フィルターのクリア

how can i generate a moving average time series data using amtalb R 2006 a?

1 回表示 (過去 30 日間)
arkedia
arkedia 2013 年 5 月 15 日
i want to generate moving average time series data , i used a the function armasim
function z = armasim(phi,theta,n)
% ARMASIM(PHI,THETA,N) generates N observations from the
% ARMA model specified by PHI, THETA
% It "burns in" with the 1st 200 observations
[p m] = size(phi);
[q m] = size(theta);
n1 = 200+n;
a = normrnd(0,1,n1+q,1);
z = zeros(p,1);
for i=1:n1
zt = z(i:(i+p-1))'*phi(p:-1:1)+a(i+q)-a(i:(i+q-1))'*theta(q:-1:1);
z = [ z ; zt ];
end
z = z((201+p):(n1+p));
it works good for MA(1) but MA(2)or more , the resulting data is not good!

回答 (1 件)

Image Analyst
Image Analyst 2013 年 5 月 15 日
To do a moving average, use conv():
movingAverage = conv(inputSignal, ones(1, windowSize)/windowSize);

カテゴリ

Help Center および File ExchangeConditional Mean Models についてさらに検索

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by