from pylab import * ## Use simulation to check the coverage probabilities of the usual ## confidence interval for a regression coefficient. ## Number of cases n = 20 ## Number of covariates p = 3 ## Construct a design matrix. '''X = rnorm(n*p) X = array(X, c(n,p)) X = X - outer(array(1,n), apply(X,2,mean)) ## Center the columns X = svd(X)$u ## Orthogonalize the columns r = 0.3 ## Introduce a correlation of X[,3] = r*X[,2] + sqrt(1-r^2)*X[,3] ## r between columns 2 and 3. X = cbind(array(1,n), X) ''' X = randn(n,p) X = X - outer(ones(n), X.mean(0)) X,_,_ = svd(X,full_matrices=0) r = 0.3 X[:,2]= r*X[:,1] + sqrt(1-r**2)*X[:,2] X = c_[ones(n), X] ## Some things we'll need below. ''' H = svd(X) H = H$v %*% diag(1/H$d^2) %*% t(H$v) ## equivalent to solve(t(X) %*% X) dc = c(0,-1,1,0) ## Contrast V = dc %*% H %*% dc ''' from collections import namedtuple SVD = namedtuple('SVD', 'u d v') H = svd(X, 0) H = SVD(*H) H2 = dot( dot(H.v, diag(1/H.d**2)), H.v.T) #ugly def mdot(*args): pass return reduce(dot, args) H3 = mdot(H.v, diag(1/H.d**2), H.v.T) # bad dc = c_[0, -1, 1, 0] # dc is 2D array!! ???? V = mdot(dc, H3, dc.T) #check the type of V # ok dc = array([0,-1,1,0]) # dc is now 1D array V = mdot(dc, H3, dc) # ok dc = r_[0,1,1,0] #dc is now 1D array V = mdot(dc, H3, dc) ''' ## Error standard deviation. sigma = 1 ## Number of simulation replications. nrep = 1000 ''' sigma = 1 nrep = 1000 for b in arange(0,1,0.1): # generate the population regression vector beta = zeros(p+1) beta[1] = b # The true value of the contrast. tv = sum(dc * beta) # storage for all the estimates of beta_1 B = empty(nrep) # The mean response EY = dot(X, beta) for k in arange(nrep): Y = EY + sigma * randn(n) # use polyfit or lstsq m = lstsq(X,Y) # m[0] is the coefficients beta_hat = m[0] mse = 1.0/(n-p) *m[1] # m[1] sum of square residual ? rmse = sqrt(mse) pe = sum ( dc * beta_hat) SE = rmse * sqrt(V) from scipy import stats f = stats.t.ppf(0.975, n-p-1) LB = pe - f*SE UB = pe + f*SE B[k]= ((tv > LB) and (tv < UB)) # and versus & print b, mean(B) ''' ## Loop over population values for beta_1. for (b in seq(0, 1, 0.1)) { ## Generate the population regression vector. beta = rep(0, p+1) beta[2] = b ## The true value of the contrast. tv = sum(dc * beta) ## Storage for all the estimates of beta_1. B = array(0, nrep) ## The mean response. EY = X %*% beta ## Simulation replications. for (k in 1:nrep) { ## Generate response data from Y|X. Y = EY + sigma*rnorm(n) ## Fit the model. m = lm(Y ~ 0+X) s = summary(m) beta_hat = m$coeff mse = s$sigma^2 rmse = sqrt(mse) ## The estimated contrast pe = sum(dc * beta_hat) ## The estimated standard error for the contrast. SE = rmse * sqrt(V) ## The multiplier for the 95% CI. f = qt(0.975, n-p-1) ## The lower and upper limit of the CI. LB = pe - f*SE UB = pe + f*SE ## Get the indicator of coverage for this sample. B[k] = 1*((tv > LB) & (tv < UB)) } ## Print the true beta value and coverage probability. print(c(b, mean(B))) } '''