Transcript Chapter 0: Getting Started

Basic Practice of
Statistics
7th Edition
Lecture PowerPoint Slides
In chapter 0 we cover …
 Where the data come from matters
 Always look at the data
 Variation is everywhere
 What lies ahead
Getting started
 Does Soundscan know what’s hot in popular
music?
 Is hormone therapy appropriate after
menopause?
 What are the extent, cause, and possible
solutions to global climate change?
Statistics is the science of learning from data.
Data are numbers, but …
“Congratulations, your baby weighs 8.5!”
 8.5 what? Kilograms? That’s a BIG baby!
 Data are numbers with a context.
 Likewise, we will use our human judgment to
guide our use of statistical tools, such as graphs
and calculations.
Where the data come from
matters
 Observational studies versus experiments
 Early hormone replacement studies:
observational. Challenge: lurking variables,
such as education and affluence of patients
 Later, definitive studies: experiments, decided no
reduction in heart attack risk due to therapy
 Just one example of complex relationship
between variables being oversimplified
Always look at the data
 Example graph:
 A few carefully chosen graphs are often more
instructive than great piles of numbers.
Just ALWAYS do
experiments?
 Can’t.
 Isn’t always necessary: well-designed
observational studies, such as sample surveys,
can yield high-quality information
 Well-designed ≠ large number of respondents,
necessarily
 Example: Ann Landers’ reader survey
Variation is everywhere
 Gas prices, June 1990 to August 2013:
4.50
Gasoline price (dollars per gallon)
4.00
High demand,
Middle East unrest,
dollar loses value
3.50
3.00
2.50
Gulf oil
spill
2.00
Gulf War
1.50
September 11
attacks world
economy slumps
1.00
90 9 1 92 93 94 95 96 97 98 99 00 0 1 02 0 3 04 05 06 0 7 08 09 1 0 11 12 1 3 14
1 9 1 9 1 9 1 9 1 9 19 1 9 19 19 1 9 20 20 2 0 20 20 2 0 20 20 2 0 20 20 2 0 2 0 20 2 0
Year
Because variation is
everywhere,
 Conclusions are uncertain.
 Example: efficiency of HPV vaccine
“was 98% (95 percent confidence interval 86% to
100%).”
 Truth? It’s in there … or not …
 Variability is inescapable.
What lies ahead
 Purpose: give a working knowledge of the ideas
and tools of practical statistics.
Three main areas:
 Data analysis (Chapters 1–6)
 Data production (Chapters 8 and 9)
 Statistical inference (Chapters 13–18, 20–27)
Doing statistics is …
 More than manipulating numbers!
You must:
 State a problem in its real-world context,
 Plan your specific statistical work in detail,
 Solve the problem by making the necessary
graphs and calculations, and
 Conclude by explaining what your findings say
about the real-world setting.