Significance Test Basics
The part of your hypothesis that always has an equal sign
The null
This is how we check the normal condition for tests with proportions
np and n(1-p) are at least 10
The normal condition when n isn't greater than or equal to 30 or from a normal population
Graph: no obvious skew or outliers
The error when you reject the null when the null is true
Type I
This is what “www” stands for in a website browser
World Wide Web
If the alpha level is .05 and the pvalue is .051, what conclusion do you make?
When you should use t-distribution for proportions
NEVER
If you had only a t score, how would you calculate the p value
tcdf
Type II
These 3 countries made up the original axis powers in WWII
Germany, Italy, and Japan
the Ha can have which 3 signs before the number that is the same as the Ho
<, >, or not equal to
If you had only a z score and it was a two sided test, how would you calculate the p value
2 times normalcdf or 1 - area in between
two things you should include in the do step
test statistic (t), p value, degrees of freedom, and numbers plugged in the formula
If alpha goes up, this happens to power
It goes up
This punctuation mark ends an imperative sentence
Period or exclamation point
to conclude a test you must mention what 2 things
connect alpha to p value
reject or fail to reject null
do or do not have evidence for Ha in CONTEXT
standard deviation for the test statistics for a one sample z test for proportion uses these values
po (p) and n
The scenario where you would run a one sample t test on two lists of data
When it is paired data
1-Power
What is type II (Beta)
This animal can be seen on the Porsche logo
Horse
Interpret a pvalue
The odds of getting this sample or more extreme if the null is true
A drug company has developed a new vaccine for preventing the flu. The company claims that fewer than 5% of adults who use its vaccine will get the flu. Of the 1000 adults who were given the vaccine, 43 got the flu. Do these data provide convincing evidence to support the company’s claim?
No, the p-value (.15) is too high to reasonably support their claim.
The average height of 18-year-old American women is 64.2 inches. You wonder whether the mean height of this year’s female graduates from a large local high school differs from the national average. You measure an SRS of 48 female graduates and find that x¯=63.5 inches and sx=3.7 inches . Find the standardized test statistic and P-value in each setting, and make an appropriate conclusion
3 ways to increase power
increase n
increase alpha
alternate value is further from null
This is how long an Olympic swimming pool is (in meters)
50 m