Chapter 1

1. Information is A. ? all the facts and figures B. ? the creation of a database C. ? the selective use of data to inform the user D. ? a summary of the solutions

2. The quantitative approach requires A. ? a scientific rigour in the collection of data B. ? the selective use of data C. ? the correctness of calculation D. ? all of the above

3. Primary data A. ? is collected for a specific purpose B. ? can be any data C. ? is supplementary data D. ? is none of the above

4. A parameter A. ? is a quantity or characteristic allowed to change within a particular problem B. ? takes a fixed value for a particular problem C. ? is always the same value

D. ? is always a different value

5. The level of measurement achieved by recording whether the person reading this book likes or dislikes the layout of a scale 1 to 5 is A. ? nominal B. ? ordinal C. ? interval D. ? ratio

6. The level of measurement achieved by recording whether the respondent smokes cigarettes or not is A. ? nominal B. ? ordinal C. ? interval D. ? ratio

7. The level of measurement achieved by calculating the travel distance of shoppers A. ? nominal B. ? ordinal C. ? interval D. ? ratio

8. Scoring models could be used for A. ? a cashflow forecast B. ? breakeven analysis

C. ? clarifying the choices between options that involve a number of factors D. ? the evaluation of a saving scheme

Chapter 2

1. Data is A. ? a coding of responses from a questionnaire B. ? a set of facts and figures from a database C. ? information collected for other purposes D. :-) all of the above

2. Secondary data A. :-) already exists for other purposes B. ? is used only second C. ? is always second best D. ? none of the above

3. Ws and H A. X is a coding of data B. :-) is a techniques for clarifying a problem or issue C. ? is a formula D. ? is a way of asking why 5 times

4. A good source of government statistics is A. ? www.ebay.co.uk B. ? www.bhs.org.uk

C. :-) www.statistics.gov.uk D. ? www.amazon.co.uk

5. We need to be cautious when using data from the internet because A. X sources may not be known B. X possible bias C. X incompleteness D. ? all of the above

6. A survey may be preferred to a census A. X because of cost constraints B. X because the methodology is adequate C. X because of time constraints D. ? all of the above

7. A smaller sample size can be used A. :-) if the variability in the population is smaller B. ? if greater accuracy if required C. ? if more detailed analysis is to be undertaken D. ? none of these

8. Market research A. X cannot estimate the market share of brands produced by other companies B. X can provide an alternative to statistical analysis

C. :-) can provide information on customer satisfaction D. ? cannot provide acceptable information on politically sensitive issues such as carbon emission and health service provision

Chapter 3

1. To reflect the opinions of a population a survey needs to A. ? Ask everyones opinion B. ? Ask opinions from any small group C. ? Ask the opinions of a representative group D. ? Ask opinions from the first 100 people you meet

2. A cluster sample will A. ? Seek views from a homogeneous group in the population B. ? Seek views from a heterogeneous group in the population C. ? Seek views from any group in the population D. ? Seek views from everyone who attends a group discussion

3. A two stage random sample A. ? Takes a random sample of groups and then a random sample in each selected one B. ? Takes a random sample and then a second one C. ? Takes a random sample from every group in the population D. ? Takes a random sample and analyses it in two stages

4. A longitudinal survey A. ? Follows a group as they travel B. ? Follows a group over many years C. ? Follows a group for a week

D. ? Follows a group as they grow up

5. 5 The question Most people liked this chocolate bar, do you? is A. ? A hypothetical question B. ? A question which contains jargon C. ? Two questions as one D. ? A leading question

6. The question Do you eat this food because it is good for you and you like it? is A. ? A hypothetical question B. ? A question which contains jargon C. ? Two questions as one D. ? A leading question

7. The question How early do you usually do your Christmas shopping? is A. ? A hypothetical question B. ? A question which contains jargon C. ? Two questions as one D. ? A leading question

8. The question How would you manage this situation if you were the manager? is A. ? A hypothetical question B. ? A question which contains jargon C. ? Two questions as one

D. ? A leading question

9. Gallup identified how many question objectives? A. ? 2 B. ? 3 C. ? 4 D. ? 5

10. Sampling methodology A. ? Is crucial to obtaining meaningful results B. ? Is a description of how the sampling was done C. ? Allows the results to be replicated D. ? All of these

Chapter 4

1. Component bar charts have A. ? All bars the same length B. ? Bars for percentages of each component C. ? Bars built up from sections for each component D. ? Are coloured to reflect the components

2. Pie charts can be used for A. ? Annual company reports B. ? Degree dissertations C. ? Publicity materials D. ? Any of these

3. 3 Earnings data is A. ? Categorical data B. ? Ordinal data C. ? Interval data D. ? Ratio data

4. If the figure for sales was 50 last year and is 61 this year, the percentage rise is A. ? 10 B. ? 11

C. ? 18 D. ? 22

5. If the following years figure is 65, the percentage rise is A. ? 4 B. ? 6.1 C. ? 6.5 D. ? 15

Chapter 6

1. Averages are A. ? A typical value B. ? A measure of location C. ? A measure of central tendency D. ? All of these

2. In a normal distribution A. ? The mean is above the median and mode B. ? The mean is below the median and mode C. ? The mean is equal to the mean and mode D. ? The mean is between the median and mode

3. Data Set 1: 14, 12, 17, 25, 14, 19, 30 For data set 1, the arithmetic mean is A. ? 14 B. ? 17 C. ? 18.7 D. ? 25

4. For data set 1 the median is A. ? 14

B. ? 17 C. ? 18.7 D. ? 25

5. For data set 1 the mode is A. ? 14 B. ? 17 C. ? 18.7 D. ? 25

6. If the final number were recorded as 300 the mean would be A. ? 17 B. ? 25 C. ? 57.3 D. ? 61.6

7. If the final number were recorded as 300, the median would be A. ? 17 B. ? 25 C. ? 57.3 D. ? 61.6

8. Data Set 2: Xf 10 65

20 25 30 10 For data set 2 the mean is A. ? 10 B. ? 14.5 C. ? 15 D. ? 20

9. For data set 2 the median is A. ? 10 B. ? 14.5 C. ? 15 D. ? 20

10. For data set 2 the mode is A. ? 10 B. ? 14.5 C. ? 15 D. ? 20

Chapter 6

1. Which of the following is not a measure of dispersion? A. ? Standard deviation B. ? Variance C. ? Median D. ? Quartile deviation

2. Measures of location and of dispersion are often used together, which of these is not a pair? A. ? Mean & standard deviation B. ? Median & quartile deviation C. ? Mode & range D. ? Mean & variance

3. Data Set 1: 8, 12, 14, 6, 12, 19, 27 For Data Set 1 the Range is: A. ? 5.5 B. ? 6.5 C. ? 19 D. ? 23

4. For Data Set 1 the standard deviation is: A. ? 5.5 B. ? 6.5

C. ? 21 D. ? 23

5. For Data Set 1 the quartile deviation is: A. ? 5.5 B. ? 6.5 C. ? 21 D. ? 23

6. For Data Set 1 the variance is: A. ? 30.25 B. ? 43.14 C. ? 441 D. ? 529

7. Data Set 2: mean = 30, median = 25, standard deviation = 4 For data set 2 the coefficient of variation is A. ? -3.75 B. ? +3.75 C. ? +7.5 D. ? +13.3

8. For data set 2 the coefficient of skewness is A. ? -3.75

B. ? +3.75 C. ? +7.5 D. ? +13.3

9. A decile represents a point in the data A. ? At a 10% value B. ? At a 5% value C. ? At a 1% value D. ? At none of these

10. Highly skewed data is best described by A. ? Range B. ? Variance C. ? Quartile deviation D. ? Percentiles

Chapter 7

1. Year Index 1 108 2 112 3 116 4 124 5 131 From the data above, the percentage change from year 1 to year 2 is A. ? 3.6 B. ? 3.7 C. ? 5.6 D. ? 6.9

2. From the data above, the percentage change from year 2 to year 3 is A. ? 3.6 B. ? 3.7 C. ? 5.6 D. ? 6.9

3. From the data above, if the index were rebased so that Year 3 = 100, the index for year 1 would be A. ? 93.1 B. ? 100 C. ? 112.9 D. ? 116

4. From the data above, if the index were rebased so that Year 3 = 100, the index for year 5 would be A. ? 93.1 B. ? 100 C. ? 112.9 D. ? 116

5. From the data above, the price relative for item B for the second year is A. ? 1.050 B. ? 1.1375 C. ? 1.167 D. ? 1.200

6. From the data above, the aggregative price for the second year is A. ? 105.0 B. ? 113.75 C. ? 116.7 D. ? 120.0

7. From the data above, the Laspeyres all items Price index for the second year is A. ? 100.0 B. ? 108.0

C. ? 112.0 D. ? 121.8

8. From the data above, the Paasche all items Price index for the second year is A. ? 100.0 B. ? 108.0 C. ? 112.8 D. ? 121.8

9. From the data above, the all items Value index for the second year is A. ? 100.0 B. ? 108.0 C. ? 112.8 D. ? 121.8

10. The Retail Prices Index uses A. ? 11 items B. ? 100 items C. ? 350 items D. ? 650 items

11. Year Index 1 108 2 112 3 116 4 124

5 131 From the data above, the percentage change from year 1 to year 2 is A. ? 3.6 B. ? 3.7 C. ? 5.6 D. ? 6.9

12. From the data above, the percentage change from year 2 to year 3 is A. ? 3.6 B. ? 3.7 C. ? 5.6 D. ? 6.9

13. From the data above, if the index were rebased so that Year 3 = 100, the index for year 1 would be A. ? 93.1 B. ? 100 C. ? 112.9 D. ? 116

14. From the data above, if the index were rebased so that Year 3 = 100, the index for year 5 would be A. ? 93.1 B. ? 100 C. ? 112.9

D. ? 116

15. From the data above, the price relative for item B for the second year is A. ? 1.050 B. ? 1.1375 C. ? 1.167 D. ? 1.200

16. From the data above, the aggregative price for the second year is A. ? 105.0 B. ? 113.75 C. ? 116.7 D. ? 120.0

17. From the data above, the Laspeyres all items Price index for the second year is A. ? 100.0 B. ? 108.0 C. ? 112.0 D. ? 121.8

18. From the data above, the Paasche all items Price index for the second year is A. ? 100.0

B. ? 108.0 C. ? 112.8 D. ? 121.8

19. From the data above, the all items Value index for the second year is A. ? 100.0 B. ? 108.0 C. ? 112.8 D. ? 121.8

20. The Retail Prices Index uses A. ? 11 items B. ? 100 items C. ? 350 items D. ? 650 items

Chapter 8

1. Throwing a die, the probability of an even number is A. ? 1/6 B. ? 2/6 C. ? 3/6 D. ? 4/6

2. Throwing 2 die, the probability of an even total score is A. ? 6/36 B. ? 9/36 C. ? 18/36 D. ? 27/36

3. Throwing 2 die, the probability of an total score below 6 is A. ? 6/36 B. ? 16/36 C. ? 20/36 D. ? 26/36

4. From a standard pack of cards, the probability of selecting an Ace or a Spade is A. ? 13/52 B. ? 16/52

C. ? 17/52 D. ? 18/52

5. From a standard pack of cards, the probability of selecting a picture card (K, Q, J) on either or both of two selections without replacement is: A. ? 69/169 B. ? 1082/2652 C. ? 1560/2652 D. ? 100/169

6. From a standard pack of cards, the probability of not selecting a queen or a heart on two selections without replacement is A. ? 1/51 B. ? 105/221 C. ? 315/679 D. ? 36/52

7. You have 12 black and 6 blue socks in a draw. The lights stop working and you pick out 2 socks in the dark, What is the probability you get a pair the same colour? A. ? 30/306 B. ? 102/306 C. ? 132/306 D. ? 162/306

8. You have bought a box of 100 badges to sell for charity. There are 60 red ones of which 10 are faulty and the rest are blue of which a quarter are faulty.

What is the probability of picking out a faulty badge? A. ? 0.2 B. ? 0.5 C. ? 0.6 D. ? 0.7

9. What is the probability of picking out a badge which is red or faulty? A. ? 0.2 B. ? 0.5 C. ? 0.6 D. ? 0.7

10. What is the probability that a faulty badge that has been selected is red? A. ? 0.2 B. ? 0.5 C. ? 0.6 D. ? 0.7

Chapter 9

1. A table of random numbers has a A. ? Normal distribution B. ? Uniform distribution C. ? Binomial distribution D. ? Poisson distribution

2. A binomial distribution has A. ? A variable chance of success B. ? An unlimited number of trials C. ? Many outcomes D. ? Independence of events

3. The number of ways of picking 4 from 6 is A. ? 15 B. ? 20 C. ? 24 D. ? 720

4. The number of ways to pick 2 from 6 is A. ? 15 B. ? 20

C. ? 24 D. ? 720

5. For a binomial probability distribution with n=5 and p=0.2, the probability of 2 successes is: A. ? 0.05792 B. ? 0.08 C. ? 0.2048 D. ? 0.26272

6. For the same distribution, the probability of less than 3 successes is: A. ? 0.05792 B. ? 0.08 C. ? 0.2048 D. ? 0.26272

7. For the same distribution, the probability of more than 3 successes is: A. ? 0.2048 B. ? 0.26272 C. ? 0.73728 D. ? 0.94208

8. For a poisson distribution with an average of 1`, the probability of zero successes is: A. ? 0.2642

B. ? 0.3679 C. ? 0.6321 D. ? 0.7358

9. For the same distribution, the probability of more than 1 is: A. ? 0.2642 B. ? 0.3679 C. ? 0.6321 D. ? 0.7358

10. For a poisson distribution, the mean is: A. ? n B. ? np C. ? npq D. ? npq

Chapter 10

1. A Normal Distribution is A. ? symmetrical B. ? bimodal C. ? skewed D. ? uniform

2. A normal distribution with a mean of 100 and a standard deviation of 10 has 5% of the values above: A. ? 101.645 B. ? 101.96 C. ? 116.45 D. ? 119.6

3. The same distribution has 97.5% of values below: A. ? 101.645 B. ? 101.96 C. ? 116.45 D. ? 119.6

4. For a standard normal distribution, the area to the right of z=+1.5 is: A. ? 0.0668 B. ? 0.1469 C. ? 0.8531

D. ? 0.9332

5. For a standard normal distribution, the area to the left of z=+1.05 is: A. ? 0.0668 B. ? 0.1469 C. ? 0.8531 D. ? 0.9332

6. For a standard normal distribution, the area to the right of z= -2.03 is: A. ? 0.01072 B. ? 0.02118 C. ? 0.97882 D. ? 0.98928

7. For a standard normal distribution, the area between z= -2 and z=+1 is: A. ? 0.18095 B. ? 0.31905 C. ? 0.61430 D. ? 0.81905

8. For a standard normal distribution, the area between z= +0.5 and z=+1 is: A. ? 0.1503 B. ? 0.4667 C. ? 0.5333

D. ? 0.8497

9. IQ scores are said to be normal with a mean of 100 and a standard deviation of 10. What percentage of people will have an IQ of over 120: A. ? 2.275% B. ? 11.51% C. ? 15.87% D. ? 22.75%

10. For the same IQ distribution, what percentage will be below 95? A. ? 3.85% B. ? 30.85% C. ? 50% D. ? 69.15%

Chapter 11

1. You can take a smaller sample if A. ? you want to do a more detailed analysis of subgroups B. ? less accuracy is acceptable C. ? a higher level of confidence is required D. ? there is more variability in the population

2. If you decide to use a 95% confidence interval rather than a 99% confidence interval you would expect the confidence interval to become A. ? wider B. ? stay the same C. ? smaller D. ? increase by 4%

3. Given the sample statistics n = 80, = 9.90 and s = 1.84 , the 95% confidence interval is given by A. ? = 9.90 0.40 B. ? = 9.90 1.84 C. ? = 8.06 1.84 D. ? = 9.90 3.61

4. To estimate the true mean to within 5.00 with a 95% confidence interval, given a standard deviation of 56.50 requires a sample size of A. ? 100 B. ? 250

C. ? 500 D. ? 1000

5. In a survey of 300 call customers, 33 complain that connection time is a problem for them. The 95% confidence interval is A. ? 33 2% B. ? 33 4% C. ? 11% 2% D. ? 11% 4%

6. Assuming a worse case scenario that p = 50% the sampling size required to give a 95% confidence interval with a sampling error of no more that 2% is A. ? 1000 B. ? 1500 C. ? 2000 D. ? 2500

7. Given n1 = 150, x1 = 78.40, s1 = 8.20 and n2 = 180, x2 = 72.00, s2 = 6.45 the 95% confidence interval for the difference of means is given by A. ? 6.40 1.62 B. ? 6.40 1.96 C. ? 6.40 0.82 D. ? 6.40 3.24

8. Given n1 = 150, p1 = 7% and n2 = 180, p2 = 4% the 95% confidence interval for the difference of means is given by

A. ? 3% 3% B. ? 3% 5% C. ? 3% 7% D. ? 3% 9%

9. A sample of 70 is taken from a population of 80. The finite population correction factor is A. ? 0.9354 B. ? 0.875 C. ? 0.3536 D. ? none of these

10. A random sample of 8 business transactions was selected from a large number of such transactions. The degrees of freedom and the critical value using the t-distribution for the 95% confidence interval would be A. ? = 7 and cv = 1.895 B. ? = 8 and cv = 1.860 C. ? = 7 and cv = 2.365 D. ? = 6 and cv = 2.447

Chapter 12

1. A hypothesis A. ? is always a good idea B. ? can always be accepted if the sample is large enough C. ? a concept that should be accepted D. ? none of the above

2. The larger the value of the test statistic the more likely you are to

A. ? reject the alternative hypothesis B. ? accept the null hypothesis C. ? reject the null hypothesis D. ? reject the null hypothesis and reject the alternative hypothesis

3. Given H0: = 100, H1: 100, a significance level of 5% and z = 2.07 A. ? you would accept the null hypothesis B. ? you would reject the null hypothesis C. ? you would change the level of significance D. ? you would accept the alternative hypothesis

4. Given H0: = 50%, H1: 50%, a significance level of 5% and z = -1.04 A. ? you would accept the null hypothesis B. ? you would reject the null hypothesis C. ? you would change the level of significance

D. ? you would accept the alternative hypothesis

5. A Local Authority is interested in whether the average travel distance to school within a study area has remained at 2 miles or has increased The hypotheses can be stated as: A. ? H0 = 2 H1 2 B. ? H0 = 2 H1 < 2 C. ? H0 = 2 H1 > 2 D. ? H0 < 2 H1 = 2

6. The marketing department claims that 60% of customers are aware of the full range of the products offered by the company. Senior management thinks it could be less. The hypotheses can be stated as: A. ? H0 = 60% H1 60% B. ? H0 = 60% H1 < 60% C. ? H0 = 60% H1 > 60% D. ? H0 < 60% H1 = 60%

7. Given H0 (1 2) = 0 and H1 ( 1 2) < 0 where is a percentage, we are testing A. ? a null hypothesis that the percentage in population 1 is smaller than the percentage in population 2 B. ? a null hypothesis that the than the percentage population 1 is larger than the percentage population 2 C. ? a null hypothesis of no difference against an alternative that the percentage of population 1 is smaller that population 2 D. ? a null hypothesis of no difference against an alternative that the percentage of population 1 is larger that population 2

8. When using the t distribution, the critical value will depend upon A. ? the sample size B. ? the level of significance C. ? degrees of freedom D. ? all of these

Chapter 13

1. A parametric test requires the following conditions A. ? a null hypothesis that can be stated in terms of a parameter B. ? a meaningful level of measurement has been achieved that gives validity to difference C. ? a test statistic that follows a known distribution D. ? all of the above is true

2. A non-parametric test requires A. ? a null hypothesis B. ? the calculation of a test statistic C. ? the use of critical values D. ? all of the above

3. A chi-squared test statistic of 16.548 has been calculated for a 4 by 5 cross tabulation (with all expected frequencies above 5). Using a 5% significance level A. ? you would compare with a critical value of 21.0 and not reject the null hypothesis B. ? you would compare with a critical value of 21.0 and reject the null hypothesis C. ? you would compare with a critical value of 14.8 and not reject the null hypothesis D. ? you would compare with a critical value of 14.8 and reject the null hypothesis

4. A frequency table has been used to report the length of life of a component. The table has 8 intervals and has been used to calculate the sample mean and sample standard deviation. It has been decided to test at the 1% significance level whether the length of life follows a normal distribution. A chi-squared test statistic of 13.246 was calculated by

comparing the observed and expected frequencies (with all expected frequencies above 5). You would compare the chi-squared value with a critical value of A. ? 11.1 and not reject the null hypothesis B. ? 11.1 and reject the null hypothesis C. ? 15.1 and not reject the null hypothesis D. ? 15.1 and reject the null hypothesis

5. You are using the Mann-Whitney U test for a small sample and have been given the following summary: Rank Sample 12 22 3.5 1 3.5 2 51 62 71 8.5 1 8.5 2 10 2 11 1 12 1 Using a 5% significance level A. ? you would compare a T value of 10 with a critical value of U of 6 and reject null hypothesis B. ? you would compare a T value of 10 with a critical value of U of 6 and not reject null hypothesis C. ? you would compare a T value of 10 with a critical value of U of 6 and reject null hypothesis D. ? you would compare a T value of 10.5 with a critical value of U of 12 and not reject null hypothesis

6. You are using the Mann-Whitney U test for a large sample and have been given the following statistics: T = 258, n1 = 15 and n2 = 25. Using a 5% significance level you would compare a z value of A. ? +1.87 with +1.645 and reject null hypothesis B. ? +1.87 with +1.96 and not reject null hypothesis C. ? -2.87with +1.96 and reject null hypothesis D. ? +2.87 with +1.96 and not reject null hypothesis

7. A company has identified a number of fraudulent claims. To test whether they are random they should use a: A. ? Mann-Whitney U test for small samples B. ? Wilcoxon test for small samples C. ? Wilcoxon test for large samples D. ? Runs test

Chapter 14

1. Correlation is a measure of A. ? cause and effect B. ? the intercept C. ? the change in y D. ? none of these

2. A correlation coefficient cannot take the value A. ? 0 B. ? -1 C. ? +1.50 D. ? 0.5567

3. A perfect positive relationship is indicated by the correlation coefficient A. ? +1 B. ? 0 C. ? -1 D. ? 100%

4. You have been given the following data for y and x:

You would expect the correlation coefficient that you would calculate to equal A. ? +1 B. ? 0

C. ? -1 D. ? any value between -1 and +1

5. You have been given the following data for y and x:

You would expect the correlation coefficient that you would calculate to equal A. ? +1 B. ? 0 C. ? -1 D. ? none of these

6. A correlation coefficient near +1 would suggest A. ? a limited correlation B. ? a complete set of data C. ? a strong positive relationship D. ? a strong negative relationship

7. A Spearmans coefficient of rank correlation near to 0 would suggest A. ? the need for an alternative test B. ? a poor relationship C. ? the possibility of a negative relationship D. ? the need fro improved measurement

8. The coefficient of determination of 90% would suggest A. ? there is a good explanation of cause and effect B. ? there is a limited explanation of cause and effect C. ? that most of the variation in the data has been explained D. ? there is a lack of explanation of variation in the data

9. Transformation of the data can A. ? improve the quality of the data B. ? increase the amount of data C. ? improve the fit of a linear relationship D. ? identify non-linear relationships

10. Using a test of significance for the correlation coefficient A. ? we may be able to accept the alternative hypothesis that some relationship exists B. ? we may be able to accept the null hypothesis that some relationship exists C. ? we may be able to reject the null hypothesis that some relationship exists D. ? none of the above

Chapter 15

1. The regression line may be referred to as A. ? the line of best fit B. ? the least squares line C. ? the regression of y on x D. ? all of the above

2. If the correlation coefficient is equal to +1 then A. ? all points will lie on a line sloping upwards to the right B. ? all points will lie on a line sloping downwards to the right C. ? some points will lie on a line sloping upwards to the right D. ? some points will lie on a line sloping downwards to the right

3. If the correlation coefficient is equal to -0.3 then we would expect to make A. ? good predictions from a regression line sloping upwards to the right B. ? good predictions from a regression line sloping downwards to the right C. ? poor predictions from a regression line sloping upwards to the right D. ? poor predictions from a regression line sloping downwards to the right

4. Which of the following equations best describe this data?

A. ? y = 8 + 12x B. ? y = 12 + 8x

C. ? y = 8 D. ? y = 12

5. You have been given the following data for y and x:

Which of the following equations best describe this data? A. ? y = 11 + 3x B. ? y = 20 + 3x C. ? y = 11 + 5x D. ? y = 20 + 5x

6. You have been given the following data for y and x: x 15 16 17 17 18 y 71 72 74 84 87 Which of the following regression lines do you think would best fit this data? Hint: you should be helpful to draw the scatter diagram first A. ? y = -12.42 - 5.42x B. ? y = -12.42 + 5.42x C. ? y = +12.42 + 5.42x D. ? y = +12.42 - 5.42x

7. If the value we would predict for y given x = 9 is A. ? 212.6 B. ? 212.8 C. ? 213.8

D. ? 214.6

8. If the value we would predict for y given x = -12 is A. ? -117 B. ? 117 C. ? -87 D. ? 87

9. Extrapolation is A. ? prediction outside the range of the data B. ? any prediction C. ? prediction within the range of the data D. ? no prediction

10. A transformation to linearity A. ? will allow regression analysis to be used B. ? will reduce the correlation coefficient C. ? limit further analysis D. ? is unnecessary provided you have sufficient data

Chapter 16

1. Multiple regression relates A. ? the dependent variable y to two or more explanatory variables B. ? the dependent variable y to two or more dependent variables C. ? an explanatory variable to one or more dependent variables D. ? an explanatory variable to one dependent variable

2. The coefficient of determination A. ? provides a measure of the variation explained by the regression model B. ? can guide the selection of additional variables C. ? can be given as an adjusted figure to provide an unbiased estimate D. ? all of the above

3. Multicollinearity exists when A. ? two or more of the independent variables are not correlated B. ? the dependent variables is highly correlated with two or more of the independent variables C. ? two or more of the independent variables are highly correlated D. ? the dependent variables is not highly correlated with the independent variables

4. The basic test of autocorrelation is provided by A. ? the coefficient of determination B. ? the Durbin-Watson test C. ? the t-test

D. ? none of the above

5. The multiple regression model will be improved by the A. ? exclusion of seasonality B. ? reduced number of variables C. ? careful specification of variables D. ? none of the above

Chapter 17

1. A time series model could include A. ? Trend B. ? Seasonal factors C. ? Cyclical factors D. ? All of the above

2. A trend is A. ? copying past figures B. ? a general direction in which the figures are moving C. ? being the same as other current figures D. ? the use of regression

3. the use of regression A. ? A = T S C R B. ? A = T S + C + R C. ? A = T + S + C + R D. ? A = T S C R

4. The additive model is given by A. ? A = T S C R B. ? A = T S + C + R C. ? A = T + S + C + R

D. ? A = T S C R

5. The number of periods included in a moving average trend correspond to A. ? always 4 , 5 or 6 B. ? the maximum possible C. ? the minimum possible D. ? none of these

6. The seasonal factor for the additive model is estimated using A. ? A - T B. ? T S C. ? T/A D. ? A/T

7. Predictions are made by A. ? averaging the trend and seasonal variation B. ? extending the trend and adjusting for seasonal factor C. ? giving the average seasonal variation D. ? extending for the trend and adjusting for the residual

8. The exponentially weighted moving average A. ? gives more weight to recent data B. ? has a sum of weights which equals 1 C. ? is weighted exponentially

D. ? all of these

Chapter 18