Introduction to Data Collection
     Learning Targets
   After this lesson, you should be able to:
        Distinguish statistical questions from other types of 
          questions. 
        Identify the population and sample in a statistical study.
        Distinguish between an observational study and an 
          experiment.
Statistics and Probability with Applications, 3rd Edition             22
     Introduction to Data Collection
     A statistics problem starts with a statistical question. Not just 
     any question will do. 
     A valid statistical question is based on data that vary.
     That is, the answer to the question won’t be the same each 
     time an observation is recorded.
     How to Complete the Statistical Problem-Solving 
     How to Complete the Statistical Problem-Solving 
     Process
     Process
     •  Ask questions: Clarify the research problem and ask one 
     •  Ask questions: Clarify the research problem and ask one 
        or more valid statistical questions.
        or more valid statistical questions.
     •  Collect data: Design and carry out an appropriate plan 
     •  Collect data: Design and carry out an appropriate plan 
        to collect the data.
        to collect the data.
     •  Analyze data: Use appropriate graphical and numerical 
     •  Analyze data: Use appropriate graphical and numerical 
        methods to analyze the data.
        methods to analyze the data.
     •  Interpret results: Draw conclusions based on the data 
     •  Interpret results: Draw conclusions based on the data 
        analysis.
        analysis.
Statistics and Probability with Applications, 3rd Edition               33
     Video games, vanilla, and violence?
     Asking valid statistical questions
     PROBLEM: Determine if each of the following is a valid 
     statistical question. Justify your answer.
     (a) How many days did students at your school play video 
     games last week?
     Valid.  The answer to this question is based on data 
     that vary—the number of days that each student at 
     your school played video games.
     (b) Which gender is more likely to choose vanilla over 
     chocolate ice cream?
     Valid.  The answer to this question is based on data 
     that vary—whether each person would choose vanilla 
     over chocolate ice cream.
     (c) How many people in the United States were convicted of 
     violent crimes last year?
     Not valid.  This question can be answered with a single 
     value that doesn’t vary. 
Statistics and Probability with Applications, 3rd Edition               44
     Introduction to Data Collection
     Suppose we want to find out what percent of young drivers in 
     the United States text while driving. To answer the question, 
     we will survey 16- to 20-year-olds who live in the United States 
     and drive. Ideally, we would ask them all (take a census). But 
     contacting every driver in this age group wouldn’t be practical. 
     It would take too much time and cost too much money. 
     Instead, we put the question to a sample chosen to represent 
     the entire population of young drivers.
     Population, Census, and Sample
     Population, Census, and Sample
     •  The population in a statistical study is the entire group 
     •  The population in a statistical study is the entire group 
        of individuals we want information about.
        of individuals we want information about.
     •  A census collects data from every individual in the 
     •  A census collects data from every individual in the 
        population.
        population.
     •  A sample is a subset of individuals in the population from 
     •  A sample is a subset of individuals in the population from 
        which we collect data.
        which we collect data.
Statistics and Probability with Applications, 3rd Edition            55
     Introduction to Data Collection
          Population                         Collect data from a 
          Population
                                             representative Sample...
                        Sample
                        Sample
Statistics and Probability with Applications, 3rd Edition                  66