# Stats Exam II review

## Terms

undefined, object
copy deck
A national fitness chain is considering opening a new fitness club in Eureka, California. They contact a marketing research firm to help them determine if adults in Eureka would be interested in joining such a club. From a list of all residential address
A. the same as for any other set of 100 residential addresses.
B. exactly 0. Simple random samples will spread out the addresses selected.
C. reasonably large due to the â€œclusterâ€ effect.
D. 100 divided by the size of the population of Eureka.
Researchers wish to determine if a new experimental medication will reduce the symptoms of allergy sufferers without the side-effect of drowsiness.
To investigate this question, the researchers give the new medication to 50 adult volunteers who suf
Using a control group.
I collect a random sample of size n from a population and from the data collected compute a 95% confidence interval for the mean of the population. Which of the following would produce a new confidence interval with larger width (larger margin of error)
A. Use a larger confidence level.
B. Use a smaller confidence level.
C. Compute the same interval many times. Approximately 5% of these intervals will be larger.
D. A confidence interval that is being a little too over-confident.
In formulating hypotheses for a statistical test of significance, the null hypothesis is oftenâ€¦
A. a statement of â€œno effectâ€ or â€œno difference.â€
B. the probability of observing the data you actually obtained.
C. a statement that
A statement os "no effect" or "no difference."
A certain population follows a normal distribution with mean µ and standard deviation ϒ = 1.2. You construct a 95% confidence interval for µ and find it to be 1.1 ± 0.8. Which of the following is true?
A test of the hypotheses H0: Âµ = 1.2, Ha: Âµ â‰  1.2 would be rejected at the 0.05 level.
A test of the hypotheses H0: Âµ = 1.1, Ha: Âµ â‰  1.1 would be rejected at the 0.05 level.
A test of the hypotheses H0: Âµ = 0, Ha: Âµ â‰  0 would be rejected at the 0.05 level.
None of these can be computed without complex math.
The value in the population that we are trying to estimate is called a ____
parameter.
With_________ we want to generalize outside of our sample to the whole population
statistical inference
In order to use ____ ____,we have to use information from our sample to estimate the value in the population.
statistical inference
2 approaches to statistical inference are ___ and ___.
confidence intervals and significance tests
___ ____estimate the value of a population parameter.
confidence intervals
___ ____see if a claim about a population is likely to be true.
significance tests
both confidence intervals and significance tests are based on___distributions.
sampling distributions
the "twisted logic" of significance tests is:
Do the data give evidence against the claim?
to calculate a "change score," calculate the difference _______.
(After value minus Before value).
The logic of significance tests is a little backwards:__________
We state a claim and then try to see if the data find evidence AGAINST it. Or, more specifically, we are trying to see if the results or evidence goes against (contradicts) the null hypothesis.
the null hypothesis is OFTEN a statement of ___effect.
no
The null hypothesis is in contrast to the statement we want to make, or the _____ _____.
alternative hypothesis
The ____hypothesis is also abbreviated H sub 0.
null hypothesis
The "alternative hypothesis" is abbreviated ____, and sometimes ____.
H sub A; H sub 1.
In a ____-tailed test, your claim is that the mean is less than 0, or your claim is that the mean is greater than 0.
1-tailed test
If we do not know the direction of change, we need to take a ___test.
2-tailed test
If we REJECT the null hypothesis, given our data, we can say that the data SUPPORT the ____ _____.
If we the null hypothesis, given our data, we can say that the data support the alternative hypothesis.
the________
compares the difference between 2 means
"one-sample z-test" compares the difference between 2 means.
the formula for z is _____.
z=(x-bar minus mean) divided by (standard deviation divided by square root of n).

(z=x bar-mean/sigma/square root of n).
In a ____-tailed test, your claim is that the mean is not equal to 0.
2-tailed test
Use sample mean to estimate ____________.
population mean.
This is the probability that the interval will capture the population parameter
Confidence Level
The formula for a confidence interval is this:
CI=x bar +/- (standard deviation/square root of n)(z*)
_____ is the % of curve around the mean
z star (z*)
90%: z* = _____
95%: z* = ____
99%: z* =____
1.645
1.960
2.576
SEM=_____________
standard deviation/square root of n
____variables are very similar to lurking variables.
confouding variables
______ ______ sampling is
One type of probability sampling
Everyone has an equal chance of being selected
In order to use___ _____sampling, use identifying information and randomly select them
Usually based on random number generator
Simple Random Sampling
Give some examples of variables we would use for Stratified Random Sampling
Examples: gender, age group, ethnicity
Name and explain some survey problems:
Undercoverage
Some groups left out of the process of choosing a sample
Nonresponse
Members of a population refuse to participate or cannot be contacted
Response bias
Participants lie, or might be affected by researcher or questions
Wording of questions and question order
The way you word a question may bias results
The way you offer answers may bias results
The order of questions may bias results
Cultural factors
Psychometric issues (reliability and validity)

35