Add possibility to compute risk

[odow]

We also need an upper bound evaluation (which is not the expectation).

How should one do this? At one point I implemented a bootstrapping method which ran a whole heap of monte-carlo simulations, then sampled a subset of those objective values (with replacement) to calculate a confidence interval for the risk-adjusted objective.

[codecov-io]

Codecov Report

Merging #151 into master will decrease coverage by 0.07%. The diff coverage is 95.65%.

@@            Coverage Diff             @@
##           master     #151      +/-   ##
==========================================
- Coverage   85.09%   85.01%   -0.08%     
==========================================
  Files          16       17       +1     
  Lines         825      854      +29     
==========================================
+ Hits          702      726      +24     
- Misses        123      128       +5

Impacted Files	Coverage Δ
src/SDDPoptimize.jl	90.69% <ø> (-1.78%)	:arrow_down:
src/stopcrit.jl	9.52% <0%> (-0.48%)	:arrow_down:
src/objects.jl	94.91% <100%> (+0.47%)	:arrow_up:
src/forwardBackwardIterations.jl	94.73% <100%> (-0.88%)	:arrow_down:
src/risk.jl	97.43% <97.43%> (ø)
src/sdp.jl	85.82% <0%> (-0.21%)	:arrow_down:

---

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 245986d...a7d43b4. Read the comment docs.