2.8 Review Questions

  1. In 2004, the mean net worth of families in the United States was $448.2 thousand and the median net worth was $93.1 thousand. Which measure of center do you think is more appropriate? Explain your answer.
  2. Wayne Gretzky, a retired professional hockey player, played 20 seasons in the National Hockey League (NHL) from 1980 through 1999. The number of games in which Gretzky played during each of his 20 seasons in the NHL are as follows: 74, 80, 73, 78, 78, 45, 80, 79, 79, 80, 48, 64, 80, 70, 80, 74, 82, 81, 80, 82.
    1. Find the mean, median, mode of these 20 numbers. Interpret the three measures for the center.
    2. Find the quartiles of the data and interpret.
    3. Find the range, interquartile range, sample standard deviation of the data and interpret.
    4. Find the five-number summary of the data and draw a boxplot of these 20 numbers. Comment on the resulting boxplot.
    5. Choose proper measures for the center and spread (variation) of the distribution. Justify your answer.
  3. The following table gives the salaries (in thousand dollars) for physics and computer science (CS) majors obtaining a bachelor’s degree, a master’s degree or a PhD.
    1. What can we tell from the side-by-side boxplot comparing the salaries of computer science (CS) and physics majors, the one on the left?
    2. What can we tell from the side-by-side boxplot comparing the salaries of Bachelor, Master and PhD, the one on the right?
    3. What can we tell from the side-by-side boxplot comparing the salaries of combinations of ”Major” and ”Degree”?
      SALARY MAJOR DEGREE
      51.9 Physics Bach
      58.2 Physics Bach
      49.9 Physics Bach
      50.6 Physics Bach
      51.4 Physics Bach
      43.7 Physics Bach
      52.9 Physics Bach
      59.2 Physics Master
      60.5 Physics Master
      57.1 Physics Master
      59.1 Physics Master
      54.9 Physics Master
      61.7 Physics Master
      62.4 Physics Master
      78.2 Physics PhD
      69.6 Physics PhD
      70.5 Physics PhD
      73.2 Physics PhD
      81.7 Physics PhD
      74.8 Physics PhD
      69.8 Physics PhD
      SALARY MAJOR DEGREE
      50.8 CS Bach
      59.4 CS Bach
      55.9 CS Bach
      45.1 CS Bach
      54.1 CS Bach
      50.7 CS Bach
      46.8 CS Bach
      65.8 CS Master
      57.5 CS Master
      66.9 CS Master
      62.8 CS Master
      68.5 CS Master
      69.3 CS Master
      61.5 CS Master
      73.3 CS PhD
      65.7 CS PhD
      71.7 CS PhD
      72.5 CS PhD
      73.0 CS PhD
      67.2 CS PhD
      67.5 CS PhD
  4. The z-score corresponding to an observed value of a variable tells you ____________________ .
  5. A positive z-score indicates that the observation is ______________  the mean, whereas a negative z-score indicates that the observation is ______________  the mean.
  6. Suppose that you obtained 350 points in an exam. The exam has 400 possible points, the mean score is 280 and the standard deviation is 20. Did you do well on the exam? Explain your answer.
  7. Each year, thousands of high school students bound for college take the Scholastic Assessment Test (SAT). This test measures the verbal and mathematical abilities of prospective college students. Student scores are reported on a scale that ranges from a low of 200 to a high of 800. In one high school graduating class, the mean SAT math score is 528 with a standard deviation of 105; the mean SAT verbal score is 475 with a standard deviation of 98. A student in the graduating class scored 740 on the SAT math and 715 on the SAT verbal. Compared to the other students in the graduating class, on which test did the student do better?
Show/Hide Answer
  1. Since the mean is much larger than the median, the distribution is extremely right skewed. It is more appropriate to use the median to describe the center.
    1. The sum of the data is [latex]\sum x_i = 1487[/latex]  and the sum of squares of the data is [latex]\sum x_i^2 = 112665[/latex]. Therefore, sample mean [latex]\bar x=\frac{\sum x_i}{n}=\frac{1487}{20}=74.35[/latex]. Arrange the data from smallest to largest: 45 48 64 70 73 74 74 78 78 79 79 80 80 80 80 80 80 81 82 82.
      Sample size n = 20, median is [latex]\frac{79+79}{2}=79[/latex]. The mode is 80.
      Interpretation: 50% of observations are below 70 and another 50% are above 79 (the median); the average of the observation is 74.35 (the mean); the observation occurs most often is 80 (the mode).
    2. The first half: 45 48 64 70 73 74 74 78 78 79, [latex]Q_1=\frac{73+74}{2}=73.5[/latex], Q2 = 79. The second half: 79 80 80 80  80 80  80 81 82 82, [latex]Q_3=\frac{80+80}{2}=80[/latex]. Therefore, the quartiles are Q1 = 73.5, Q2 = 79, Q3 = 80.
      Interpretation: the bottom 25% of observations are below 73.5, 25% are between 73.5 and 79, 25% are between 79 and 80, the top 25% are above 80.
    3. Range=Max-min=82-45=37. IQR=Q3 − Q1 = 80 − 73.5 = 6.5.
      [latex]s=\sqrt{\frac{\sum x^2-\frac{(\sum x)^2}{n}}{n-1}}=\sqrt{\frac{112665-\frac{1487^2}{20}}{20-1}}=10.5295.[/latex]
      Interpretation: the data spread over an interval of length 37 (range); the middle 50% of the observations spread over an interval of length 6.5 (IQR); roughly speaking, the average distance from the observations to the sample mean 74.35 is 10.5295 (standard deviation).
    4. The 5-number summaries are min = 45, Q1 = 73.5, Q2 = 79, Q3, max = 82. The distribution is left-skewed with two outliers at the lower end.
    5. Use median for the center and IQR for the spread (variation) since outliers exist.
    1. CS majors have a higher median salary. Physics majors have a larger variation in salary. The distribution for CS majors is left skewed; while the distribution for physic majors is right skewed.
    2. The median salary for PhD is higher than master, and master is higher than bachelor. Salary for master has a larger IQR than the other two groups. The variations for PhD and bachelor are similar.
    3. For PhD and bachelor, physics majors have a slightly higher median; for master, however, CS majors have a higher median salary than physics. The variation is similar for CS majors at the three different education level; the variations in salary increase for physics majors when the education level increases.
  2. how far the observation is away from the mean in units of standard deviation.
  3. A positive z-score indicates that the observation is above the mean, whereas a negative z-score indicates that the observation is below the mean.
  4. The z-score is [latex]z=\frac{350-280}{20}=3.5[/latex]. You did extremely well since you are 3.5 standard deviations above the mean. Most x-scores are between -3 and 3.
  5. The z-score for math is: [latex]z_1=\frac{740-528}{105}=2.02[/latex]. The z-score for verbal is [latex]z_2=\frac{715-475}{98}=2.45[/latex]. The student did better in verbal, since it has a larger z-score.

License

Icon for the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

Introduction to Applied Statistics Copyright © 2024 by Wanhua Su is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License, except where otherwise noted.