研究方法：防止错误的保障（三）——读《心理学改变思维》（二十）

第二类方法是“自我报告法和调查法”：

Psychologists frequently use self-report measures, often called questionnaires, to assess a variety of characteristics, such as personality traits, mental illnesses, and interests.

Closely related to self-report measures are surveys, which psychologists typically use to measure people’s opinions and attitudes.

所以：

- 性格测试，就是自我报告法，通过问卷

- 类似地就是通过市场调研的方式

- 两者的差别是谁主动，调研是商家之类的主动发起

这里的核心点在于，执行的方法，要采用黄金法则，随机试验，及其变种。

那么，有了测量，下一个问题就是：

When evaluating the results from any dependent variable or measure, we need to ask two crucial questions: Is our measure reliable? Is it valid?

结果是否可靠？是否有效？而这对应着两个不同的维度：

Reliability refers to consistency of measurement (Haynes, Smith, & Hunsley, 2011; Sijtsma & van der Ark, 2015).

For example, a reliable questionnaire should yield similar scores over time. This type of reliability is called test–retest reliability.

Interrater reliability is the extent to which different people who conduct an interview, or make behavioral observations, agree on the characteristics they’re measuring.

所以，可靠是对“测量”，这个过程质量的一致性的衡量：

- 重测信度，就是同样的问卷，再次测试，得到一致的结果，而

- 评分者信度，是不同的人，得到一致的结果

对应地，就是测量结果本身，与被测量对象之间的一致性，称之为“效度”：

Validity, in contrast, is the extent to which a measure assesses what it purports (claims) to measure (Borsboom, 2005; Haynes et al., 2011).

举例来说，一把稳定的、不准的尺子，是有信度的，但是没有效度 —— 所以有效度一定要有信度，但是反之未必。

另外，需要注意的是，不同的问卷表述方式，很可能具有不同的引导效果，导向不同的答案：

When interpreting the results of self-report measures and surveys, we should bear in mind that we can obtain quite different answers depending on how we phrase the questions (Schwarz, 1999; Smith, Schwarz, & Roberts, 2006).

更可怕的是，很可能被问到的人，都不知道自己在回答什么（就是说心里没任何一点B数）：

In a survey conducted in late 2015, 30 percent of U.S Republicans and 19 percent of U.S. Democrats said that they supported bombing Agrabah (Berenson, 2015). There’s only one problem: Agrabah doesn’t exist. It’s the fictional country in Disney’s film Aladdin.

连虚构的阿拉丁电影中的都可以 —— 美国人民棒棒的。