Description Usage Arguments Details Author(s) References See Also Examples
BaB
finds an exact p-value by solving a 0-1 knapsack problem.
The 0-1 knapsack problem is solved by a branch and bound algorithm.
For more details, see Higgins, Rivest, Stark.
1 2 3 4 |
Z |
A |
t |
Value of the observed maximum, either as the MRO, as taint, or as the overstatement of the margin in votes. |
asTaint |
Set |
asNumber |
Set |
M |
A priori margin. If NULL, |
takeOutZeroMMB |
Setting |
give.strategy |
If |
bound.col, calc.e_p, w_p |
Arguments used to compute
|
BaB
pre-processes the data to make the branch and bound algorithm
more efficient, and obtains all information from Z
necessary to perform
the branch and bound algorithm.
BaB
then calls runBaB
, which calls the branch and bound
function.
When give.strategy = TRUE
, the output of the solution will be
a vector strategy
of size length(nrow(Z$strat))
.
The solution can be obtained by, for each stratum i
, putting
e.max
amount of difference in the strategy[i]
batches
corresponding to the largest values of u
.
For more details, see Higgins, Rivest, Stark.
Mike Higgins, Hua Yang
M. Higgins, R. L. Rivest, P. B. Stark. Sharper p-Values for Stratified Election Audits
See LKPBound
for finding a p-value through a continuous relaxation.
See eqValBound
and withReplaceBound
for finding a p-value through other relaxations.
See runBaB
for running the branch and bound algorithm given
a value vector u
, a cost vector q
, a margin M
, and
a CIDnum
vector.
See compute.stark.t
for computing t
through audit data.
1 2 | data(MN_Senate_2006)
BaB(MN_Senate_2006.strat, takeOutZeroMMB = FALSE, give.strategy = TRUE)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.