Samples_ Good and Bad

							Samples, Good and Bad



          STA 200
          Chapter 2
How Can You Goof Up Sampling?

 Bias
    Geographical
    Generational
    Informational
    Financial
    There’s More!
Biased Sampling Methods

   Bias
    –   Systematically favors certain outcomes
   Convenience Sampling
    –   Interviewer selects most reachable individuals
   Voluntary Response Sample
    –   Individuals choose themselves
Example
             GLAMOUR asked readers
              who said “I love you” first? Of
              the 200 coupled respondents:
             63% said he did
             37% said she did
Simple Random Sampling
   Personal choice produces bias
   Impersonal chance chooses the sample
   All individuals and every possible sample
    have an equal chance
   Sample size is n
Random Digits

   A table of random digits is a list of the digits
    0, 1, 2, 3, 4, 5, 6, 7, 8, 9 that has the following
    properties:
      1.   The digit in any position in the list has the same chance
           of being any one of 0 – 9
      2.   The digits in different positions are independent in the
           sense that the value of one has no influence on the value
           of any other.
Choosing an SRS

  Let’s find a sample of 5 from this class
Line 101: 19223 95034 05756 28713 96409
            12531 42544 82853

Line 101: 19223 95034 05756 28713 96409
           12531 42544 82853
Choose Another SRS

Let’s find a sample of 5 from this class
Line 116: 14459 26056 31424 80371 65103
           62253 50490 61181

Line 116: 14459 26056 31424 80371 65103
          62253 50490 61181
 Notice that this is different from before!
Kentucky Crime Survey
   About 18,000 Kentucky residents will be asked their
    views on crime and punishment to help come up with
    recommendations to improve the state’s criminal
    justice system.
   The survey will mail questionnaires to a random
    statewide sample.
   Questions will deal with attitudes regarding
    punishment, fear of crime, victimization within the past
    year, and how well the criminal justice system is
    working.
    Americans Still Prefer Boys

   If Americans could only have one child:

   42% say they would prefer a boy
   27% say they would prefer a girl
   25% say it would not matter to them either way

   The results are based on telephone interviews with a
    randomly selected national sample of 1,026 adults, 18 years
    and older, conducted December 2-4, 2000.
Homework

   Suggested Chapter 2 Problems: 2 & 8
   Read Chapter 3