Hypothesis Tests
Test used to determine if two variables have an association
Chi squared test for independence
What is linearity assumption?
The scatterplot must be linear and there must be no patter in the residuals
You take a list of names and select the every 10th name
Systematic sample
You flip a coin three times and it lands on tails all three times. What is the probability of getting tails on the fourth flip?
A range of values derived from sample data that is likely to contain the true population parameter with a certain level of confidence.
Confidence Interval
Test that looks for a difference between data from the same group
Matched pair test
Three Answers:
If a sample is random it is.....
If the sample makes up less than 10% of the population it is...
If there are 10 successes and failures the sample size is..
Representative, independent, adequate
Every possible sample of a given size has an equal chance of being selected.
Simple Random Sampling
What is replication?
Must test many subjects to draw conclusions and should also repeat whole experiments to generalize to larger populations.
A statistical method used to make inferences about population parameters based on sample data. It involves testing a null hypothesis against an alternative hypothesis using statistical techniques.
Hypothesis Testing.
Name the procedure: A group of 50 highschoolers complain about being unable to pay attention. They report that with Adderall they can pay 15 more minutes of attention per class with a standard deviation of 5 minutes. Create a 90% confidence interval for the attentive time.
1 sample t interval
When taking a 2-mean T-interval, the two sample sizes were 27 and 24, so we were unable to do the Central Limit Theorem. What can we do instead for the sample size condition?
Look at the histograms and see if they are normal enough.
Dividing the population into subgroups based on certain characteristics and then taking a random sample from each subgroup.
Stratified Sampling
Which model, binomial or geometric, helps us answer the question: "What is the probability of the first success on the nth trial?"
Geometric model
A statistical technique used to model the relationship between one or more independent variables and a dependent variable. Common examples of this include simple linear, multiple linear, and logistic.
Regression Analysis
How do you find degrees of freedom for chi-squared test of independence and homogeneity?
((# of colums)-1)*((# of rows)-1)
To proceed past the normality assumption if a sample size is less than 30 in a t test what must be true
The histogram of the residual is roughly normal
Whitman conducts a survey during lunch asking their students whether or not they like the school provided lunch. What type of bias is this and why?
Undercoverage bias because seniors or students who dislike school lunch may go out to eat.
Events where if event A occurs, then event B cannot occur. This means that the venn diagram does not overlap and events A and B have no outcomes in common.
Disjoint/mutually exclusive events
A nutritionist samples 50 adults. The sample mean daily vitamin C intake is 75 mg with a standard deviation of 12 mg.
What is the margin of error for a 95% confidence interval?
ME = z*(s/root n)
95% confidence level, z*= 1.96
ME = 1.96(12/root 50) = 3.33
ME = 3.33mg
What is the largest drawback of the Chi Squared Goodness of Fit Test?
You can never prove the null hypothesis, only fail to reject it.
How does one determine if the sample size assumption is passed for a two proportion z test. Name the steps and formulas
A company conducts a customer satisfaction survey by offering a 20% discount coupon for their next purchase to customers who complete the survey online.
Identify the greatest potential source of bias in this sampling method.
Non-response bias
Customers who choose not to participate in the survey may have different opinions or experiences than those who choose to participate.
List the four conditions for a Bernoulli trial.
-Probability for success is the same for each trial
-The trials are independent
-Number of trials should be finite.
A sample of 25 students has a mean test score of 78 with a standard deviation of 10. Construct a 95% confidence interval for the true mean test score.
Margin of error = t*(s/root n)
For 24 degrees of freedom t* = 2.064
ME = 2.064 (10/root25) = 4.13
78+-4.13 =
(73.87, 82.13)