Week 2 - Satistical Testing Part 2 Flashcards
Give 5 examples of tests
One-Sample t-test
Chi-squared test for independence
Two-sample t-test for independent samples
Two-sample t-test for paired samples
Linear regression
what is One-sample t-test
A one-sample t-test is a statistical test used to determine whether the mean of a single sample is significantly different from a known or hypothesized population mean. This test is useful when you want to compare the sample mean to a specific value, which could be a theoretical expectation, a historical average, or any other value of interest.
what is chi-squared test for independence
null: variables are independent
P(A and B) = P(A)P(B)
☞ example: collect 10 pets and see if there’s a relationship between type of pet and how they do on a test.
what is two-sample t-test for independence
Null: mean1=mean2
Example: is the mean IQ score for cats the same as for dogs
what is two-sample t-test for paired samples
Null: equal means in both conditions
Example: is the mean iq score for cats the same before training as after training.
what is linear regression
Example: what is the effect of pet type, coat type and tail length on IQ.
What is inference
Inference is about making statements about a population, based on a sample
What is type I error
Rejecting the null hypothesis when it is true
what is type II error
failing to reject the null hypothsis that is not true
what is p-value
The probability of finding this test statistic, or a more extreme one, if the null-hypothesis is true.
The probability of obeserving a p-value of x or lower under H0 is ____
p
If H0 is true (nothing going on), the distribution of p-values is ____.
uniform
What is the probability of making a type I error
alpha
how to avoid making type II errors
type II is less likely if:
1. There is a large true effect
2. The random variation (noise) is low
3. Our alpha is high
4. The sample is large
