1 / 26

STATISTICS: THE ART & SCIENCE OF LEARNING FROM DATA

STATISTICS: THE ART & SCIENCE OF LEARNING FROM DATA. Chapter 1. How can we evaluate evidence against global warming? Are cell phones dangerous? What are the chances of a tax return being audited? How likely are we to win the lottery? Is there bias against women in appointing managers?.

azriel
Download Presentation

STATISTICS: THE ART & SCIENCE OF LEARNING FROM DATA

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. STATISTICS: THE ART & SCIENCE OF LEARNING FROM DATA Chapter 1

  2. How can we evaluate evidence against global warming? Are cell phones dangerous? What are the chances of a tax return being audited? How likely are we to win the lottery? Is there bias against women in appointing managers?

  3. 1.1 How Can You Investigate Using Data?

  4. Data Data is information we gather through experiments and surveys. • Experiment on low carb diet • Data: weight of subjects before and after • Survey on effectiveness of a TV ad • Data: percentage who went to Starbucks since ad aired beanactivist.files.wordpress.com

  5. Statistics Statistics is the art and science of • Designing studies, • Analyzing data that those studies produce. The ultimate goal is to translate data into knowledge and understanding. Statistics is the art and science of learning from data.

  6. Three Aspects of a Study • Design: Planning how to obtain data • Description: Summarizing the data • Inference: Making decisions and predictions www.icts.uiowa.edu

  7. 1st Aspect of a Study: Design How do we conduct the experiment or select people for the survey to insure trustworthy results? Design Examples: • Planning data collection to study effects of Vitamin E on athletic strength • For a marketing survey, selecting people to provide proper coverage fineartamerica.com

  8. 2nd Aspect of a Study: Description Summarize raw data and present in useful formats (e.g., average, charts or graphs) Description Examples: • A graph showing total precipitation in Clarksville for each month of 2005 • Average age of students in a statistics class is 25 years www.emecogroup.org

  9. 3rd Aspect of a Study: Inference Make decisions or predictions based on the data Inference Examples: • Relationship between smoking cigarettes and getting emphysema • 47% of the registered voters in Illinois will vote in the primary Ladder of Inferencewww.reply-mc.com

  10. Activity 1 (Page 7) Go to http://sda.berkeley.edu/GSS Click on GSS - with 'no weight' as the default weight selection and choose the following Row Variables • TVHOURS • HAPPY

  11. 1.2 We Learn about Populations Using Samples

  12. Subjects Subjects - The entities that we measure in a study Subjects could be • individuals, • schools, • rats, • counties, • widgets Mr. Ages from the Rats of NIMH kiriko-moth.com

  13. Population and Samples • Population: All subjects of interest • Sample: Subset of the population for whom we have data • We observe samples, but we are interested in populations.

  14. Sample & Population for an Exit Poll In California in 2003, a special election was held to consider whether Governor Gray Davis should be recalled from office. • An exit poll sampled 3160 of the 8 million people who voted. Define the sample and the population for this exit poll. Itn.co.uk

  15. Descriptive vs. Inferential Statistics • Descriptive statistics summarize data – graphs and numbers such as averages and percentages • Inferential statistics make decisions or predictions about a population based on data obtained from a sample of that population. mallimages.mallfinder.com

  16. Descriptive Statistics Example Types of U.S. Households

  17. Inferential Statistics Example By surveying 1000 likely voters, we find 39% who approve of the job President Bush is doing. • We are 95% confident that the population proportion of likely voters who approve of the job President Bush is doing is between 36% and 42%. bigjournalism.com

  18. Sample Statistics & Population Parameters static.howstuffworks.com

  19. Randomness • Simple Random Sampling: each subject in the population has the same chance of being included in the sample • Randomness is crucial to insuring that the sample is representative of the population so that powerful inferences can be made www.nedarc.org

  20. Variability • Measurements may vary from subject to subject, and • Measurements may vary from sample to sample. Predictions are therefore likely to be more accurate for larger samples. www.pinguicula.org

  21. 1.3 What Role Do Computers Play in Statistics?

  22. What Role Do Computers Play in Statistics? • Data files - Large data sets organized in a spreadsheet format known as a data file • Each row contains measurements for a particular subject and column for a particular characteristic • Databases – An existing archive collection of data files Sources should always be checked for reliability. www.masternewmedia.org

  23. What Role Do Computers Play in Statistics? • Applets – A short application program for performing a specific task • Useful for performing activities that illustrate the ideas of statistics People, not technology, select valid analyses. www.atelier-us.com

  24. Activity 2 (Page 19) Choose the applet: sample from a population from the CD. Choose Binary: p = 0.5 for the population. Choose the sample button and experiment with various sample sizes.

More Related