Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Foundations of statistics wikipedia , lookup
History of statistics wikipedia , lookup
Taylor's law wikipedia , lookup
Bootstrapping (statistics) wikipedia , lookup
Confidence interval wikipedia , lookup
Categorical variable wikipedia , lookup
Resampling (statistics) wikipedia , lookup
Question 1 of 20: What type of variable would the 'level of client satisfaction with customer service' be? A: Discrete variable B: Continuous variable C: Nominal categorical variable D: Ordered categorical variable E: Not sure Question 2 of 20: What is the distance between the third and first quartile of a continuous variable called? A: Semi-interquartile range B: Standard deviation C: Interquartile range D: Mean deviation E: Don't know Question 3 of 20: Box plots are a graphical summary of the distribution of numerical values in a dataset. What are they appropriate for illustrating? A: Relationships between variables B: The structure in the data C: Don't know D: Which records to delete from the dataset E: The degree of skewness present in the dataset Question 4 of 20: What is a summary measure that is computed from only a sample of the population called? A: A discrete variable B: Don't know C: A population D: A statistic E: A parameter Question 5 of 20: A dataset has a roughly symmetric distribution. What would you expect to find within two standard deviations either side of the mean? A: All of the data B: About 95% of the data, only if the variable follows a Normal distribution C: The sample mean 95% of the time D: Outliers E: Don't know Question 6 of 20: What effect does increasing the sample size of a study have in general? A: It just generates more data records B: It worsens the precision of the estimates C: It improves the precision of the estimates D: Don't know E: It reduces the standard deviation Question 7 of 20: What is a standard error? A: A measure of the spread of the values in the data B: A measure of the precision of an estimate C: A measure of the variability of the values in the data D: The standard deviation E: Don't know Question 8 of 20: A survey found that the proportion of respondents who regularly drank fizzy drinks was 0.25. Which is the correct statement about this finding? A: Three out of ten respondents regularly drank fizzy drinks B: One out of four respondents regularly drank fizzy drinks C: Don't know D: One out of three respondents regularly drank fizzy drinks E: One out of five respondents regularly drank fizzy drinks Question 9 of 20: Which of the following statements is a reason why the Normal distribution is important in statistical analysis? A: Many statistical models are based on assuming the data follows a Normal distribution B: It is a useful model for data where the values are often zero C: It is a distribution followed by many naturally occurring variables D: The sample distribution of the mean approaches a Normal distribution as the sample size becomes sufficiently large E: Don't know Question 10 of 20: Which of the following is the correct method for calculating an approximate 95% confidence interval for a population mean? A: Don't know B: Sample mean ± 2 × sample standard deviation C: Sample mean ± 2 × standard error of the population mean D: Population mean ± 2 × standard error of the sample mean E: Sample mean ± 2 × standard error of the sample mean Question 11 of 20: A 95% and a 99% confidence interval for a population mean are obtained from the same dataset. What is the difference between the two intervals? A: None, they are exactly the same B: The 95% confidence interval is narrower than the 99% confidence interval C: The 99% confidence interval is narrower than the 95% confidence interval D: It is impossible to say without accessing the actual data records E: Don't know Question 12 of 20: When testing a null hypothesis, if the test yields a p-value < 0.001, what does this imply? A: That there is a very small probability that the null hypothesis is true B: That the data provides strong evidence against the null hypothesis C: That the alternative hypothesis must be rejected D: That the result is of practical importance because I have found a statistically significant difference E: Don't know Question 13 of 20: Statistically speaking, which of the following would be an appropriate null hypothesis to set? A: The introduction of a smoking ban in public buildings, pubs and restaurants has reduced the number of customers served by the industry B: The introduction of a smoking ban in public buildings, pubs and restaurants has had no effect on the number of customers served by the industry C: Either would be an appropriate null hypothesis D: Neither is appropriate E: Don't know Question 14 of 20: After fitting a straight line regression model to your data, testing that the true value of the slope is zero gives a p-value of 0.0063. What do you decide about the null hypothesis? A: To not reject the null hypothesis because the observed data provides little evidence against it B: To accept the null hypothesis because the observed data provides no evidence against it C: To reject the null hypothesis in favour of the alternative, because the observed data provides strong evidence against the null hypothesis D: To reject the null hypothesis because the observed data provides some evidence against it E: Don't know Question 15 of 20: When comparing three groups of customers in relation to their mean weekly spending, which statistical tool is the most appropriate? A: Analysis of variance B: A series of three separate two-sample t-tests C: Linear regression D: A chi-squared test E: Don't know Question 16 of 20: When comparing two or more groups of customers in relation to the proportion of which own an android smartphone, which statistical tool is the most appropriate? A: Analysis of variance B: A series of three separate two-sample t-tests C: Linear regression D: A chi-squared test E: Don't know Question 17 of 20: Women were asked whether they smoked during their last pregnancy or not. Is the question 'Are babies born lighter for women who smoked during pregnancy?' a question about: A: Estimates B: Relationships C: Comparisons D: None of these E: Not sure Question 18 of 20: When assessing the relationship between two continuous variables, which statistical tool is the most appropriate? A: Analysis of variance B: A two-sample t-test C: Linear regression D: A chi-squared test E: Don't know Question 19 of 20: What is the correct interpretation of a 95% confidence interval? A: The interval has a 95% chance of containing the population mean B: 95% of data records are found inside the interval C: The population mean has only a 5% chance of being outside the interval D: The population mean has a 95% chance of being inside the interval E: Don't know Question 20 of 20: A suitable statistical method for testing the equality of two groups' means suggests that these are 'significantly different'. What can you say about the estimated difference? A: Not much unless we see the estimated difference and its margin of error B: It is large C: It is precisely estimated D: It is of practical importance E: Don't know So, how did you do? Don't worry if you got what you consider to be a low score! This programme will fill in the gaps for you. If you didn't know the answers to the majority of the questions, however, it might be a good idea if you take some time to read through the glossaries listed at the beginning of each course and familiarise yourself with the terms we will use before you proceed. Copyright, acknowledgements and legal notice © Epigeum