For Questions 1 to 10 pick the option that correctly completes each statement.
1. Proportions are usually used to summarise:
(1) numeric variables.
(2) categorical variables.
2. Media reports that describe two variables as being linked or associated:
(1) can be interpreted as a change in one variable will cause a change in the other
(2) should not be interpreted as a change in one variable will cause a change in
the other variable.
3. When doing a randomisation test, if the tail proportion in the re-randomisation
distribution is large then we may conclude that:
(1) it is implausible that chance was acting alone.
(2) it is plausible that chance was acting alone.
4. Selection bias is when:
(1) the population sampled is not exactly the population of interest.
(2) people decide for themselves whether to be surveyed or not.
5. The process of finding a bootstrap confidence interval is a:
(1) simulation-based method.
(2) Normality-based method.
6. If we repeatedly took random samples from a population and from each sample
constructed a 95% confidence interval for , then, in the long run, we expect 95%
of these confidence intervals would:
(1) include the true unknown value of .
(2) include the sample mean, x.
7. The P-value measures the strength of evidence:
(1) against the null hypothesis.
(2) against the alternative hypothesis.
8. When data are paired we analyse:
(1) the differences.
(2) the two groups of data.
9. For a Chi-square test to be valid we require that at least 80% of the:
(1) expected counts are five or more and each expected count is greater than one.
(2) observed counts are five or more and each observed count is greater than one.
10. The sign (+ or ) of the sample correlation coefficient, r, is:
(1) not necessarily the same as the slope of the least squares regression line.
(2) always the same as the slope of the least squares regression line.
EasyDue™ 支持PayPal, AliPay, WechatPay, Taobao等各种付款方式!
E-mail: email@example.com 微信:easydue