GEA1000 chapt 4 hypothesis testing

brooooooooooo

what is a hypothesis test

a statistical inference method used to decide if the data from a random sample is sufficient to reject a particular hypothesis about a population

what is the steps for hypothesis testing

1. determine the null and the alternate hypothesis

2. set the significance level

3. find the relevant sample statistic

4. calculate the p-value

5. conclusion of the hypothesis test

what are the types of hypothesis tests

• for population proportion

• for population mean (t-test)

• for association (chi-squared test for association)

what is the null hypothesis

corresponds to the case where out observation can be explained by chance variation 

ALWAYS equal to the value provided

what is the alternative hypothesis

corresponds to the case where our observation is NOT due to random chance

either <, >, or ≠

what should be important to note between null and alternative hypothesis

they are mutually exclusive

what is the p-value

is the probability of obtaining a result as extreme or more extreme than our observation in the direction of the alternative hypothesis, assuming that the null is true

what are the different criterias for p-value and significance level and the null-hypothesis

• p-value < significance level: reject null-hypothesis

• p-value > significance level: insufficient evidence to reject null hypothesis → hypothesis test is inconclusive

NEVER accept the null hypothesis

how do you find the sample statistic for population proportion and t-Test

population proportion: find the sample proportion 

t-Test: read off from the sample mean

what is the null hypothesis for a chi-squared test

there is no association between categorical variable A and categorical variable B at the population level

what is the alternative hypothesis for chi-squared test

there is an association between categorical variable A and categorical variable B at the population level