Module 4 Hypothesis Testing Flashcards
Hypothesis Testing
What is a research hypothesis?
a statement of expectation or prediction that will be tested by research (or a question)
What do research hypotheses look at and how?
The differences in groups by comparing the means of each group.
What are the 5 steps of Hypothesis Testing?
- State the null hypothesis
- Select the level of significance
- Choose the appropriate statistical test
- Obtain a p-value
- Make a decision about the null hypothesis
What does null mean?
There is no difference or everything is equal
What is a null hypothesis?
A statement of no difference between
groups or no relationship among variables
When do you make a null hypothesis?
Before your research; start by saying the groups are equal/the same
What is being determined when finding the level of significance?
if the difference in the means is large enough to say it is a “significant” difference
When is the level of significance usually set?
Before the study begins
What are the most common levels of significance and which one will we use?
0.05 and 0.01
We use 0.05
How do you choose which statistical test to use?
- The research hypotheses
- The number of independent and dependent variables
What is a p-value?
The probability that the difference or
the relationship you found is due to chance (or the probability that the null hypothesis should be accepted)
What is the decision if the p-value is small?
The difference or the relationship
is real (significant)
What is the decision if the p-value is large?
The difference or the relationship
is due to chance (not significant)
If your p-value is less than or equal to your alpha you…
reject the null hypothesis – the difference or relationship is significant
If your p-value is greater than your alpha you…
accept the null hypothesis – the difference or relationship is due to chance and not significant
What is Type 1 error?
Rejecting the null hypothesis when it is
true
What is Type 2 error?
Accepting the null hypothesis when it is false
How do we control Type 1 error?
With the alpha level (0.05 is safe)
True or False?
A lower alpha, decreases our chance of Type 2 error.
False. A lower alpha, INCREASES our chance of Type 2 error.
True or False?
Significance and meaningfulness mean the same thing.
False. Just because you find a significant difference or a significant relationship, that does not mean the result is meaningful.
What is the definition of meaningfulness?
Does the statistical difference/relationship mean anything in the REAL WORLD?
What are the 5 statistical tests?
- Independent T-test
- Dependent T-test
- One-way ANOVA
- Two-way ANOVA
- Two-way ANOVA with repeated measure
Describe the Independent Variable, Groups, and Dependent Variable of an INDEPENDENT T-TEST
Independent - 1
Group(s) - 2
Dependent -1
Describe the Independent Variable, Groups, and Dependent Variable of a DEPENDENT T-TEST
Independent - 1
Group(s) - 1
Dependent - 2
Describe the Independent Variable, Groups, and Dependent Variable of a ONE-WAY ANOVA
Independent - 1
Group(s) - 2+
Dependent - 1
Describe the Independent Variable, Groups, and Dependent Variable of a TWO-WAY ANOVA
Independent - 2
Group(s) - 2+
Dependent - 1
Describe the Independent Variable, Groups, and Dependent Variable of a TWO-WAY ANOVA WITH REPEATED MEASURE
Independent - 1
Group(s) - 2+
Dependent - 2+