For Exercise 5.1, see page 101.
5.2 Explanatory and response variables. Does regular church attendance lengthen people’s lives? One study of the effect of regular attendance at religious services gathered data from a random sample of 3617 adults. The researchers measured whether a person attended religious services regularly and length of life. Which of the following is true?
(a) In this study, length of life is the explanatory variable and regular attendance of religious services is the response variable.
(b) In this study, regular attendance of religious services is the explanatory variable and length of life is the response variable.
(c) In this study, the 3617 adults are the explanatory variable and the information they provided is the response variable.
(d) In this study, there are no explanatory and response variables because these data come from a survey.
5.3 Observational study or experiment? The study described in Exercise 5.2 is
(a) a randomized comparative experiment.
(b) an experiment, but not a randomized experiment.
(c) an observational study.
(d) neither an experiment nor an observational study but, instead, a sample survey.
5.4 Lurking variables. People who attend church or synagogue are less likely to smoke or be overweight than nonattenders. In the study described in Exercise 5.2,
(a) smoking is a lurking variable, but weight is not.
(b) weight is a lurking variable, but smoking is not.
(c) smoking and weight are both lurking variables.
(d) neither smoking nor weight is a lurking variable.
5.5 Statistical significance. In the study described in Exercise 5.2, researchers found that, by the end of the study, there was a statistically significant difference in the likelihood of dying between those who regularly attend religious services and nonattenders. Nonattenders were 25% more likely to have died by the end of the study. Statistical significance here means
(a) the size of the observed difference in the likelihood of dying is not likely to be due to chance.
(b) the size of the observed difference in the likelihood of dying is likely to be due to chance.
(c) the size of the observed difference in the likelihood of dying has a 25% chance of occurring.
(d) the size of the observed difference in the likelihood of dying has a 75% chance of occurring.
109
5.6 Randomized comparative experiment? For which of the following studies would it be possible to conduct a randomized comparative experiment?
(a) A study to determine if the month you were born in affects how long you will live.
(b) A study to determine if taking Tylenol dulls your emotions.
(c) A study to determine if a person’s sex affects his or her salary.
(d) A study to determine if the wealth of parents affects the wealth of their children.