问一下matlab里ARIMA模型咋预测

n1这个是数据
dylog_h_adf = adftest(n1)
dylog_h_kpss = kpsstest(n1)%稳定性判断
%结果是1 1 不稳定
data=diff(data)
dylog_h_adf = adftest(data)
dylog_h_kpss = kpsstest(data)
%结果是1 0 稳定
LOGL = zeros(7,7); %Initialize
PQ = zeros(7,7);
for p = 1:7
for q = 1:7
mod = arima(p,0,q);
[fit,~,logL] = estimate(mod,data,‘print’,false);
LOGL(p,q) = logL;
PQ(p,q) = p+q;
end
end
LOGL = reshape(LOGL,49,1);
PQ = reshape(PQ,49,1);
[aic,bic] = aicbic(LOGL,PQ+1,100);
reshape(bic,7,7)
reshape(aic,7,7)
上边是确定阶数 假如我确定阶数是p=4 q=4 然后咋用这个模型来预测未来的数据呢？