Description Usage Arguments Details Value References Examples
Computes the asymptotic efficiency of two-sided fixed-length confidence
intervals at c=0, as well as the efficiency of one-sided confidence
intervals that optimize a given beta
quantile of excess length, when
the set \mathcal{C} is characterized by \ell_p constraints.
1 |
eo |
List containing initial estimates with the following components:
|
B |
matrix B with full rank and dimension d_g by d_gamma that determines the set \mathcal{C}, where d_gamma is the number of invalid moments, and d_g is the number of moments |
M |
Bound on the norm of gamma |
p |
Parameter determining which lp norm to use, must equal
|
beta |
Quantile of excess length that a one-sided confidence interval is optimizing. |
alpha |
determines confidence level, |
The set \mathcal{C} takes the form B*gamma where the lp norm of gamma is bounded by M.
A list with two elements, "onesided"
for efficiency of
one-sided CIs and "twosided"
for efficiency of two-sided CIs
Armstrong, T. B., and M. Kolesár (2020): Sensitivity Analysis Using Approximate Moment Condition Models, https://arxiv.org/abs/1808.07387
1 2 3 4 5 6 7 | ## Replicates first line of Table 2 in Armstrong and Kolesár (2020)
## First compute matrix B
I <- vector(mode="logical", length=nrow(blp$G))
I[6] <- TRUE
B <- (blp$ZZ %*% diag(sqrt(blp$n)*abs(blp$perturb)/blp$sdZ))[, I, drop=FALSE]
eo <- list(H=blp$H, G=blp$G, Sig=solve(blp$W), n=blp$n, g_init=blp$g_init)
EffBounds(eo, B, M=1, p=Inf, beta=0.5, alpha=0.05)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.