Probability and Significance Flashcards
Acceptance of the Null Hypothesis
If the stats test is not significant the null hypothesis is accepted.
The null hypothesis states there’s no difference or no correlation between the conditions.
The stats test determines which hypothesis (null or alternative) is true and thus which we accept and reject
Probability and the Null Hypothesis
Probability is a measure of the likelihood that a particular event will occur.
The null hypothesis is accepted or rejected at a particular level of probability
Level of Significance
What are the two compromises?
Usual level of significance is 0.005 (or 5%).
This means the probability that the observed effect (the result) occurred by chance is equal to or less than 5%.
This is a compromise between too lenient (10%) or too stringent (1%)
Calculated and Critical Values
To check for statistical significance, the calculated value (ie result of the statistical test) is compared with a critical value in a table of critical values based on probabilities
Three Criteria to find the correct Critical Value
- Hypothesis one-tailed (directional) or two-tailed (non-directional)
- Number (N) of participants (aka degrees of freedom, df)
- Level of significance (or p value)
One-Tailed Hypothesis
Directional hypothesis
Two-Tailed Hypothesis
Non-directional hypothesis
Type I Error
Description of this error
The null hypothesis is rejected and the alternative is accepted when the null hypothesis is true.
This is an optimistic error or false positive as a significant difference or correlation is found when one doesn’t exist
Type II Error
Description of this error
The null hypothesis is accepted, but in reality, the alternative hypothesis is true.
This is a pessimistic error or false negative
What makes a Type I error more likely?
Type I error more likely to be made if the significance level is too lenient (too high, eg 0.1 or 10%)
What makes a Type II error more likely?
Type II error is more likely if the significance level is too stringent (too low, eg 0.01 or 1%), as potentially significant values may be missed
