The standard error measures the …
precision of the sample mean.
The chi-square test is a nonparametric test to compare …
nominal or ordinal data comprising of one to multiple sample tests.
The approximate percentage of data that is greater than one standard deviation to the right/left?
There is an additional 0.2% beyond 3 standard deviations. Therefore, 15.9% of data will be greater than one standard deviation (σ) to the right of the mean (μ).
This is calculated by 13.6% (1 to 2 σ) plus 2.1% (2 to 3 σ) plus 0.2% (> 3 σ). Often, numerical answers will be rounded to the nearest whole number (16%), particularly if the question asks for an approximation.
Standard error of the mean is equal to …
the standard deviation divided by the square root of the sample size. If standard deviation is 1 and population size is 100, then SEM = 0.1.
A type I error is
incorrectly accepting A type I error is incorrectly accepting Ha. (False positive)
Type II or β error =
incorrectly accepting null hypothesis Ho. (false negative)
Analysis of variance (ANOVA) is used to test …
parametric continuous data when 3 or more groups exist.
Paired t-test vs unpaired t-test?
A paired t-test compares outcomes in a single group who serve as their own control, whereas an unpaired t-test compares an outcome in two different groups.
Factors effecting type 2 error?
- As the alpha number is lowered, the chance of a Type I error is lowered, but the risk of a Type II error increases.
- As the difference between the two groups increases, there is less of a chance to obtain a Type II error.
- Increasing the number of data points within the experiment decreases the risk of a Type II error.
- variability of population is increased, the risk of a Type II error is increased.
