Effects of data noise on statistical judgement
Effects of data noise on statistical judgement
复制标题
数据噪声对统计判断的影响
DOI：
10.1080/135467897394383
复制
发表时间：
1997
影响因子：
2.6
通讯作者：
Nigel West
中科院分区：
文献类型：
--
作者：
Nigel West
人们根据图形呈现的时间序列做出预测。系列是由零或正线性趋势以及零、低、中或高噪声水平覆盖的正弦曲线。预测性能受到这两个变量的影响。然而，它与识别趋势的能力无关，并且仅当序列无噪声时才与检测正弦模式的能力显着相关。第二个实验表明，数据噪声的影响不受人们对一系列数据做出的预测数量的影响。这些发现与以下观点一致：数据噪声不会影响预测的方式，但会因两个原因而损害预测。首先，它降低了其背后的锚定和调整启发式的效率。其次，它会导致人们在试图使自己的判断能够代表数据时添加更多的噪音。
People made forecasts from graphically presented time series. Series were sinusoids overlaid by a zero or positive linear trend and a zero, low, moderate, or high level of noise. Forecasting performance was affected by both these variables. However, it did not correlate with ability to identify the trend and correlated significantly with ability to detect the sinusoidal pattern only when series were noise-free. A second experiment showed that the effect of data noise was not influenced by the number of forecasts that people made from a series. These findings are consistent with the view that data noise does not affect the way that forecasts are made but that it impairs them for two reasons. First, it renders the anchor-and-adjust heuristics underlying them less effective. Second, it causes people to add more noise to their judgements in their attempts to make them representative of the data.