r - solve.QP - Constraints are Inconsistent -

i attempting use solve.qp solve quadratic program there 3 constraints:

• all sum 1 (this works fine)
• all must greater 0 (this works fine well)
• all must less .30 (this not working)

first, test data:

n <- 6 r <- array(rnorm(n^2, mean=1), c(100,n)) # 'returns' colnames(r) <- c("a", "b", "c", "d", "e", "f") 

my function:

eff.frontier <- function (returns, short="no", max.allocation=null, risk.premium.up=.5, risk.increment=.005){        covariance <- cov(returns)   n <- ncol(covariance)   amat <- matrix (1, nrow=n)   bvec <- 1   meq <- 1   if(short=="no"){     amat <- cbind(1, diag(n))     bvec <- c(bvec, rep(0, n))   }   if(!is.null(max.allocation)){     if(max.allocation > 1 | max.allocation <0){       stop("max.allocation must greater 0 , less 1")     }     amat <- cbind(amat, -1*diag(n))     # seems issue area....     bvec <- c(bvec, rep(-max.allocation, n))     print(bvec)   }   loops <- risk.premium.up / risk.increment + 1   loop <- 1   #initialize matrix contain allocation , statistics   eff <- matrix(nrow=loops, ncol=n+3)   # need give matrix column names   colnames(eff) <- c(colnames(returns), "std.dev", "exp.return", "sharpe")   # loop through quadratic program solver   (i in seq(from=0, to=risk.premium.up, by=risk.increment)){     dvec <- colmeans(returns) *     sol <- solve.qp(covariance, dvec=dvec, amat=amat, bvec=bvec, meq=meq)     eff[loop,"std.dev"] <- sqrt(sum(sol$solution *colsums((covariance * sol$solution))))     eff[loop,"exp.return"] <- as.numeric(sol$solution %*% colmeans(returns))     eff[loop,"sharpe"] <- eff[loop,"exp.return"] / eff[loop,"std.dev"]     eff[loop,1:n] <- sol$solution     loop <- loop+1   }   return(as.data.frame(eff)) } 

when don't try set allocation maximum, works fine. no matter try set max.allocation, fails.

am setting amat or bvec incorrectly?

here error:

> eff <- eff.frontier(returns=r, short="yes", risk.premium.up=.5, risk.increment=.001, max.allocation=.15)      error in solve.qp(covariance, dvec = dvec, amat = amat, bvec = bvec, meq = meq) :    constraints inconsistent, no solution! 

here amat:

   [,1] [,2] [,3] [,4] [,5] [,6] [,7] [1,]    1   -1    0    0    0    0    0 [2,]    1    0   -1    0    0    0    0 [3,]    1    0    0   -1    0    0    0 [4,]    1    0    0    0   -1    0    0 [5,]    1    0    0    0    0   -1    0 [6,]    1    0    0    0    0    0   -1 

and here bvec:

[1]  1.00 -0.15 -0.15 -0.15 -0.15 -0.15 -0.15 

how these inconsistent??

thank you,

andrew