This paper aims to examine the weak form of efficiency for price series of four precious metals, i.e. gold, silver, platinum and palladium, using a generalized spectral method.,The method has the advantage of detecting both linear and non-linear serial dependence in the conditional mean, and it is robust to various forms of conditional heteroscedasticity. The authors use three different rolling windows for the purpose of robustness.,The authors report weak form of efficiency across metals series for almost all rolling windows. The optimum efficiency for Gold and Palladium is achieved through 250 days rolling window estimates whereas it is 500 days rolling window for silver. Platinum has similar efficiency levels across rolling windows. The degree of efficiency for metal prices is observed to be varying over time with silver market possessing highest levels of efficiency. The efficiency synchronization also varies across rolling windows and metals.,The results reveal that metal markets are efficient for most times implying the low predictability and the low likelihood of earning abnormal returns by speculating in these markets.,The study uses a relatively new statistical technique, the generalized spectral test, to capture linear and non-linear serial dependence. Therefore, the results possess adequate power against departure from market efficiency.

中文翻译：

---

测试金属市场的效率：广义光谱测试的新证据

本文旨在用广义谱方法研究金，银，铂和钯四种贵金属价格序列的弱效率形式。该方法具有检测线性和非线性序列相关性的优点。条件均值，并且对各种形式的条件异方差强健。作者出于鲁棒性的目的使用了三种不同的滚动窗口。作者报告说，几乎所有滚动窗口在整个金属系列中的效率形式都很弱。金和钯的最佳效率是通过250天的滚动窗口估算来实现的，而银是500天的滚动窗口估算。铂金在滚动窗口中的效率水平相似。观察到金属价格的效率程度随时间变化，白银市场具有最高的效率水平。效率同步在滚动窗口和金属上也有所不同。结果表明，金属市场在大多数时间都是有效的，这意味着通过对这些市场进行投机，其可预测性较低，获得异常收益的可能性也较低。该研究使用了一种相对较新的统计技术，通用频谱测试，以捕获线性和非线性序列相关性。因此，结果具有足够的力量来抵抗偏离市场效率。结果表明，金属市场在大多数时候都是有效的，这意味着通过在这些市场进行投机，其可预测性较低，获得异常收益的可能性也很低。该研究使用了一种相对较新的统计技术，即广义频谱检验，来捕获线性和非线性。线性序列相关性。因此，结果具有足够的力量来抵抗偏离市场效率。结果表明，金属市场在大多数时候都是有效的，这意味着通过在这些市场进行投机，其可预测性较低，获得异常收益的可能性也很低。该研究使用了一种相对较新的统计技术，即广义频谱检验，来捕获线性和非线性。线性序列相关性。因此，结果具有足够的力量来抵抗偏离市场效率。