Quantitative Data Analysis Test Bank Docx Chapter.14

Chapter 14

1. Statistics used to describe the distribution and relationship among variables are:

a. Descriptive statistics.

b. Variability measures.

c. Measures of central tendency.

d. Inferential statistics.

2. When using _______ coding, a second person recodes a sample of the forms and then the percentage of agreement on all the items on the forms is computed.

a. Spot

b. Check

c. Procedure

d. Systemic

3. Coding refers to

a. The assignment of a number or numeral to represent the categories of a variable.

b. The assignment of a row in a data matrix to each questionnaire item.

c. The assignment of a number or numeral to each questionnaire item.

d. Transferring variables to the computer.

e. The assignment of a variable to a computer column.

4. A friend tells you that a codebook contained codes 1, 2, and 9 for the variable “religion.” You found a single code of 5 in the distribution on religion. You should:

a. Assume this is a random error and ignore it.

b. Do possible-code cleaning.

c. Do contingency cleaning.

d. Do some data analysis.

5. Certain guidelines should be kept in mind when coding. Among these is:

a. The coding scheme should be appropriate to the analysis intended in the study.

b. Data should be coded in somewhat more detail than the researcher intends to use in the analysis.

c. The reliability of the coder(s) should always be verified.

d. All of the above.

e. a and b only are correct.

6. The skewness of a data distribution can be

a. Right or left.

b. Positive or inverse.

c. Nominal or ordinal.

d. Ordinal or interval.

7. Data should be grouped in distributions in all of the following situations except:

a. There are more than 15–20 values on the variable to begin with.

b. There are too many categories to be displayed on an easily readable table.

c. The distribution will be clearer if some values are combined.

d. The values between categories are significantly different.

8. If a single frequency display presents a set of conceptually similar variables having the same response categories, it is called a:

a. Combined frequency display.

b. Frequency polygon.

c. Frequency distribution.

d. Compressed frequency display..

9. A unimodal distribution has:

a. No probability average.

b. A normal distribution.

c. A single most frequent value in the distribution.

d. 68 percent of the cases within one standard deviation from the mean.

10. To determine the approiateness of a particular statistic it is imporant to know which one of the following?

a. The frequency of its occurance in the population

b. The level of measurement

c. How the information was collected

d. The sample from whom the data were collected.

11. If the order of a variable’s categories is arbitracy, which of the following is used to summarize the central tendency of quantitative variables?

a. Mean

b. Mode

c. Median

d. Mean and Mode

12. Which of the following are used to summarize the central tendency of quantitative variables?

a. Mean and mode

b. Variance and range

c. Gamma and chi square

d. Median and mean

13. If the mean is greater than the median, which of the following must be true?

a. Variable is normally distributed.

b. Variable is measured at the ordinal level.

c. The variable’s distribution must be positively skewed.

d. The relationship between variables is inverse.

14. If the purpose of a statistic is to report the middle position in one or more distributions, which of the following is the appropriate statistic?

a. Mean

b. Median

c. Chi square

d. Pearson’s r

15. A standard deviation is the square root of the:

a. mean.

b. median.

c. range.

d. variance.

16. A scatterplot is used to display the relationship between ____ continuous variables.

a. Three

b. Six

c. Five

d. Two

17. A Type ___ error is influenced by the effect of the intervention or the strength of the relationship between an independent variable and a dependent variable.

a. I

b. II

c. III

d. IV

18. If r = 0, then:

a. The correlation is perfect.

b. The correlation is negative.

c. The correlation is normal.

d. There is no linear correlation.

19. Which of the following data displays would be most appropriate for displaying the distribution of gender (male, female, and other)?

a. Mean

b. Median

c. Bar chart

d. Frequency polygon

20. Which of the following data displays would be the most appropriate for displaying the distribution of the highest year of school completed?

a. Mean

b. Mode

c. Bar chart

d. Histogram

21. Which of the following is NOT a guideline for constructing graphs?

a. Begin the graph of a quantitative variable at zero on both axes.

b. Always use bars of equal width.

c. The two axes should be of approximately equal length.

d. When possible, use graphics instead of bars.

22. The total number cases in a distribution is called:

a. The base number N.

b. The range.

c. The row marginal.

d. The mode.

23. Which summary statistic should be used to answer the question, “What hobby is most common for college students today”?

a. Range

b. Variance

c. Mean

d. Mode

24. Scores on seven quizzes: 25, 23, 22, 17, 5, 42, 105. What is the median quiz score?

a. 22

b. 23

c. 5

d. 42

e. 17

25. Quiz scores: 25, 23, 22, 17, 46, 42, 105. What is the mean score?

a. 35.2

b. 40

c. 23

d. 30.5

e. 40.2

26. An alternative to the histogram, which is particularly useful for displaying variables with a wide range of values?

a. Bar chart

b. Pie chart

c. Categorical chart

d. Frequency polygon

27. In a normal curve, about what percent of all cases fall within plus or minus two standard deviations?

a. 10%

b. 25%

c. 50%

d. 95%

28. Which of the following is FALSE about standard deviations?

a. It tells how wide the variation of any set of cases is.

b. It is the square root of the variance.

c. It is the square root of the average squared deviation of each case from the mean.

d. It is a measure of central tendency.

29. Which of the following are statistical measures of variation:

a. Mean, median, and mode

b. Variance and standard deviation

c. Gamma and chi square

d. Highest and lowest value

For questions 30–32 refer to the following table: Drug use by educational level

EDUCATION LEVEL

DRUG USE Grade School High School+ Total

Yes 210 190 400

No 290 310 600

Total 500 500 1000

30. In this table, how many persons with at least a high school education use drugs?

a. 310

b. 400

c. 190

d. 500

e. 120

31. In this table, what percentage of persons uses drug users?

a. 40%

b. 42%

c. 50%

d. 60%

e. 38%

32. Descriptive statistics estimate the degree of confidence in generalizations made from a sampe to a population.

a. True

b. False

33. The median in a frequency distribution is determined by identifying the value corresponding to a cumulative percentage of 50.

a. True

b. False

34. Three features of a shape are important in a univariate distribution: mean, median, and mode.

a. True

b. False

35. The mean, median, and mode can all be used to describe any variable.

a. True

b. False

36. A frequency polygon displays a number and percentage of cases per cell in a table.

a. True

b. False

37. The mode is the most frequent value in a distribution.

a. True

b. False

38. In bar charts and histograms, bars should be of unequal width to facilitate comparing between categories.

a. True

b. False

39. The mode is the only appropriate measure of central tendency for nominal variables.

a. True

b. False

40. The median is the arithmetic average of the values on a given variable.

a. True

b. False

41. The median is not affected by the skewness of a variable’s distribution.

a. True

b. False

42. The mean is the most commonly used measure of central tendency for quantitative variables.

a. True

b. False

43. Range is computed by subtracting the highest value from the lowest value and adding one.

a. True

b. False

44. The interquartile range measures variability while avoiding problems created by outliers.

a. True

b. False

45. Level of measurement is essential to determine the appropriate statistical test.

a. True

b. False

46. In a normal distribution, about 68 percent of all cases will fall between plus or minus one standard deviations from the mean.

a. True

b. False

47. Type I error occurs when there is no evidence of a statistical relationship between two variables based on the sample, but in fact, the two variables are related.

a. True

b. False

48. An alpha level of .10 means that the researcher is willing to accept a 10% chance of concluding that there is a relationship between the variables in the sample when there is no relationship in the population.

a. True

b. False

49. Match the concept with the definition.

[e] 1. Mean

[c] 2. Median

[b] 3. Mode

[a] 4. Range

[d] 5. Standard deviation

a. The highest value in a distribution minus the lowest value plus one

b. The most frequent value in a distribution

c. The point that divides the distribution in half

d. The average squared deviation of each case from the mean

e. The arithmetic average of the distribution

50. Match the concept with the definition.

[d] 1. Bar chart

[a] 2. Histogram

[c] 3. Frequency polygon

[b] 4. Normal distribution

a. A distribution of adjacent bars

b. A bell-shaped distribution centered on the mean

c. A continuous line connecting points that represent the number or percentage of cases at each value

d. A distribution containing solid bars separated by spaces

51. Match the concept with the definition.

[b] 1. Body of the table

[e] 2. Cell

[c] 3. Marginals

[d] 4. Column

[a] 5. Base number (N)

a. The total number cases in the distribution

b. Part of table between row and column labels and row and column totals

c. Frequency distributions for independent and dependent variables

d. Typically divided into categories of the independent variable

e. Combinations of row and column values that represent unique combinations of values.

52. Match the cross-tabulation concept with the definition.

[d] 1. Existence

[a] 2. Strength

[c] 3. Direction

[b] 4. Patterm

a. The amount by which the percentage distributions vary between categories of the independent variable

b. A bell-shaped distribution centered on the mean

c. When values on the dependent variable tend to increase or decrease with an increase in value on the independent variable

d. There is a pattern of percentage distributions that vary between categories of the dependent variable

53. Why is it important to assign a unique identifying number to each respondent?

This allows you to check if there are coding mistakes, you can go back to the original form to find the correct response. It allows you to match respondents over time.

54. Describe circumstances in which mean, median, and mode are best used as measures of central tendency, providing at least two concrete examples for each.

The mode should be used to measure the central tendency of variables measured at the nominal level (and it can also be used to measure the central tendency of variables measured at the ordinal, interval, and ratio levels). The median is most suited to measure the central tendency of variables measured at the ordinal level (and it can also be used to measure the central tendency of variables measured at the interval and ratio levels). The mean is only suited to measure central tendency for variables measured at the interval and ratio levels.

55. Discuss the problems you may encounter as you review instruments/questionnaires from a survey you administered.

Responses that are not clearly indicated; unexpected responses; respondents misreading instructions; and incomplete questionnaires.

56. Compare and contrast Type I and Type II errors.

Type I errors threaten our ability to conclude that there is an association. Type I error is easy to calculate as it is equal to the alpha level you chose as a criterion for statistical significance or the p value produced as part of an analysis computed by statistical software. A Type II error is committed when we have concluded that there is no relationship based on our one sample, but in fact there is a relationship between the two variables in the population we sampled.

57. What are the problems that occur when comparisons are made across ethnic groups?

Ann Kathleen Burlew and her colleagues (2009) note the following limitations with race group comparisons: It ignores within-group differences for each ethnic group. Such a strategy assumes that each group is homogeneous, yet this is not the case. Both the presence and absence of mean score group differences may lead to wrong conclusions. The absence of group differences may lead to the premature combining of the groups; there may be relationships to other variables that might be missed. The presence of mean score differences may lead the researcher to attribute too much meaning to the finding and may contribute to ethnic stereotyping. The results may be misleading if the measures are not equivalent for each group. Intervention research samples tend to be convenience samples and therefore may not be representative of the broader population. Participants in treatment studies may differ from nonparticipants with the same presenting problem.

58. Compare and contrast a bar chart, histogram, and frequency polygon.

A bar chart contains solid bars separated by spaces. It is a good tool for displaying the distribution of varimeasured at the nominal level and other discrete categorical variables because there is, in effect, a gap between each of the categories. Histograms, in which the bars are adjacent, are used to display the distribution of quantitative variables that vary along a continuum that has no necessary gaps. In a frequency polygon, a continuous line connects the points representing the number or percentage of cases with each value. The frequency polygon is an alternative to the histogram when the distribution of a quantitative continuous variable must be displayed; this alternative is particularly useful when the variable has a wide range of values.

cases, it is not affected in any way by extreme values. Because the mean is based on adding the value of all the cases, it will be pulled in the direction of exceptionally high (or low) values. When the value of the mean is larger than the median, we know that the distribution is skewed in a positive direction, with proportionately more cases with higher than lower values. When the mean is smaller than the median, the distribution is skewed in a negative direction. The single most important influence on the choice of the median or the mean should be the purpose of the statistical summary. If the purpose is to report the middle position in one or more distributions, then the median is the appropriate statistic regardless of whether the distribution is skewed.

59. Why is a variable’s level of measurement important in determining the appropriate descriptive statistics, graphs, and bivariate statistics? Provide examples to describe the nature of the problem.

The level of measurement dictates the appropriate measure. Examples vary.