October 18, 2016
(1) Systematic variation is
Week 12
- variation caused by random effects in any direction
- variation coming from a factor that introduces bias in one direction only
- always deflating the standard deviation
- all of the above
(2) The y-axis of a histogram represents…
Week 12
- the frequencies
- the scores
- any metric
- none of the above
(3) The standard error…
Week 12
- equals the standard deviation divided by the square root of the sample size
- estimates the correlation between two variables
- equals the mean in most cases
- often equals the standard deviation
(4) Pick the variable that is categorical and nominal
Week 12
- Rank in a 100 m race
- Civil status
- Numbers of cigarettes smoked per day
- Cholesterol level in blood samples (in mg/ml)
(5) Which of the following is not correct:
Week 12
- An independent variable is the same as a predictor variable
- A predictor variable can be a factor
- A response variable is the same as a factor
- A factor can have two or more factor levels
- A response variable can be categorical or continuous
(6) Which operation in calculating the variance helps to make sure the latter does not automatically increase with sample size?
Week 12
- Squaring the sum of the differences between observations and the mean
- Dividing by the degrees of freedom
- Summing up the differences between observations and the mean
- All of the above is correct
(7) In this sample: [1, 3, 11, 15, 19, 20, 22, 24, 30, 31, 39], …
Week 12
- the median is 20
- the first quartile is 11
- the third quartile is 30
- the interquartile range is 19
- all of the above are correct
- only (1) is correct
(8) A population is known to be chi-squared distributed with 4 degrees of freedom. What is the chance of finding a value greater than 10?
Week 12
- About 95%
- About 50%
- About 4%
- less than 4%
- Almost zero
(9) You want to find out whether protein content in yogurt (on a continuous scale from 0 to 10) affects the viscosity of the product. What test would you use?
Week 12
- A two-tailed Wilcoxon test
- A two tailed t-test
- A correlation analysis
- A regression approach
(10) In a power t-test, if you increase your sample size AND you decrease your standard deviation,…
Week 12
- you increase your power
- you increase your type I error probability
- you decrease your type II error probability
- you improve your chances to find a difference, should there be one
- All but (2) are correct
(11) After regression analysis, we need to check…
Week 12
- whether the residuals are continuous
- whether the residuals are homogenous along the fitted values
- whether the residuals are normal
- all of the above
- only (2) and (3) are correct
(12) Which is true for the correlation coefficient?
Week 12
- It ranges from -1 to 1
- It is not necessarily associated with a p-value
- It has nothing to do with the t-statistic
- It is the normalised covariance
- All of the above is correct
(13) Just by sketching a standard normal distribution, what is the probability of sampling a value greater than 2 from such a distribution?
Week 12
- the same as sampling a value lower than -2
- quite low, maybe a few percent
- around 30%
- infinitely small
- 1 and 2 are correct
(14) In regression analysis, we try to…
Week 12
- minimise the sum of squared differences between the observed values and the mean
- minimise the distances between the fitted values and the observed values
- minimise the sum of squared differences between the fitted values and the observed values
- maximise the sum of squared differences between the fitted values and the observed values
(15) If in a Chi-squared test with 1 degree of freedom, you obtain a Chi-squared value of 1, this means that
Week 12
- your p-value is extremely low
- your p-value is clearly not significant (i.e. not below 0.05)
- your p-value is above 1
- given the information, it is impossible to make a statement on the p-value