Chapter 18 Flashcards
(18 cards)
Define simple random sampling.
Procedure where every possible sample of a given size had an equal chance of selection.
Define opportunity sampling.
Involves choosing respondents based upon convenience and availability.
Define systematic sampling.
Taking participants at regular intervals from a list of the population with a randomly chosen starting point.
Define stratified sampling.
Splitting the population into groups based on factors relevant to the research, then random sampling from each group in proportion to the group’s size.
Define quota sampling.
Splitting the population into groups based on factors relevant to the research, then opportunity sampling from each group until they have found the required number of participants.
Define cluster sampling.
Splitting the population into clusters based on convenience, then randomly choosing some clusters for further study.
Define a Hypothesis Test.
A procedure for answering a question such as:
Does a sample provide significant evidence that a population parameter (proportion/mean/spread) has changed from an assumed/previously known value?
Define the null hypothesis H0.
The previous or assumed population proportion.
Define the alternative hypothesis, H1.
How you think the proportion may have changed.
What do you do if the p-value is smaller than the significance level?
You have enough evidence to reject H0, else don’t.
How do you conduct a hypothesis test?
.State H0, H1 and define parameters.
.Decide significance level.
.State distribution if H0 = true.
.Calculate the p-value.
.Compare p-value to SL.
.Interpret the conclusion with context.
What do you do in a one-tail test?
.H1 is p < a or p > a.
.Compare to SL.
What do you do in a two-tail test?
.H1 is p not equal to a.
.Compare to 1/2 of SL.
Define the critical/rejection region.
The set of values of the test statistic which provides sufficient evidence to reject H0.
Define the critical value.
The value at the edge of the critical region.
Define the acceptance region.
The set of values of the test statistic which don’t provide sufficient evidence to reject H0.
What do you do if the p-value is in the critical region?
Reject H0.
What is the probability of rejecting a correct H0 equal to?
The probability of the p-value being in the critical region - smaller than or equal to the SL.
