Final answer:
The statement is false because an unreliable test results in inflated apparent variability due to a significant amount of measurement error or noise. This affects the true score variability, making it difficult to discern amidst the inflated variability.
Step-by-step explanation:
The statement, 'If a test was unreliable then the true test score variability would only be a small proportion of the actual test score variability,' is False. In the context of statistics, reliability refers to the consistency of a test or measurement tool. An unreliable test would yield inconsistent results across multiple administrations, meaning that the observed variability in test scores would include not only true variability but also a significant amount of measurement error or noise. Therefore, unreliable tests can actually inflate the apparent variability, making it difficult to discern the true score variability.
As a reference, when we say that 'approximately 90 percent of the confidence intervals calculated from those samples would contain the true value of the population mean,' this implies that we have confidence in the reliability of our estimation method. It suggests that if the method were unreliable, the actual proportion of confidence intervals containing the true population mean would be significantly less.