PSYC204 content between 2 midterms

4 steps of the hypothesis

1. state the hypothesis about the population

2. use hypothesis to predict the characteristics the sample should have. determine the probability at which you will conclude the sample outcome is very unlikely.

3. obtain a sample from the population. compute the z score for this sample

4. compare data with the hypothesis decision.interpret results to make a decision

what is the purpose of the hypothesis test?

to decide between two explanations.

1. the difference b/t sample and population can be explained by sampling error (there doesn’t seem to be a treatment effect)

2. the difference between the sample and population is too large to be explained by sampling error (there seems to be a treatment effect)

null hypothesis H₀

predicts that the IV has no effect on the DV

alternative hypothesis H₁

predicts that the IV did have an effect on the DV

null distribution

distribution of the population if there is no effect of treatment. assumed to be true unless the data provide convincing evidence that it is false.

The α level establishes a criterion, or "cut-off", for making

a decision about the null hypothesis. What does the critical region consist of?

consists of outcomes that are very unlikely to occur if the null hypothesis is true. That is, the critical region is defined by sample means that are almost impossible to obtain if the treatment has no effect (when there is convincing evidence against H₀

true or false: the critical region defines unlikely values if the null hypothesis is true

True

what happens if the test statistic falls in the critical region?

we conclude that the difference is significant. in this case we reject the null hypothesis. if it’s not in the critical region, we fail to reject the null hypothesis

α=0.05 (unidirectional) means what?

there is an effect if there is a .05 or less probability of obtaining that sample with mean x^bar from the null distribution

α=0.05 (bidirectional) means what?

this would be on both sides of distribution, so α/2=.05/2 =.025

Directional (one-sided) test

when a research study predicts a direction for the effect (increase or decrease), it is a one-sided test. A directional includes the directional prediction in the statement of the hypotheses and in the location of the critical region.

difference between one-sided and two-sided tests

1. how you write and specify the alternative hypothesis: You explicitly set up the hypothesis with a direction in mind

2. the critical value associated with your cut-off. 5% on one sided means its just one one side, corresponding to a z-score of 1.65. 5$ on two sided means 2.5% one each side, corresponding to a z-score of 1.96 on either side

calculation steps for a hypothesis test

1. state the hypothesis: null and alternative

2. set the criterion: alpha level; find z-score cut off that delineates critical region

3. calculate the test statistic: standard error of the mean; sample z-score

4. make a decision: reject or fail to reject H₀

what makes a type one error less likely to occur?

smaller critical region

What is the power of a statistical test? how much power of a statistical test do you normally want to have?

It is the probability of rejecting the null, when the null is actually false. 80-90%.

what is the term used to determine effect size and what is the formula?

cohen’s d = (mean difference)/(standard deviation) = (M-𝜇)/𝜎

what are the three cohen’s d values that correlate to a low, medium, high effect size

.2 = small

.5= medium

.8 = large

what is a Type 1 vs a Type 2 error?

Type 1: when the sample data appears to show a treatment effect when, in fact, there is none.

Type 2: when sample does not appear to have been affected by the treatment when, in fact, the treatment does have an effect

if you have ¾ of these 4 variables, you can always find the fourth. what are they?

n, effect size (population), α, power (desired protection against “false negatives”