qpSetupBound: Constructing QCQP problem for bounding
In ivmte: Instrumental Variables: Extrapolation by Marginal Treatment Effects

This function is only used when the direct MTR regression procedure is used. This function simply constructs the quadratic constraint, and adds it to the LP problem defined by the linear optimization problem for the bounds and the linear shape constraints.

qpSetupBound(
  env,
  g0,
  g1,
  criterion.tol,
  criterion.min,
  rescale = FALSE,
  setup = TRUE
)

`env`	environment containing the matrices defining the LP problem.
`g0`	set of expectations for each terms of the MTR for the control group.
`g1`	set of expectations for each terms of the MTR for the control group.
`criterion.tol`	non-negative scalar, determines how much the quadratic constraint should be relaxed by. If set to 0, the constraint is not relaxed at all.
`criterion.min`	minimum of (SSR - SSY) of a linear regression with shape constraints.
`rescale`	boolean, set to `TRUE` if the MTR components should be rescaled to improve stability in the LP/QP/QCP optimization.
`setup`	boolean, set to `TRUE` if the QP problem should be set up for solving the bounds, which includes the quadratic constraint. Set to `FALSE` if the quadratic constraint should be removed.