold parameter takes precedence over pval_threshold if both are specified.

See mvnQuadratic for details regarding the available inference methods.

An object of class mvnLinear.

mvnQuadratic, psatGLM, getCI, getPval.

ammeir2/PSAT documentation built on May 27, 2019, 7:40 a.m.