11 Flashcards
If n > ___, its okay to use normal approximations?
~50
If variances between two samples are different but the standard deviation is roughly 3-fold difference, then you can use?
Two-sample t test.
Data transformations?
Changes each data point by some simple mathematical formula.
The log transformation is useful when?
•the variable is likely to be the result of multiplication of various components
•The frequency distribution of the data is skewed to the right
•The variance seems to increase as the mean gets larger (in comparisons across groups).
Choosing transformations? 3•
•Must transform each individual in the same way
•The transformed values must still carry biological meaning
•You cannot keep trying transformations and statistical tests until P<0.05.
Non-parametric methods?
Sign test? 5•
•Non parametric test
•Compares data from one sample to a hypothesized median value
•Simple: for each data point, record whether individual is above + or below - the hypothesized median value.
•Use a binomial test to compare result to proportion = 1/2
•Very little power.
Species that mate multiple times, they are more/less likely to get sexual selection.
More
Variance in reproductive success increase/decrease?
Increase, which results in more sexual selection.
Ranking data?
•Rank each data point in all samples from lowest to highest.
•Lowest data point gets rank 1, next lowest gets rank 2
Mann-whitney U test?
Compares the central tendencies of two groups using ranks. It doesn’t assume normality unlike 2 sample t test.
Permutation test steps? 3•
•Variable 1 from an individual is paired with variable 2 data from randomly chosen individuals. This is done for all individuals.
•The estimate is made on the randomized data
•The whole process is repeated numerous times. The distribution of the randomized estimates is the null distribution.
In a permutation test, all data points are used ____?
Once
How do you determine the P-value if you have the permitted and real data?
You compare it.
