Election News and Numbers Making sense of polls, statistics and more for the 2008 election!

Slides:



Advertisements
Similar presentations
What to believe What not to believe.  Traditional public opinion polls  Determine the content phrasing the questions  Selecting the sample  Random.
Advertisements

Mean, Proportion, CLT Bootstrap
Chapter 8: Mass Media and Public Opinion Section 2
Chapter 8b Sample size for an interval estimate of a population mean.
1. Exams 2. Sampling Distributions 3. Estimation + Confidence Intervals.
Newsroom math Prof. Steve Doig Cronkite School, ASU.
Confidence Intervals with proportions a. k. a
INFERENTIAL STATISTICS  Samples are only estimates of the population  Sample statistics will be slightly off from the true values of its population’s.
Beginning the Research Design
Decide whether each sampling method is likely to result in a biased
Determining the Size of a Sample
Determining the Size of
INFERENTIAL STATISTICS – Samples are only estimates of the population – Sample statistics will be slightly off from the true values of its population’s.
How We Form Political Opinions Political Opinions Personal Beliefs Political Knowledge Cues From Leaders.
Sampling Distributions
The American Political Landscape: Demographics and political predispositions 1.Sectionalism 2.Race/Ethnicity 3.Gender 4.Income 5.Education.
Chapter 9: Mathematics of Finance
Business Communications & Presentations.  Numbers are so much a part of your life that you probably pay little attention to them:  “The unemployment.
Today’s Agenda Any Announcements? Any Questions? Let's Review our Bellwork.... Now... Let’s Begin Today’s Lesson…..
Announcements… The end of the quarter is this Friday ▫Check your grades online ▫Turn in any missing assignments Quiz Friday--Voting ▫Expect a study guide.
C1, L2, S1 Design Method of Data Collection Surveys and Polls Experimentation Observational Studies.
THE WHO AND HOW. Opinion Polling. Who does polling? News organizations like CNN, Fox News, ABC, and NBC. Polling organizations like Rasmussen, Gallup,
Copyright © 2009 Pearson Education, Inc. Publishing as Longman. The 1936 Literary Digest Presidential Election Poll Case Study: Special Topic Lecture Chapter.
Ch 8 Estimating with Confidence. Today’s Objectives ✓ I can interpret a confidence level. ✓ I can interpret a confidence interval in context. ✓ I can.
8.2 Estimating Population Means LEARNING GOAL Learn to estimate population means and compute the associated margins of error and confidence intervals.
Chapter Twelve Census: Population canvass - not really a “sample” Asking the entire population Budget Available: A valid factor – how much can we.
About the Poll The Washington Poll is a non-partisan, academic survey research project sponsored the University of Washington Department of Political Science.
+ The Practice of Statistics, 4 th edition – For AP* STARNES, YATES, MOORE Chapter 8: Estimating with Confidence Section 8.1 Confidence Intervals: The.
Ch 8 Estimating with Confidence. Today’s Objectives ✓ I can interpret a confidence level. ✓ I can interpret a confidence interval in context. ✓ I can.
Surveys and Questionnaires Government agencies, news organizations, and marketing companies often conduct surveys. The results can be factual or subjective.
American Government and Politics Today Chapter 6 Public Opinion and Political Socialization.
Chapter 11 Political Socialization and Public Opinion Pearson Education, Inc. © 2008 American Government: Continuity and Change 9th Edition to accompany.
CONFIDENCE INTERVALS Feb. 18 th, A STATS PROFESSOR ASKED HER STUDENTS WHETHER OR NOT THEY WERE REGISTERED TO VOTE. IN A SAMPLE OF 50 OF HER STUDENTS.
Public Opinion Polls What is public opinion?. Public Opinion Polls take the pulse of America regarding many different issues. They are also predictors.
Statistical Inference: Making conclusions about the population from sample data.
Chapter 8 Quantitative Data Analysis. Meaningful Information Quantitative Analysis Quantitative analysis Quantitative analysis is a scientific approach.
News & Numbers Why should journalists know numbers & math? ·Explain what numbers mean to readers ·Make complicated numbers understandable Create.
Treatment of Uncertainties
1 MARKETING RESEARCH Week 5 Session A IBMS Term 2,
Objectives Describe the challenges involved in measuring public opinion. Explain why scientific opinion polls are the best way to measure public opinion.
Random Samples 12/5/2013. Readings Chapter 6 Foundations of Statistical Inference (Pollock) (pp )
Chapter 8: Estimating with Confidence
CONFIDENCE STATEMENT MARGIN OF ERROR CONFIDENCE INTERVAL 1.
Sampling distributions rule of thumb…. Some important points about sample distributions… If we obtain a sample that meets the rules of thumb, then…
1 First Day Data Sheet – fill out and bring to lab tomorrow Syllabus – go over.
Margin of Error How accurate are statistics in the media?
Chapter 19 Confidence intervals for proportions
Essential Questions How do we estimate population means and proportions and develop margin of error from simulations involving random sampling? How do.
Inference: Probabilities and Distributions Feb , 2012.
General Exam Tips Think Read the question carefully and try to understand the scenario, then think about the Maths you will need to do. Is it perimeter,
Sampling Distributions 9.2. When a survey is used to gather data, it is important to consider how the sample is selected for the survey. If the sampling.
Uncertainty2 Types of Uncertainties Random Uncertainties: result from the randomness of measuring instruments. They can be dealt with by making repeated.
PB #5 Polling. Measuring PO Public Opinion – people’s opinion on an issue PO Poll: small number of people – the sample (respondents) – are interviewed.
Statistic for the day: % of Americans who didn’t attend college who say they believe in extraterrestrials: 37 Who did attend college: 47 Assignment: Read.
Using math in journalism Proportion – Explain issues relative to the size or magnitude as a whole: $250,000 increase in Brookline taxes compared to $250,000.
The accuracy of averages We learned how to make inference from the sample to the population: Counting the percentages. Here we begin to learn how to make.
Chapter 11 Unit 3 Political Socialization Pearson Education, Inc. © 2008 American Government: Continuity and Change 9th Edition to accompany Comprehensive,
Introduction Sample surveys involve chance error. Here we will study how to find the likely size of the chance error in a percentage, for simple random.
Intro to Probability and Statistics 1-1: How Can You Investigate Using Data? 1-2: We Learn about Populations Using Samples 1-3: What Role Do Computers.
Check it out! : Estimating with Confidence.
Making Sense of Statistics: A Conceptual Overview Sixth Edition PowerPoints by Pamela Pitman Brown, PhD, CPG Fred Pyrczak Pyrczak Publishing.
Dr. Justin Bateh. Point of Estimate the value of a single sample statistics, such as the sample mean (or the average of the sample data). Confidence Interval.
Confidence Intervals with proportions a. k. a
Measuring Public Opinion
Chapter 8: Mass Media and Public Opinion Section 2
Chapter 8: Mass Media and Public Opinion Section 2
Chapter 8: Mass Media and Public Opinion Section 2
Chapter 8: Mass Media and Public Opinion Section 2
Presentation transcript:

Election News and Numbers Making sense of polls, statistics and more for the 2008 election!

Why should journalists know numbers & math? Explain what numbers mean to readers –Make complicated numbers understandable Create impact in stories Give context to a situation –Check credibility of government, industry, etc. Do the numbers back up what they’re saying? What are the numbers hiding?

Editing with numbers Balance! –Too few numbers  unclear –Too many numbers  confusing Context! –Be careful when comparing raw numbers Accuracy! –Know how to apply & check formulas

Polls and accuracy Consider the following: “Likely Voters” Cell-phone only voters Internet polling

“Likely Voters” “likely voters” are determined by pollsters. They are usually people who answer “yes” to questions like: Did you vote in the last election? Historically polls that count “likely voters” are more accurate Who does this leave out? Why might the “likely voter” rule not be as accurate this election?

Cell-phone only voters Laws prohibit that method for cell phones so pollsters would have to manually call which is $$$$$$$ But Cell phone only voters only make up 13% of the populations and are mostly under 30 years of age. Some polls try to adjust results accordingly

Internet Polls What are some potential issues? What are some factors that might make these polls less accurate?

Polls and Surveys Poll—estimate of public opinion on a single topic –Which candidate will win the election? Survey—multiple questions asked to get data about a sample of the population –American Community Survey (U.S. Census)

Poll/Survey Sources (multiple sources) (Gallup polls) (polls and analysis from a Colorado company) –Browse research & subject guide for Polls or Public Opinion Information

5 W’s of describing polls WHO is behind the poll WHAT is being polled (slight changes in wording can affect response) WHEN was the poll taken WHERE did the sample come from (nationwide vs. Colorado) HOW was the poll conducted (random vs. targeted, phone vs. Internet)

Polls Margin of Error –Maximum distance from the expressed value that the true result should be –Expressed as +/- % –Why? The margin of error. In this case, the four percent margin of error. That means that if you asked a question from this poll 100 times, 95 of those times the percentage of people giving a particular answer would be within 4 points of the percentage who gave that same answer in this poll.

Question 1.“Gallup Daily election tracking reports the percentage of registered voters who say they would support each candidate if the presidential election were held today.” In an October 10 th poll 51 percent of registered voters said they would support Barack Obama while 41 percent said they would support John McCain. The margin of error is +/- 2. Considering the margin of error what is the lowest percent and highest percent of people who voted for Obama? For McCain? Take the percent polled and add the margin of error. Take the percent polled and subtract the margin of error.

Answer 1 The actual result could be a range.

Using polls in articles Always include margin of error when writing poll results in a story! Remember that sample size can affect Margin of Error: 400 people, margin of error ~ 5 % 1000 people, margin of error ~ 3 % Political polls—often very close, margin of error can cancel out any apparent lead

Key Formulas: Percent of total Percent of total = Amount/total *100 Q 2: To date McCain has raised $230 million for his campaign of which Merrill Lynch employees, PAC etc. contributed $329,170. What percentage of his campaign financing comes from Merrill Lynch employees, PAC’s etc.? Take contribution amount and divide by total campaign financing. Next multiply by 100. Data from opensecrets.org

Question 3 Last year's city budget was $7,000,012. This year, you're told, the budget will be cut by 5 percent. How much will the budget be cut by (in dollars)? Take last years city budget and multiply by the percentage it will be cut. Make sure to change 5% to a decimal figure.

Key Formulas: per capita Per capita (often used with crime, murder, number registered voters etc.) –Number of occurrences/Total population –Q4: In 2004 small- city had 58,000 registered voters and large- city had 1,000,500 registered voters. Does this mean you’re less likely to meet a registered voter in small-town? Not quite…Small-city’s 2004 population: 102,000. Large-city’s 2004 population: 3,000,000 What’s the per capita registered voter rate? –Small-city 2004 population: 102,000. Large-city 2004 population: 3,000,000 –What’s the per capita registered voter rate? –Number of registered voters divided by the towns population. Do this for EACH town.

Per capita continued Per capita, cont. –Q 5:How would you report Small-city and Large-city’s per capita voter rates in a story? –Multiply the per capita amount you found for each city by a factor that makes sense like 1000 people.

Key formulas Estimating crowd size –Adds context and descriptive power when talking about an event –Square footage of venue/density of crowd – Would be useful for estimating crowd at Michelle Obama event at Farrand field. –Be wary of using event organizers estimates they are usually above the actual crowd number –Rules of thumb: Densely packed crowd: 2.5 square feet per person Moderately dense crowd: 5 square feet per person Loosely packed crowd: 10 square feet per person Pay attention to units and conversion factors!

Question 6 What is the best estimate of how many people gathered to see Michelle Obama speak at Farrand Field? The crowd loosely fills Farrand field measuring 67 yards by 150 yards? Convert yards to feet by multiplying yards by the correct conversion factor. Convert feet to square feet. Divide square footage by square footage per person.

Statistics AVERAGE??? Be careful with this word! Many different meanings! Mean=statistical average –Sum of all values/number of values

Question 7 Barack Obama’s campaign received donations from many different groups of people. Lawyers/Law Firms donated $27,689,330, Retired donated $27,220,507, Education gave $12,222,365, Securities & Investment gave $10,847,652 and Business Services gave $7,451,886 to Obama’s campaign. What is the mean? Add up all the donations. Next, divide by the number of donations.

Statistics Median –The value in the middle $100,000; $50,000; $25,000; $15,000; $10,000 Median = $25,000 Often a better reflection of the range of values Cautions: –Mean can be skewed by what’s happening at the outer boundaries, but median might not reflect changes happening in the high or low range –When looking at large sets of numbers use excel!

Question 8 What is the mean contribution to Obama’s campaign? Look at the data set from question 7: ($27,689,330 + $27,220,507 + $12,222,365+ $10,847,652 + $7,451,886) What is the middle number?

Questions? Link to these questions and a few more to practice on Helpful site with good definitions