matlab很小的数,matlab中aicbic确定阶数的太小

想用aicbic确定ARMA的阶数，但用这个确定的阶数时会出现如下错误

Error using arima/validateModel (line 1314)

The non-seasonal moving average polynomial is non-invertible.

Error in arima/setLagOp (line 391)

Mdl = validateModel(Mdl);

Error in arima/estimate (line 1183)

Mdl = setLagOp(Mdl, 'MA' , LagOp([1  coefficients(iMA)' ], 'Lags', [0 LagsMA ]));

解决方法：

论坛有人说把p，q的阶数设置小点，我有300个数据呢，最后阶数只能设置为pMax=5; qMax=2; pMax设置为6都出错，如果这样的话，就感觉太小了，而且和eviews自相关函数和偏自相关函数的结果相差好大，能有人帮看下原因吗，谢谢

代码如下：

LogL = zeros(pMax,qMax);%pMax,qMax来自于自相关、偏自相关序列图显著阶数最(较)大值

SumPQ = LogL;

for p = 1:pMax

for q = 1:qMax

Mdl = arima(p,0,q);

[fit,~,LogL(p,q)] = estimate(Mdl,X,'print',false);%X是待检验序列

SumPQ(p,q) = p+q;

end

end

logL = reshape(LogL,pMax*qMax,1);

numParams = reshape(SumPQ,pMax*qMax,1) + 1;

[~,bic] = aicbic(logL,numParams,500);

BIC = reshape(bic,pMax,qMax);

minBIC = min(bic)

[BICbestP,BICbestQ] = find(BIC == minBIC)

Mdl = arima(BICbestP,0,BICbestQ);

%[fit,~,~] = estimate(Mdl,lnR,'print',false)