Principles of Data Analysis

Question 1

Other things being equal, as the sample size increases, the effect size also
increases

Answer

true

Question 2

The standard error of a statistic will always be smaller than its standard deviation

Answer

true

Question 3

The statement “perceived brand switching cost for loyal consumers is
significantly different than that for non-loyal consumers” corresponds to a one tailed
hypothesis

Answer

true

Question 4

Statistically significant results indicate that a test statistic, at least as big as the
one obtained in a given study, has a low probability of occurance (typically less
than 5%), if there is no effect in the population.

Answer

true

Question 5

the standard deviation is a measure of how well a given statistic (e.g mean) represents the sample

Answer

true

Question 6

Other things being equal, the size of the population increases the statistical
power of a test

Answer

true

Question 7

A distribution in which the most frequent scores are lower than the average score
(mean) is a positively skewed distribution (= skewness > 0)

Answer

true

Question 8

validity is the measurement of a variable that cannot be influenced by systematic error, if random error is zero

Answer

true

Question 9

statistical power is the opposite of the probability making a Type 1 error

Answer

true

Question 10

Given a 95% confidence interval (CI) for a mean, we can argue that 95 out of 100 CIs constructed by different samples will contain the true population paramenter

Answer

true

Question 11

The regional manager of a multinational company with 8 different sales offices in Austria wants to compare sales performance across the 8 offices in order to award a bonus to the best performing office. In this case “sales office” would be a dependent variable

Answer

true

Question 12

A brand manager wants to compare the revenues brand Z generates across the different months. In this case “months” would be an ordinal variable.

Answer

true

Question 13

the discrepancy between the numbers used to represent something that we are trying to measure and the actual value of what we are measuring is called variance

Answer

true

Question 14

Other things being equal, the 99% confidence interval (CI) for an estimate in a
given sample will be

Accepted Answer

wider than the 95% CI

Answer

narrower than the 95% CI

Question 15

with 99% confidence level, when would it be correct to not reject the null
hypothesis (H0)?

Accepted Answer

when the resulting test has a p > 0.05

Answer

when the resulting test has a p < 0.05

Question 16

the assumption of homogeneity of variance is successfully met when the variance of a variable across different levels of another variable is significantly different

Answer

true

Question 17

Validity in the measurement of a variable cannot be influenced by systematic error, if random error is zero

Answer

true

Question 18

other things being equal, the higher the systematic error in a measurement of a variable, the lower the reliability of the measurement

Answer

true

Question 19

the critical test yielded a p-value of 0.015 and the researcher concluded that the findings are statistically significant at the 5% significant level. The decision is:

Answer

true

Question 20

a frequency distribution that has very few scores at the extremes (i.e. the tails) in relation to the midpoint of the distribution is said to be platykurtic

Answer

true

Question 21

This histogram shows the distribution of Lady Gaga’s fifth studio album, Joanne. Based on the data from this histogram, we safely conclude that the mode = 5 and the median is <4.

Answer

true

Question 22

a recent article on a local newspaper presented the following graph (sample means for mathematics performance and respective 95% confidence intervals) claiming that in Austria the average performance of male students in Mathematics is worse than that of females. A researcher investigated the graph and concluded that this statement cannot be true because even though the sample means differ, their confidence intervals overlap, showing that this difference cannot be statistically significant. Do you agree or disagree with the researcher’s conclusion?

Answer

true

Question 23

the statistical power of a test does not depend on the effect size

Answer

true

Question 24

the p-value of a test indicates how likely it is that the results we obtained are due to chance

Answer

true

Question 25

a distribution in which the most frequent scores are lower than the average score is a positively skewed distribution (Skewness > 0)

Answer

true

Principles of Data Analysis

Create a free account to finish this quiz

Questions in this quiz (25)

Information

Feedback

What do you think of the new look?