Creating Hypotheses
Significance Tests
Type I and II Errors
Grab Bag
100
What is the null hypothesis?
The "no change" hypothesis, mean stays the same.
100
If your p-value is less than your significance level, alpha, you....
Reject the null hypothesis.
100
What is a type 1 error?
A false positive; reject the null hypothesis when you shouldn't.
100
The current unemployment rate is 11.3%. Is 11.3 a parameter or statistic?
Parameter
200
What are the three possibilities for the alternative hypothesis?
greater than the population mean, less than the population mean, or different than (not equal to) the population mean.
200

What is a p-value?

It is the probability of observing a statistical result (or a more extreme one) if the null hypothesis is true. It essentially tells you how likely your data is to have occurred by chance, assuming there's no real effect.

200
What is a type II error?
A false negative; don't reject the null hypothesis when you should.
200
What is a statistic?
A number that describes a sample.
300
Ariana wants to investigate how the GPA of Lakeview students compares to the average high school gpa of 3.1. What would be an example of a one-sided and a two-sided hypothesis for this scenario?
One sided: Lakeview students have a higher gpa than 3.1 or Lakeview students have a lower gpa than 3.1 Two sided: Lakeview students have a different gpa than a 3.1
300
You find a p-value of .06. What do you do with the null hypothesis at a .1 significance level?
Reject the null hypothesis.
300

An employee takes a drug test. What are the type I and type II errors that can be made? If you are the employee, which is worse?

type 1: false positive--It's believed that the employee is positive for drugs when she is not 2: false negative--it is believed that the employee is sober when they are not. As for which one is worse, Type 2 is worse.

300
What is the probability associated with a z-score of 0?
50%.
400
Define the null and alternative hypotheses for the following situation: In 2000, 36% of adults in a certain country were morbidly obese. A health practitioner suspects that the percent has changed since then. She obtains a random sample of 1042 adults and finds that 393 are morbidly obese.
Null hypothesis: m = .36 The percent of morbidly obese adults is 36% Alternative Hypothesis: m not equal to .36 The percent of morbidly obese adults is not equal to 36%
400
A small p-value means that the data is statistically _______ because __________________.
significant; it is not likely to happen by pure chance.
400

A psychologist claims that more than 7.1% of adults suffer from extreme shyness. Identify the type II error for the test.

Type II error: Saying the psychologist is wrong when his claim is really correct.

400

If you want to avoid a Type II error, how should we adjust the significance level?

To avoid a Type II error means to increase the likelihood of rejecting the null hypothesis, therefore we should increase significance level. 

500
A candidate for state representative of a certain state claims to be favored by at least half of the voters. If a hypothesis test is performed, how should you interpret a decision that fails to reject the null hypothesis?
The candidate isn't favored by at least half of the voters.
500
A local juice manufacturer distributes juice in bottles labeled 32 ounces. A government agency thinks that the company is cheating its customers. The agency selects 50 of these bottles, measures their contents, and obtains a sample mean of 31.6 ounces with a standard deviation of 0.90 ounce. At a 0.01 significance level, run a 5 step hypothesis test to test the agency's claim that the company is cheating its customers.
null hyp: m = 32 alt hyp: m < 32 z-score: -3.14 p-value: .0008 reject null hypothesis Yes, the company is cheating it's customers.
500
A medical researcher claims that 3% of children suffer from a certain disorder. Identify the type I error for the test.
Asserting that 3% of children suffer from this disorder when the true value is not that.
500

Hypotheses should be created before you see the data, or else ______________.

you'll be biased/it's cheating

M
e
n
u