How can I plot wald test statistics to show that they converge to the chi-squared distribution?

I am using the following code --

clear

rng(12345)

%Setting up the model

n = 200;

%The model has 4 variables X1, X2, X3, X4

X1=rand(n,1); X2=rand(n,1); X3=rand(n,1); X4=rand(n,1);

X=[X1,X2,X3,X4];

beta1=-0.6; beta2=-0.5; beta3=0.1; beta4=0.05;

beta = [beta1,beta2,beta3,beta4];

A=100;

R = [0 0 1 0];

q = [0.1]; %restriction function contains hypothesis

for r=1:A

sigma = 1; epsilon = randn(n,1)*sigma;

y = beta1*X1+beta2*X2+beta3*X3+beta4*X4+epsilon; %model

b_est = X\y;

e = y - X*b_est;

sigma_est = (e'*e)/n; V=sigma_est*inv(X'*X);

M=[b_est(3,1)-0.1];

W(r) = M'*inv(R*V*R')*M

end

X=0:50;

subplot(1,2,1), plot(X,chi2pdf(X,1)), xlim([3 50]), title('Chi-squared distribution')

subplot(1,2,2), plot(W), xlim([3 50]), ylim([0 5]), title('Wald statistics')

Am I doing any mistake in the code which is why maybe it is not converging to chi-squared distribution? Any help would be appreciated. Thank you.