测量、方法、统计与历史
GRE Subject Test · GRE 心理学 知识点 6 3:07 英语旁白 · 英中内嵌字幕
章节
文本转录
Define a construct, state its observable measure, then ask whether the measure supports the intended interpretation.
定义一个构念，陈述其可观测的测量指标，然后询问该测量是否支持预期的解释。
Random sampling concerns who enters a study; random assignment concerns which condition participants receive.
随机抽样关注的是谁进入研究；随机分配关注的是参与者接受哪种条件。
A causal conclusion needs a credible comparison as well as measurement and ethical safeguards.
因果结论既需要可信的比较，也需要测量和伦理保障。
Historical schools differ in the questions and methods they prioritize.
历史学派在优先关注的研究问题和研究方法上有所不同。
See MM.1, MM.2 and HT.1 before using statistical or historical labels as explanations.
在使用统计或历史标签作为解释之前，请参阅MM.1、MM.2和HT.1。
Reliability concerns consistency; validity concerns evidence supporting a particular interpretation or use.
信度关注一致性；效度关注支持特定解释或使用的证据。
Operational definitions specify how a construct is measured.
操作定义规定了如何测量一个构念。
A questionnaire label does not establish construct validity.
问卷标签并不能确立构念效度。
Random assignment improves comparisons; random sampling supports population generalisation.
随机分配有助于比较，随机抽样支持总体推广。
Ethics constrains both design and interpretation.
伦理学对设计和解释均有限制。
A p-value is a probability of data at least as incompatible under the null model, not the probability that the null is true.
p值是在零模型下数据至少同样不兼容的概率，而非零假设为真的概率。
History questions distinguish explanatory schools and their methods.
历史类题目旨在区分不同的解释学派及其研究方法。
Volunteers are randomly assigned to two memory tasks.
志愿者被随机分配到两个记忆任务中。
Does this make the sample representative of all adults?
这是否使样本能代表所有成年人？
No.
不能。
Assignment improves comparability of conditions within the recruited sample; it does not undo volunteer selection.
分配提高了招募样本内部各组条件的可比性，但无法消除志愿者选择带来的偏差。
Generalization requires attention to recruitment, eligibility and population differences.
推广结论时需关注招募方式、入选资格及人群差异。
Describe random sampling and assignment separately.
请分别描述随机抽样与随机分配。
Tight grouping is like reliability, being on target like validity: a test can be reliable but not valid.
弹着点集中好比信度，命中靶心好比效度：测验可以可靠却不有效。
Read the labels before drawing a conclusion.
先读清标签，再下结论。
A report finds p=.03 and concludes that its theory has a 97% probability of being true and a large effect.
一份报告发现p值为0.03，并据此得出其理论有97%的概率为真且效应量大的结论。
Correct both inferences.
请纠正这两个推论。
Pause before the model.
请在模型出现前暂停。
Under the specified null model and assumptions, the probability of results at least as extreme as the observed result is .03.
在指定的零模型和假设下，观测结果至少同样极端的概率为0.03。
It is not a posterior probability for the theory.
这不是该理论的后验概率。
Effect size and uncertainty must be reported separately; even a small effect can have a small p-value in a large sample.
效应量和不确定性必须分别报告。 即使效应量很小，在大样本中也可能得到很小的p值。
Design bias is not removed by significance.
设计偏差无法通过显著性检验来消除。
Statistical significance alone does not tell you effect size, practical value or absence of design bias.
仅凭统计显著性无法说明效应量、实际价值或设计偏差的缺失。
State the source and the limits.
请注明数据来源及其局限性。
Random sampling is used but allocation is not random.
随机抽样被采用，但分配并非随机。
Which inference is strengthened and which causal problem remains?
哪种推断得到了加强？ 哪种因果问题仍然存在？
Pause and write a justified answer.
请先暂停，写出有依据的答案。