Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
25 Cards in this Set
- Front
- Back
What are the five steps of hypothesis testing (in order)?
|
1. Identify populations and state research and null hypotheses.
2. Determine characteristics of the comparison distribution. 3. Establish cutoff sample score/critical value. 4. Calculate test statistic. 5. Make decision about the null hypothesis and draw conclusions about the research question. |
|
Population one
|
The population of interest. This is the population to which you've applied a treatment or that has a characteristic of interest.
|
|
Population two
|
The population to which you are comparing those exposed to a treatment or with a characteristic of interest. This is often a "general population."
|
|
Research hypothesis
|
Hypothesis that specifies a difference between populations.
|
|
Directional hypothesis
|
Research hypothesis that predicts a specific direction of difference between populations.
|
|
Non-directional hypothesis
|
Research hypothesis that indicates a difference between populations, but does not predict the direction of that difference.
|
|
Null hypothesis
|
Hypothesis that negates the prediction made in a research hypothesis.
|
|
The three main characteristics we need to know about the comparison distribution
|
1. Shape
2. Mean 3. Standard deviation |
|
Comparison distribution
|
The distribution of scores if the null hypothesis is true.
|
|
Cutoff sample score
|
The point on a comparison distribution that defines the line between population one being "different' or "not different" from population two.
|
|
Significance level
|
The probability that population one differs from population two by chance alone.
|
|
When do you use a one-tailed hypothesis test?
|
When you have a directional research hypothesis.
|
|
When do you use a two-tailed hypothesis test?
|
When you have a non-directional hypothesis.
|
|
How can you identify a directional research hypothesis?
|
There is a comparison word in the research hypothesis (e.g, higher, lower, more, less, greater, fewer).
|
|
When do you reject the null hypothesis?
|
When the test statistic you calculate is farther from the mean than the cutoff sample score (in the predicted direction).
|
|
When do you NOT reject the null hypothesis?
|
When the test statistic you calculate is not more extreme than the cutoff sample score.
|
|
What does it mean if you do not reject the null hypothesis?
|
It means that population one does not differ from population two in the way that was predicted by the research hypothesis.
|
|
Type I error
|
Rejecting the null hypothesis when there is no true difference between populations.
|
|
Type II error
|
Not rejecting the null hypothesis when there truly is a difference between populations.
|
|
What is another name for type I error?
|
False positive
|
|
What is another name for type II error?
|
False negative
|
|
What happens to the probability of type I error if you select a higher (i.e., less stringent) significance level?
|
The chance of a type I error increases.
|
|
What happens to the probability of type I error if you select a lower (i.e., more stringent) significance level?
|
The chance of a type I error decreases.
|
|
What is the relationship between type I error and type II error?
|
As the probability of type I error increases, the probability of type II error decreases. As the probability of type I error decreases, the probability of type II error increases.
|
|
Hypothesis
|
Statement that predicts how two populations are expected to differ.
|