Why is it correct to say, “We are 95% sure that the population mean is between $15.85 and $19.36” but not proper to say, “The probability is 0.95 that the population mean is between $15.85 and $19.36”?
> Test to see if the gender ratio differs significantly from 50%.
> You would like to claim that the population has significantly more than five years of experience, on average. Can you support this claim?
> Is Jones correct? That is, using the more complete data set, is it true that Jones has the lowest defect rate overall? Are Jones’s percentages correct overall (i.e., combining domestic and overseas production)?
> Is the average annual salary significantly different from $40,000?
> Viewing the database in Appendix A as a random sample from a much larger population, consider the age values. a. Find the 95% confidence interval. b. Find the 90% confidence interval.
> Repeat exercise 1, parts b and c, using a90% confidence interval. Is the population mean annual salary in the interval? Data from exercise 1: View this database as a population. Consider the following sample of five employee numbers from this database:
> Now look at the entire population of salaries, which you can not usually do in real life. a. Find the population mean and standard deviation, and compare them to the sample estimates from the previous problem. b. Draw a graph for this situation in the st
> Viewing the database in Appendix A as a random sample from the idealized population of potential employees you might hire next: a. Find the 95% prediction interval for the experience of your next hire. Why is this interval so much wider than the confiden
> Viewing the database in Appendix A as a random sample from a much larger population of employees: a. Find the 95% one-sided confidence interval for the population mean annual salary specifying that salaries are at least some amount. b. Find the 99% one-s
> View this database as a population. Consider the following sample of five employee numbers from this database: 24, 54, 17, 34, and 53. a. Find the average, standard deviation, and standard error for annual salary based on this sample. b. Find the 95% con
> What assumptions are required concerning the distribution of each population?
> Which assumption helps the data be representative of the population?
> Name and interpret the two sources of variation in the one-way analysis of variance.
> Why can the standard error of the average difference be a different number depending on which samples you are comparing?
> What kinds of additional terms are needed to include seasonal behavior in advanced ARIMA models?
> Are statistical estimates always correct? If not, what else will you need (in addition to the estimated values) in order to use them effectively?
> For each of the following, say whether it is stationary or non stationary: a. Autoregressive process. b. Random walk. c. Moving-average process. d. ARMA process.
> Distinguish stationary and non stationary time-series behavior.
> Do exercise 8 using the binomial proportion p in place of X. Data from exercise 8: Continuing with the sample from exercise 2: a.* Find the binomial X for the gender variable (counting the number of females) and interpret it. b.* Find the standard erro
> a. How is a time series different from cross-sectional data? b. What information is lost when you look at a histogram for time-series data?
> Should you assume that everyone who reads your conclusion is already familiar with all of the details of the analysis and methods section?
> Is it OK to repeat material in the introduction that already appeared in the executive summary?
> How can you use the executive summary and introduction to reach a diverse audience with limited time?
> How can an outline help you?
> How can you find synonyms for a given word? Why might you want to?
> How would you check the meaning of a word to be sure that you are using it correctly?
> What is the relationship between the outline and the finished report?
> What can a statistical model help you accomplish? Which basic activity of statistics can help you choose an appropriate model for your data?
> When is the best time to write the introduction and executive summary, first or last? Why?
> Continuing with the sample from exercise 2: a.* Find the binomial X for the gender variable (counting the number of females) and interpret it. b.* Find the standard error of X and interpret it. c. Find the population mean for the binomial X. d. How far i
> What can you do to help those in your audience who are short of time?
> What is the primary purpose of writing a report?
> Describe the two measures that tell you how helpful a multiple regression analysis is.
> Why should variables measured in the same basic units be transformed in the same way?
> Which activity (correlation or regression analysis) is involved in each of the following situations? a. Investigating to see whether there is any measurable connection between advertising expenditures and sales. b. Developing a system to predict portfoli
> Distinguish correlation and regression analysis.
> What is extrapolation? Why is it especially troublesome?
> a. Which is usually better, a lower or a higher value for R2? b. Which is better, a lower or a higher value for Se?
> For each of the following situations tell whether the predicted value or the residual would be most useful. a. For budgeting purposes you need to know what number to place under “cost of goods sold” based on the expected sales figure for the next quarter
> What can be done with multivariate data?
> Do exercise 3 using the experiences instead of the salaries. Data from exercise 3: Continuing with the sample from the preceding exercise: a. Find the population mean for salary. (Note: In real life, you usually cannot find the population mean. We are
> Are Kellerman’s conclusions correct?
> What is new and different about analysis of bivariate data compared to univariate data?
> Suppose you learn that the p- value for a hypothesis test is equal to 0.0217. What can you say about the result of this test?
> What standard error would you use to test whether a new observation came from the same population as a sample? (Give both its name and the formula.)
> Suppose you have an estimator and would like to test whether or not the population mean value equals 0. What do you need in addition to the estimated value?
> What p-value statement is associated with each of the following outcomes of a hypothesis test? a. Not significant. b. Significant. c. Highly significant. d. Very highly significant.
> a. What confidence levels other than 95% are in common use? b. What would you do differently to compute a 99% confidence interval instead of a 95% interval? c. Which is larger, a two-sided 90% confidence interval or a two-sided 95% confidence interval?
> Why are critical t values generally larger than1.960 for a two-sided 95% confidence interval?
> Which fact about a normal distribution leads to the factor 2 (or 1.960) in the approximate confidence interval statement?
> What does a confidence interval tell you about the population that an estimated value alone does not?
> Do exercise 3 using the ages instead of the salaries. Data from exercise 3: Continuing with the sample from the preceding exercise: a. Find the population mean for salary. (Note: In real life, you usually cannot find the population mean. We are peeking
> In what way do bivariate data represent more than just two separate univariate data sets?
> In what important way does statistical inference go beyond summarizing the data?
> a. What is the sampling distribution of a statistic? b. What is the standard deviation of a statistic?
> a. What is a statistic? b. What is a parameter?
> What is a frame? What is its role in sampling?
> What do the standard errors Sx and Sp indicate for a binomial situation?
> a. What is the complement of an event? b. What is the probability of the complement of an event?
> What are mutually exclusive events?
> a. What is an event? b. Can a random experiment have more than one event of interest?
> a. What is an outcome? b. Must the outcome be a number?
> Do exercise 2 using the experiences instead of the salaries. Data from exercise 2: Draw a random sample without replacement of 10 employees, using the table of random digits, starting in row 23, column 7. a.* List the employee numbers for your sample.
> a. What is a sample space? b. Is there anything random or uncertain about a sample space?
> What is the design phase of a statistical study?
> What is a joint probability table?
> a. What is the coefficient of variation? b. What are the measurement units of the coefficient of variation?
> If your data set is normally distributed, what proportion of the individuals do you expect to find: a. Within one standard deviation from the average? b. Within two standard deviations from the average? c. Within three standard deviations from the averag
> a. What is a deviation from the average? b. What is the average of all of the deviations?
> a. What is the traditional measure of variability? b. What other measures are also used?
> When a fixed number is added to each data value, what happens to a. The average, median, and mode? b. The standard deviation and range? c. The coefficient of variation?
> Which variability measure is most useful for comparing variability in two different situations, adjusting for the fact that the situations have very different average sizes? Justify your choice.
> What is variability?
> Do exercise 2 using the ages instead of the salaries. Data from exercise 2: Draw a random sample without replacement of 10 employees, using the table of random digits, starting in row 23, column 7. a.* List the employee numbers for your sample. b. Find
> What is the mode?
> How do you find the median for a data set: a. With an odd number of values? b. With an even number of values?
> What is statistics?
> What is the median? How can it be found from its rank?
> What is meant by a typical value for a list of numbers? Name three different ways of finding one.
> How should you deal with exceptions when summarizing a set of data?
> What is a box plot? What additional detail is often included in a box plot?
> What is the five-number summary?
> What are the quartiles?
> Name two ways in which percentiles are used.
> Continuing with the sample from the preceding exercise: a. Find the population mean for salary. (Note: In real life, you usually cannot find the population mean. We are peeking “behind the scenes” here.) b. Compare this population mean to the sample aver
> Which summary measure is best for a. A normal distribution? b. Projecting total amounts? c. A skewed distribution when totals are not important?
> Which summary measure(s) may be used on a. Nominal data? b. Ordinal data? c. Quantitative data?
> What is summarization of a data set? Why is it important?
> How should statistical analysis and business experience interact with each other?
> What is a skewed distribution?
> Are all data sets normally distributed?
> When a real data set is normally distributed, should you expect the histogram to be a perfectly smooth bell shaped curve? Why or why not?
> Why is the normal distribution important in statistics?
> What is a normal distribution?
> What is a number line?
> Draw a random sample without replacement of 10 employees, using the table of random digits, starting in row 23, column 7. a.* List the employee numbers for your sample. b. Find the average salary for yours sample and interpret this number. c. Find the st
> Suppose there is an outlier in your data. You plan to analyze the data twice: once with and once without the outlier. What result would you be most pleased with? Why?
> When is it appropriate to set aside an outlier and analyze only the rest of the data?
> What is an outlier?
> How can you interpret the logarithm of a number?
