what is hypothesis testing
formal procedure used by researchers to accept or reject a hypothesis made about about a population based on evidence from a sample
what are the 5 steps in hypothesis testing
- state the null hypothesis and the research (or alternate) hypothesis
2 . determine characteristics of the comparison distribution - determine the cutoff sample score (the critical value on the comparison distirbution)
- compare your samples score to the cutoff score
- decide whether or not to reject the null hypothesis
What does the null hypothesis state
that there is no difference between the sample you are testing and the normal distribution
why is it called the null hypothesis
because it is nullafiable - you can invalidate it
what does the research hypothesis state?
that there is a difference between your test group and the normal distribution
i.e. that the experiment had an effect
it is the complete opposite of the null hypothesis
what does the comparison distribution represent?
the population situation if the null hypothesis is true
what is another name for the comparison distribution
a sampling distribution
when would you use a one tailed test
when you are interested in a specific direction on the normal distribution
when would you use a two tailed test
when you are not interested in the specific direction of the effect - just want to know our results differe from the nomral distribution
what type of test is also called non-directional
two-tailed
what is a type 1 error
you reject a null hypothesis that is true
what is the chance of making a type 1 error
the same as your significance level
i.e. if the significance level is <0.05 then the probability of committing a type 1 error is less than 5%
what is a type 2 error
you fail to reject a null hypothesis that is false
when is a type 2 error more likely to occur?
if you have a very stringent level of significance such as .01 or .001 you are increasing the likelihood of failing to reject a false null
why do we say hypothesis testing involves a double negative logic
since we are interested in the research hypothesis but we test whether it may be true by seeing if we can reject its opposite the null hypothesis
when we conclude that we can reject the null hypothesis what does that mean?
that our alternative hypothesis is true and that there is a difference between the experimental group and the comparison distribution
that the result is statistically significant
what is a hypothesis
a predicution we test using statistical methods
What are the cut off Z scores for a significance level of .05 in a one tailed test? two-tailed test?
one tailed -/+ 1.64
two tailed -/+ 1.96
What are the cut off Z scores for a significance level of .01 in a one tailed test? two-tailed test?
one tailed -/+ 2.33
two tailed -/+ 2.58
are cutoff scores more extreme with a two tailed or one tailed test
two
true or false: To reduce the risk of making a Type II error, investigators can use a significance level lower than .05
false
In a type 1 Error is the null hypothesis true or false
true
in a type II error is the research decision rejected?
no
Which type of error produces a false positive
type 1
-
Unit 138
-
Unit 224
-
Unit 362
-
Unit 421
-
Unit 530
-
Unit 6: Hypothesis Tests with means of samples27
-
Unit 7: Effect Size and Statistical Power Notes74
-
Unit 8 Introduction to the t test: Single Sample and Dependent Means42
-
Unit 9: T test for Independent Means52
-
Unit 10: Introduction to the Analysis Of Variance ANOVA76
-
Chapter 11: Chi-Square Tests and Strategies when population distributions are not normal44
