Section outline

  • General

    Collapse all Expand all

  • 非概率抽样

    Suppose your friend were to tell you “candy is sweet.”  You would probably accept the statement without argument, since we generally think of candy as almost a synonym for sweet in the U.S. However, if you wanted to prove the claim wrong and demonstrate that candy is not always sweet, you could conduct an experiment to see if candy is sometimes not sweet.
    ::假设你的朋友会告诉你“糖果是甜的 ” 。 你可能会接受这种说法而没有争论,因为我们一般认为糖果在美国几乎是甜的同义词。 然而,如果你想证明这种说法是错误的,并证明糖果并不总是甜的,你可以进行实验,看看糖果有时是不是甜的。

    Given the practically limitless different types of candy, how could you collect a useable sample if you can’t possibly give each and every type of candy an equal chance of being a part of a random selection?
    ::如何收集有用的样本? 如果不能给每一种糖果同等的机会成为随机选择的一部分,

    Non-Probability Sampling 
    ::非概率抽样

    There are a number of recognized non-probability sampling methods, including:
    ::有一些公认的非概率抽样方法,包括:

    • Convenience Sampling – Choosing samples based on easy or convenient access
      ::便利度抽样——根据方便或方便的取用选择样本
    • Volunteer (or Snowball) Sampling – Asking for volunteers or for recommendations from other samples
      ::志愿者(或雪球)抽样 — — 询问志愿者或其他样本的建议
    • Judgment Sampling – Deliberately choosing samples based on a desired characteristic
      ::抽样调查 - 故意根据期望的特征选择样本
    • Quota Sampling – Choosing samples to fill a specific quota of each of several sup-populations of the original
      ::配额抽样 — 选择样本,以填充最初几个人口组别中每个组别的具体配额。

    Some studies do not lend themselves to the collection of a randomized sample.  Although a random sample is necessary if the goal is to directly generalize results back to an entire population , sometimes that isn’t the purpose of the study.
    ::有些研究不适于收集随机抽样。 尽管随机抽样是必要的,但目标是将结果直接推广到整个人口,有时这不是研究的目的。

    Common situations where non-probability sampling may be appropriate include:
    ::非概率抽样可能适当的常见情况包括:

    1. Qualitative Research – Studies with the general goal of identifying topics worthy of future more detailed (quantitative) study
      ::定性研究 -- -- 研究的总目标是确定值得今后进行更详细(定量)研究的专题
    2. Studies particularly focused on specific portions of large population
      ::特别以人口众多的特定部分为重点的研究
    3. Studies with limited funding and/or time
      ::资金和/或时间有限的研究
    4. Studies with a goal of either disproving a particular theory, or of demonstrating the existence of a specific trait in a population.
      ::研究的目的不是否定某一特定理论,就是证明人口中存在特定特征。

    Determining Sampling Method Used 
    ::确定所用抽样方法

    A toy designer is looking to develop the next ‘big thing’ in toys for young children.  A brainstorming session results in 15 possible new ideas across a wide range of types from puzzles to remote-controlled chickens.  A full-scale prototype development and testing for each idea would not be cost effective, so the company decides to perform a preliminary study.  One of the employees suggests drawing sketches of the ideas and taking them to his son’s daycare to see which pictures get the most attention from the kids there.
    ::玩具设计师正在寻找为幼儿开发下一个玩具中的“大东西 ” 。 集思广益会产生了15种可能的新想法,从谜题到遥控鸡等多种类型。 每个想法的全面原型开发和测试不会具有成本效益,因此公司决定进行初步研究。 其中一位雇员建议绘制这些想法的草图,并带他们去他儿子的日间护理,看看那里孩子对哪些图片的关注最大。

    What kind of sampling is this?  Is it an appropriate choice for the application?
    ::这算什么取样?

    lesson content

    Solution:   As a preliminary data collection resource, this convenience sampling of kids is a reasonable choice.  Once the suggestions have been narrowed down a bit by judging the responses of the day-care kids, a more conventional random sampling may be used to pick out a specific design or two and then further refine it.
    ::解决方案:作为初步的数据收集资源,这种方便儿童抽样是一种合理的选择。 一旦通过判断日托儿童的反应来缩小建议的范围,就可以使用更常规的随机抽样来选择具体设计或两个,然后进一步完善。

    Choosing the Most Appropriate Sampling Method 
    ::选择最适当的抽样方法

    You are trying to convince your teacher that listening to music while doing homework improves scores.  You decide to conduct a study of the effects of listening to music while doing homework and correlate it to student scores. Since your hypothesis is that listening to music improves scores on homework, would it be most effective to select a random sample of all the students in your school?  If not, what type of non-probability sampling would be most appropriate and why?
    ::你试图说服你的老师,在做功课时听音乐会提高分数。你决定在做功课时研究听音乐的效果,并将其与学生分数联系起来。既然你的假设是听音乐会提高功课成绩,那么随机抽取学校所有学生的分数是否最为有效?如果没有,哪种非概率抽样最合适,原因何在?

    If you are trying to find out if listening to music affects homework scores, then you would want a random selection of the entire population.  However, since your very specific goal is to demonstrate music being associated with high scores, you might want to take a judgment sample of only students who listen to music while doing homework, and have high scores.
    ::如果您试图找出听音乐是否影响功课成绩, 那么您会想要随机选择全部人口。 但是,由于您的特殊目标是展示音乐与高分相关联, 您可能想要对做功课时只听音乐的学生进行判断抽样, 并获得高分。

    Finding Missing Values 
    ::查找缺失价值

    The student council at Cedar Valley Public School wants to gauge student opinion on the quality of their extracurricular activities. They decide to survey approximately 150 of the school’s 1,000 students using the grade levels (7 to 12) as the sub-population.
    ::Cedar Valley 公立学校的学生理事会想评估学生对其课外活动质量的意见,他们决定用年级(7-12)作为亚人口调查学校1000名学生中大约150名学生。

    The table below gives the number of students in each grade level.  Fill in the missing values for the number of students that should be in the sample from each grade level.
    ::下表列出每个年级的学生人数,填写每个年级抽样中学生人数的缺失值。

    Grade level Number of students enrolled Percentage of students (%) Quota of students in sample of 150
    7 150    
    8 220 22  
    9 160    
    10 150 15  
    11 200    
    12 120 12  
    Total 1,000 100 150

    First fill in the missing percentages by dividing the number of students in each grade by the total number of students in the school:
    ::将每一年级的学生人数除以在校学生总数,从而首先填补缺失的百分比:

    Grade 7 : 150   s t u d e n t s 1000   s t u d e n t s = 15 % Grade 9 : 160   s t u d e n t s 1000   s t u d e n t s = 16 % Grade 11 : 200   s t u d e n t s 1000   s t u d e n t s = 20 %

    ::7:150名学生1000名学生=15% 9:160名学生1000名学生=16% 11:200学生1000名学生=20%

    Now apply each grade’s percentage of enrollment to the sample size of 150:
    ::现在将每个年级的入学率百分比适用于150个样本的抽样规模:

    • Grade 7 sample should contain 15% of 150 or 22.5 students, rounded up to 23 students
      ::7年级抽样应包含150名学生或22.5名学生的15%或22.5名学生,四舍五入至23名学生。
    • Grade 8 sample should contain 22% of 150  or 33 students
      ::8年级抽样应占150名或33名学生的22%
    • Grade 9 sample should contain 16% of 150  or 24 students
      ::9年级抽样应占150或24名学生的16%
    • Grade 10 sample should contain 15% of 150  or 22.5 students, rounded up to 23 students
      ::10年级抽样应包含150名学生或22.5名学生中的15%或22.5名学生,四舍五入至23名学生。
    • Grade 11 sample should contain 20% of 150  or 30 students
      ::在150名或30名学生中,11年级抽样应占20%
    • Grade 12 sample should contain 12% of 150 students or 18 students
      ::12年级抽样应包括150名学生中12%的学生1818年级学生

    Earlier  Problem Revisited
    ::重审先前的问题

    It is commonly accepted that any survey conducted by mail, or over the internet, or by telephone will have a very low response rate .  It is not unheard of for such surveys to have less than 5% of the chosen sample actually return usable results.
    ::人们普遍认为,通过邮件、互联网或电话进行的任何调查的回复率都很低。 这种调查只有不到所选抽样的5%实际返回了可用结果,这是众所周知的。

    It certainly seems logical to attempt to get a response rate as high as possible, but does a low response mean that the experiment is invalid?
    ::试图获得尽可能高的回复率似乎是符合逻辑的,但低的回复率是否意味着实验无效?

    No, it doesn’t.  Certainly a very low response rate should be investigated, but the more important consideration is how well the results actually collected represent a random sampling of the population under study.
    ::当然,应该调查一个非常低的回复率,但更重要的考虑是,实际收集的结果在多大程度上代表了所研究人口的随机抽样。

    Examples 
    ::实例

    Example 1
    ::例1

    Your mom says that sticking your tongue out every day will cause your face to get stuck that way.  Would a non-probability sample be appropriate for a study attempting to prove that hypothesis wrong?  What type would you recommend, and why?
    ::你妈妈说,每天伸出舌头会让你的脸被卡住。 一个非概率样本是否适合用来进行一项研究,试图证明这一假设是错误的? 你会建议哪种类型,为什么?

    This is actually an appropriate use of convenience sample. According to the hypothesis "...will cause it to get stuck", all you need is one example of it not getting stuck to disprove the statement. Since any example will work, you might as well try easy possibilities first.
    ::事实上,这是对方便抽样的适当利用。根据假设“...会让它卡住”,你所需要的只是一个不会被卡住来反驳声明的例子。因为任何例子都会有效,你最好先尝试简单的可能性。

    Example 2
    ::例2

    Would a non-probability sample be appropriate for a study attempting to show that brand-name band-aids are superior?  Which type would be appropriate and why?
    ::一种非概率抽样是否适合进行一项研究,试图表明品牌名带状标志优异?哪种类型合适,为什么合适?

    No. Here you are hoping to generalize from your sample to the whole population of band-aid users. Extrapolation requires a true random sample.
    ::否。 您希望从样本中将样本推广到所有带状援助使用者。 外推需要真正的随机样本 。

    Example 3
    ::例3

    How would a Snowball sampling method apply to a study of which flavor of gum has the longest-lasting flavor?
    ::雪球取样方法如何适用于研究哪种口香糖的口香糖口味最耐久?

    Here your study is actually on gum rather than the chewer, so asking friends to ask friends what gum they have found has the longest flavor would be convenient and appropriate
    ::在这里,你的研究实际上是在口香糖而不是咀嚼器上, 所以请朋友问朋友他们找到什么口香糖有最长的口香糖口味会方便而合适

    Example 4
    ::例4

    Would a non-probability sample be a good choice if you want to run a study to see if people who wear glasses are the best students? What type of sample would you recommend and why?
    ::非概率抽样是否是一个好选择,如果你想进行一项研究,看看戴眼镜的人是否是最好的学生?你会推荐哪种样本以及为什么?

    A judgment sample of the best students to see if they wear glasses would be a more efficient way to test your hypothesis than just a random sample of all students or all glasses-wearers.
    ::最佳学生的判断样本 看看他们是否戴眼镜 将是一个更有效率的方法 测试你的假设 而不是仅仅随机抽样 所有学生 或所有戴眼镜的人。

    Review 
    ::回顾

    1. A marketing company offers $75.00 to the first 100 people who respond to their advertisement in a magazine and complete a questionnaire. This situation is an example of:
    ::1. 一家营销公司向在杂志上对其广告作出答复并填写调查问卷的第一批100人提供75.00美元。

    a. simple random sample
    ::a. 简单随机抽样

    b. convenience sample
    ::b. 方便抽样

    c. voluntary response sample
    ::c. 自愿答复抽样

    d. multistage cluster sample
    ::d. 多阶段集群抽样

    The marketing class at a local high school wants to conduct a survey of the opinions of 60 students. Identify each type of sampling method they might use listed below.
    ::当地一所高中的营销班希望对60名学生的意见进行调查,确定他们可能使用的每一种抽样方法,如下表所示。

    2. Survey the first 60 students to walk through the doors at school in the morning.
    ::2. 调查每天早上在学校走出大门的第一批60名学生。

    3. Marketing class members each ask a friend for his/her opinion, and for the names of 3 other students to ask also.
    ::3. 营销班成员各自向朋友征求自己的意见,并要求另外3名学生的名字也征求朋友的意见。

    4. Class members discuss who would be most appropriate to survey based on the results they want, then choose those persons.
    ::4. 班级成员讨论谁最适合根据他们想要的结果进行调查,然后选择这些人。

    5. Marketing class members decide to split students up into groups based on color of clothing, then choose a sample with the same ratio of colors as the whole school.
    ::5. 营销班成员决定根据着装颜色将学生分成若干组,然后选择一个与整个学校相同的颜色比例的样本。

    6. Number the students in the official school roster. Use a table of random numbers to choose 60 students from this roster for the survey.
    ::6. 正式学校名册上的学生人数:使用随机数字表从名册上挑选60名学生参加调查。

    7. A researcher plans a study to examine the depth of belief in an afterlife among the adult population of a small town. He obtains a simple random sample of 100 adults as they leave church one Sunday morning. All but one of them agree to participate in the survey. Which of the following is a true statement?
    ::7. 一位研究人员计划进行一项研究,研究一个小城镇成年人口对后世信仰的深度,他在一个星期天早上离开教堂时获得100名成人的简单随机抽样,除其中一人外,所有人都同意参加调查。

    a. Proper use of chance as evidenced by the simple random sample makes this a well-designed survey.
    ::a. 以简单随机抽样为证明的正确利用机会使这一调查成为设计周密的调查。

    b. The high response rate makes this a well-designed survey.
    ::b. 由于答复率高,因此这是设计良好的调查。

    c. Selection bias makes this a poorly designed survey
    ::c. 选择偏差使得这一调查设计不当

    d. None of these statements is true.
    ::d. 这些说法都不属实。

    8. Do any of the following use simple random sampling?
    ::8. 下列任何一种方法是否使用简单的随机抽样?

    a. Bingo game
    ::a. 游戏游戏游戏

    b. Presidential elections
    ::b. 总统选举

    c. US Census
    ::c. 美国人口普查

    Identify the type or types of sampling used for the following.
    ::确定用于以下目的的取样类型或类型。

    9. Sarah went through a telephone directory and called every person with a name she liked.
    ::9. Sarah通过一个电话簿,给每一个她喜欢的名字的人打电话。

    10. Four people divided a telephone directory evenly and each called the first 10 numbers they found.
    ::10. 4人平分一个电话簿,每个号码都打头10个号码。

    11. Every  5 t h block of 10 students walking past the classroom where the surveyors are working is exhaustively sampled about their faith in opinion polls.
    ::11. 每五个街区有10名学生通过测量员所在的教室,就对他们对民意测验的信心进行详尽无遗的抽样调查。

    Describe possible weaknesses of each of the following sampling procedures:
    ::描述下列每一取样程序可能存在的弱点:

    12. A sample of size 200 from a population of corporate personnel were asked to give their opinion about the federal government’s affirmative action hiring program. Ninety-three percent expressed opposition to the program.
    ::12. 要求来自公司人员人口的200号样本对联邦政府的平权行动雇用计划发表意见。 93%的人表示反对该计划。

    13. A TV show takes a survey by asking individuals to call in to identify whether they are ‘FOR’ or ‘AGAINST’ more restrictions on gun control.
    ::13. 电视节目通过要求个人打电话查明他们是否对枪支管制有 " 支持 " 或 " 支持 " 或 " 支持 " 更多限制来进行调查。

    14. We are interested in obtaining a sample representative of all males age 18 or older. We run an advertisement on the Internet, ask for volunteers, and then choose a random sample from the list of people who volunteer.
    ::14. 我们有兴趣获得18岁或18岁以上的所有男性的抽样代表,我们在因特网上刊登广告,要求志愿者,然后从自愿者名单中随机抽取样本。

    Review (Answers)
    ::回顾(答复)

    Click to see the answer key or go to the Table of Contents and click on the Answer Key under the 'Other Versions' option.
    ::单击可查看答题键, 或转到目录中, 单击“ 其他版本” 选项下的答题键 。