stats practice test

1) You are studying whether owning a dog and can improve happiness and reduce stress. You sample 100 families with dogs and 100 families without dogs and measure the blood stress hormone cortisol. What analysis would you use to test the null hypothesis that owning a dog does not impact the concentration of stress hormones? [1 mark] A. 2-sample t-test B. correlation C. 1-samplet-test D. paired t-test E. linear regression

A

15)You get a phone call from a friend working at Dupont who is trying to quantify the variation in a new monitoring technique. Having just taken statistics, you proudly reply that the standard error is a good metric and proceed to quickly work up the number for her. Your friend has obtained 22 samples and found a standard deviation of s=1.1. What is the standard error of the sampling distribution? [1 mark] A. 0≤ANSWER<0.5 B. 0.5 ≤ ANSWER < 1.0 C. 1.0 ≤ ANSWER < 1.5 D. 1.5 ≤ ANSWER < 2.0 E. 2.0 ≤ ANSWER < 2.5

A

Select the study design that is the best match to the scientific question "What is the risk that men who were exposed to lead in their water supply as children will have cancer at age 40 when they are assessed, compared to those who were unexposed?" [1 mark] A. Observational case-control study B. Observational cohort study C. Observational stratified survey with different regions as strata D. Experimental treatment-control study E. Experimental treatment-control study with blocking by region

A

TUDY C Use the following study to answer questions 16 and 17. Researchers interested in the effect of sleep on the likelihood of contracting a common cold followed 30 adults for one year. Subjects were selected by first randomly choosing an address from the City of Kingston tax list, and then selecting the oldest adult in the house. Subjects were asked to record the number of sleep hours each night, as well as the number of colds. The researchers then evaluated whether the number of sleep hours could be used to predict number of colds. 1 6)For STUDY C, what is the observation unit? [1 mark] A. The adult B. The home address C. The hours of sleep D. The number of colds E. The number of people in the household 17)For STUDY C, what is the most appropriate statistical test? [1 mark] A. 2-sample t-test B. correlation C. 1-samplet-test D. paired t-test

A and E

You are interested in comparing whether 'flyer' advertising has an impact on the sales of Fluevog shoes. To study this, you compare sales for two groups of 20 stores—ones that used flyers and ones that didn't. The null hypothesis for the test would be that the difference in sales for the two groups is zero, but the null distribution includes a range of values that are below zero and above zero. What generates this variation in the null distribution? [1 mark] A. Type I error B. Type II error C. Power D. Sampling error E. None of the above

D

4)Select which of the following null and alternative hypotheses are most appropriate for a two-sample t-test that answers the following question: "Is the mean of treatment A (μA) different than the mean of treatment B (μB)?". [1 mark] A. H0:μA≤μB B. H0:μA≤μB C. H0:μA≥μB D. H0:μA≠μB E. H0:μA=μB HA:μA=μB HA:μA>μB HA:μA<μB HA:μA=μB HA:μA≠μB

E

A marketing researcher wanted to test the hypothesis that a new advertisement campaign aimed at making the company seem more 'real' to customers by highlighting the deficiencies of the company was better than their typical campaign presenting a polished appearance. The results show a t-observed score that was less extreme than the t-critical. Which of the following statistical conclusions is correct based on these results? [1 mark] A. Reject the null hypothesis because the 'p'-value is less than the type I error rate. B. Fail to reject the null hypothesis because the t-observed is greater than the t- critical. C. Accept the alternative hypothesis because the 'p'-value is greater than the type I error rate. D. Reject the null hypothesis because the 'p'-value is greater than the type I error rate. E. Fail to reject the null hypothesis because the 'p'-value is greater than the type I error rate.

E

9) You take a random sample from a population and form a 95% confidence interval. Which quantity is guaranteed to be in the interval you form? [1 mark] A. 0 B. 0.05 C. the true population mean D. the sample mean E. the extreme values

d

Which of the following scientific questions would be best investigated using a 1- tailed test of significance? (Multiple answers possible: 1 mark for each correct response. You will lose 0.5 marks for each incorrect answer, but only applied to this question.) A. Does Pepsi taste better than Coke? B. Is there an increased risk of depression from consuming too much alcohol? C. Does changing dietary salt intake have an impact on blood pressure? D. Is there an association between the amount of money spent on homeopathic remedies and lifespan? E. Can we use small amounts of spice to alter taste perception in place of salt? F. Do increased wage earnings improve the amount of money you save?

A, B & F

Which of the following statements about confidence intervals are correct? (Multiple answers possible: 1 mark for each correct response. You will lose 0.5 marks for each incorrect answer, but only applied to this question.) A. Confidence intervals of the mean share a common sampling distribution with t-tests. B. Confidence intervals indicate the range over which the true population value lies. C. Confidence intervals show the probability of rejecting the null distribution when it is in fact correct. D. Confidence intervals use the standard error estimated from your sample. E. Confidence intervals are one-tailed. F. Confidence intervals are not used to test hypotheses.

A,D,F

13) Which of the following statements about statistical errors is true? [1 mark] A. Type I error is the probability of failing to reject a false null hypothesis and is set by the researcher. B. Type II error is the probability of rejecting a false null hypothesis and is not set by the researcher. C. Type I error is the probability of rejecting a true null hypothesis and is set by the researcher. D. Type II error is the probability of rejecting a true null hypothesis and is not set by the researcher. E. Type I and II errors are forms of the technical term "Sampling Error".

C

10) Much statistical theory is based on the distinction between the sample, the sampling distribution and the population. Which of the following is unaffected by the sample size (n)? [1 mark] A. the mean of the sample B. the standard deviation of the sampling distribution C. the population mean D. the standard deviation of the sample E. the variance of the sampling distribution

c

4) For STUDY A, what is the most appropriate test to evaluate whether the level of sleep is independent of school grades? [1 mark] A. Single-sample t-test B. Two-sample t-test C. Chi-square test D. Correlation test E. Linear regression test

c

STUDY A Use the following study to answer questions 3 and 4. You have been hired by the local municipal government to study the relationship between student grades and hours of sleep in elementary school children. Your study design is to randomly select classrooms in the district and interview 10 children from each classroom. For each child, you record information about their age (years), amount of sleep per night (categories of low, average or high), school grades (categories of letter grade) and their home address. 2 3) For STUDY A, what is the sampling unit? [1 mark] A. The child B. The home address C. The classroom D. The school E. The district

c