eM2 Analysis Flashcards
What is independent/ dependent (unpaired/ paired) groups?
The last question in the statistical decision tree asks whether the groups that are being compared are dependent or independent. This question is asking whether each group is composed of the same subjects of interest, or if they are different.
What is the difference between a parametric and non parametric test?
Parametric- data which is normally distributed
Non-parametric- data which is not normally distributed
Which is better: parametric or non-parametric and why?
Parametric- they are easier to understand and analyses are more powerful/ less likely to incorrectly reject or fail to reject a hypothesis
What is the paired and unpaired t-test?
Comparing means from two normally distributed samples either different variables from the same sample (paired) or the same variable from different samples (unpaired)
What is the one-way ANOVA?
Compares parametric means of data from more than 2 samples. It can be for paired data (repeated measures, one-way ANOVA) or unpaired (one-way ANOVA)
What is the two way ANOVA?
Compares two independent variables
What is the MANOVA?
Multivariate ANOVA
What is the problem with a one way ANOVA and how do we get over this?
You cannot tell which sets of data of the 3+ samples show difference.
You need to use a (Tukey/Bonferonni) post hoc test
What are the non parametric tests and what data are they used for?
Wilcoxon- non-parametric, paired, two sample
Mann-Whitney U- non-parametric, unpaired, two sample
Friedman- non parametric, paired, 3+ sample
Kruskal Wallis- non-parametric, unpaired, 3+ sample
What type of data are non parametric tests generally used for?
Quantitative
What do you report?
Only the p value
What is a correlation?
A relationship between two data sets
What are the types of correlation test?
Pearson (Parametric)
Spearman rank (Not parametric)
What is an r-value?
Part of the Pearson test. It is a correlation coefficient telling you how strong the relationship is. It is between -1 and +1.
What is a p-value in Pearson’s correlation test?
Tells you how reliable the R value is.
What is an r^2 value?
Tells you how close the data is fitted to a correlation line.
What are the lower boundaries for correlation in Pearson’s?
0- very low
- 2-low
- 4- reasonable
- 6- High
- 8- Very high
What is the Spearman Rank test?
Finds correlation of non-parametric data; it identifies linear trends.
What does the Spearman Rank show?
Spearman’s Rho (p) showing how strong a relationship is.
P value showing how reliable rho is (smaller is better)
What is regression?
Regression quantifies the association between the two variables (the impact changing one variable will have on the other)
What is the equation of regression?
y=a+bx
a= y intercept
b= gradient
What is Chi-squared?
Tests similarities or differences between two discrete (categorical) variables.
What will Xsquared be if the observed and expected frequencies are the same?
0- the higher the value, the bigger the difference
P-value is used to show significance