Bivariate Data Flashcards
What is usually plotted on the horizontal and vertical axis?
Horizontal axis- independent variable
Vertical axis- dependent variable
What are control variables?
Non random variables that appear in regular intervals
What does rs = 1 imply about correlation?
It implies that each item of data has the same rank for both variables. This does not mean that the line is straight.
When is it appropriate to use Spearmans rank correlation coefficient?
- when data is given in the form of ranks
- or when data is is not taken from a bivariate normal population (so that it is not appropriate to use the PMCC)
Spearman’s rank correlation coefficient is an example of a non-parametric test. What is a non-parametric test?
In a non-parametric test, no assumptions are made that the samples are from any particular statistical distribution.
When to use a y on x regression line
When you have an x value and you want to predict a y value
When to use a x on y regression line
When you have an y value and you want to predict a x value
Conditions for a hypothesis test involving the PMCC
- Data must be drawn from a bivariate normal distribution, which is indicated by an approximately elliptical shape on a scatter diagram
- Both variables must be random (otherwise cannot be normally distributed)
- r is the PMCC value used as an estimate for p (rho), the null and alternative hypothesis involve rho, not r
Null and alternative hypothesis for Spearman’s Rank?
Ho: There is no association between x and y (in context)
H1: There is some association between x and y (in context)
Null and alternative hypothesis for PMCC?
Ho: ρ = 0
H1: ρ ≠ 0 or ρ > 0 or ρ < 0
where ρ represents population product moment correlation coefficient
Null and alternative hypothesis for Chi-squared?
Ho: There is no association between x and y (in context)
H1: There is some association between x and y (in context)
