Interential Statistics Exam 2 Flashcards
Type II Error
Do not reject the null when in fact it is false.
Type I Error
Reject the null hypothesis when in fact it it true.
Type I Error Example
Does this new drug reduce blood pressure?
We conclude that this drug DOES reduce blood, when in fact it DOES’NT.
Type II Error Example
Does this new drug reduce blood pressure?
The results are INCONCLUSIVE, when in truth the new drug DOES lower blood pressure.
Effect Size
- Differences between population means
- Population standard deviation
- Figuring power from PREDICTED effect sizes
What determines the Power of a Study?
- How big an effect (the effect size) the research hypothesis predicts.
- How many participants are in the study (Sample Size)
Statistical Power
Probability that the study will give a significant result of the research hypothesis is true.
Effect Size Conventions
d=.2 (Small Effect)
d=.5 (Medium Effect)
d=.8 (Large Effect)
Meta-Analysis
- Combines results from different studies
- Provides an overall effect size
- Common in more applied areas of psychology
Influences on Power
- Sample Size
- Significance level (alpha)
- One-versus-two-tailed tests
- Type of hypothesis-testing procedure
What type of test are the best type for testing procedure?
Parametric Test
What are some PRACTICAL ways of raising power?
- Use less diverse population
- Use a larger sample size
- Use a more lenient level of significance (such as .05 if you started w/ 0.1)
- Increase intensity of experimental procedure
- Use a one-tailed test
- Use standardized, controlled circumstances of testing
What is the biggest influence of POWER?
Sample Size
Distribution of means
Distribution of means of samples of a given size from a population.
Why do we use Distribution of means?
We use it as a Comparison distribution when testing hypotheses involving a single sample of more than one individual.
