... The Scientific Approach to Polling
• There is a scientific method used to ensure that
a survey is not biased.
• When samples mirror the population they are
said to be “Representative”.
• Randomness is critical to sampling.
– Randomness implies that each person within the
entire population being pol ...
... a population has an equal and random chance of being
selected, but other types of error can also influence poll
results. Any violation of equal and random selection may
produce sampling errors that can bias survey estimates
away from the population’s true value. Nonresponse errors
can occur when per ...
... The point estimate, x-bar, must be calculated
from an SRS for the results to generalize.
Outliers can have a big effect on confidence
intervals. Check for these graphically.
When the population is non-normal, the
Central Limit Theorem is important (n ≥ 30).
You must know σ from the population.
... a. process in which individual initiative is abandoned in favor of party politics.
b. belief that one's vote does not count.
c. process by which people formulate their political attitudes and opinions.
d. practice of voting for candidates of only one specific party in any given election.
3. The expa ...
... reason why is because of the use of common words that are in the
dictionary as technical terms.
• Examples: mean, variation, correlation, sample, population, random,
hypothesis, confidence, and the list goes on.
... The poll produces a single estimate for the public’s thinking, but this estimate is a range of
The sampling error is about four percent for a sample of six hundred respondents.
That four percent generates the confidence interval.
With that said, caution is always required when in ...
... public’s opinion, a sample (that is the number of voters you would interview) need only
be about 1000 individuals! That is about one voter out of every 70,000! With that size
sample, pollsters can predict outcomes with a tolerated error, or confidence interval, of
only plus-or-minus 3%. In the mid-1 ...
... 17. Which of the following is not true about exit polling?
(A) Voting places are selected randomly around the country.
(B) Survey data shows that few voters have been actually influenced by exit-poll results.
(C) Exit polls deserve most of the blame for the network’s 2000 presidential election night ...
... If you have no “best guess” for p this conservative approach is the one
you should take.
Example: How many patients would need to be used to estimate the success rate of
medical procedure, if researchers initially believe the success rate is no smaller than 85%
and wish to estimate the true success ...
... Professionals now design well-specified polls that capture popular
views with a high degree of accuracy.
• Poll results can affect public opinion.
• Sampling errors, response bias, and other potential flaws inevitably
confer a measure of uncertainty on any survey.
... data in hand. In order to use this result we need to plug in a “best guess” for p. This
guess might come from:
Pilot study where p̂ = sample proportion is calculated
Use the worst case scenario by noting that p(1 p) .25 and is equal to
.25 when p=.50. Using p = .50 simplifies ...
... Suppose we want to estimate the mean speed of
vehicles with 90% confidence and error margin
no greater than 0.5 mph.
with (n 1) DF
Results of the prior study have the standard
deviation around 6.3. (There is no guarantee that
S will be 6.292 for a future study. In fact: it
won’t. You c ...
... the desired power, α = the significance-level, σ = the within group standard
deviation, and Δ = a difference worth detecting.
c. Suppose it is twice as easy to study girls as boys. How many subjects do you
need to study with a 2:1 sampling ratio? What was the influence of using this
sample ratio (as ...
... (C) In repeated sampling, 95% of the time the true population mean of fish weights will be equal to 6.8 pounds.
(D) In repeated sampling, 95% of the time the true population mean of fish weight will be captured in the
(E) We are 95 percent confident that all the fish weigh less ...
... a. At the 95% confidence level, what is the margin of error associated with the
estimated proportion of users who are women?
b. What is the 95% confidence interval for the population proportion of ESPN
Sports-Zone web site users who are women?
c. How large a sample should be taken if the desired mar ...
... selected. Sampling error, which depends on the size of the sample, is the level of confidence that
the sample represents the total population. A good sampling error based on a sample of 1500 to
2000 people is plus or minus 3 percent. Most polling is now done on the telephone with samples
selected th ...
An opinion poll, sometimes simply referred to as a poll, is a survey of public opinion from a particular sample. Opinion polls are usually designed to represent the opinions of a population by conducting a series of questions and then extrapolating generalities in ratio or within confidence intervals.