03.2 Flashcards
why is it now recommended that the hypothesis test can be accompanied by a measure of the effect size?
because a significant effect does not necessarily mean a large effect
effect sizes enable researchers to …
arrive at common metric or evaluating diverse experiments
cohen’s d is …
a standardized measure of effect size
what does cohen’s d measure?
the size of the mean difference in terms of the standard deviation
what is the relationship between Cohen’s d and statistical significance?
- Statistical significance is about how sure you are that an effect is real; it does not refer to the size of the effect. It depends on factors like the sample size and the significance level.
- Effect size determines how big the effect is.
what does a power analysis allow for?
to determine the sample size required to detect an effect of a given size with a given degree of confidence
why run a power analysis?
- To avoid failing to reject the null hypothesis because there is not enough power to detect your effect.
- Making transparent why you chose a specific sample size.
what do you need for a a priori power analysis?
- Statistical power: the likelihood that a test will detect an effect of a certain size if there is one, usually set at 80% or higher.
- Significance level (alpha): the maximum risk of rejecting a true null hypothesis that you are willing to take, usually set at 5%.
- Expected effect size: a standardized way of expressing the magnitude of the expected result of your study, usually based on similar studies or a pilot study
what is the confidence interval and what does it tell us?
The confidence interval is an inferential statistic that tells us that based on the sample data we can be 95% confident that the interval contains the population mean.
types of inferential statistics
- comparison tests
- t-test
- analysis of variance (anova)
- two-way anova
what does the t-test tell you?
how significant the differences between two group means are
when is the t-test usually used?
when data sets follow a normal distribution but the population variance is unknown
independent sample t-test
compares the means for two groups (e.g. is therapy x more efficient than therapy y by comparing two samples)
paired sample t-test
compares means from the same group at different times (e.g. testing the effect of therapy x after 3 and 6 month in the same sample
one sample t-test
compares the mean of a single group against a known mean (e.g. if a group has above average intelligence)
