Z-test for Correlation
Jump to navigation
Jump to search
A Z-test for Correlation is a parametric correlational hypothesis test of continuous variables that is based on a z-test statistic.
- Context:
- It can be described and solved by the following procedure:
- Test Requirements:
- Input Data : Pairs of continuous random variables [math]\displaystyle{ (X_i, Y_i) }[/math] corresponding to the values of a bivariate random sample of size [math]\displaystyle{ n }[/math] (i.e. [math]\displaystyle{ (i=1,...,n) }[/math]. Each pair must be bivariately normally distributed as well as independent and identically distributed.
- Input Parameters: a sample correlation coefficient, [math]\displaystyle{ r(X,Y) }[/math], a significance level value ([math]\displaystyle{ \alpha_0 }[/math]) to be used in the decision rule approach.
- Hypotheses to be tested:
- [math]\displaystyle{ H_0 :\; \rho_0=0 }[/math] - null hypothesis states the population correlation coefficient is 0; there is no correlation.
- [math]\displaystyle{ H_A :\; \rho_0 \neq 0 }[/math] - alternative hypothesis states the population correlation coefficient is not 0; there is non-zero correlation.
- Test Method and Sample Data Analysis:
- Test Statistic: z-test statistic for correlation is given by
- [math]\displaystyle{ Z_{r,n-1} = \frac{\sqrt{n-3}}{2} [ln (\frac{1+r}{1−r})−ln(\frac{1+\rho_0}{1−\rho_0})] }[/math], with [math]\displaystyle{ r }[/math] being the sample correlation coefficient.
- Decision Rule: Null hypothesis is reject if P-value is less than [math]\displaystyle{ \alpha_0 }[/math] or if the z-test statistic value follows outside region of acceptance.
- Results and Interpretation:
- Test Requirements:
- Counter-Example(s)
- See: Correlational Hypothesis Test, Correlation Coefficient, Autocorrelation, Cointegration.
References
2017
- (Stat 415, 2017) ⇒ Intro Mathematical Statistics: Three Tests for Rho https://onlinecourses.science.psu.edu/stat414/node/254
- (...) Theorem. The statistic:
- [math]\displaystyle{ W=\frac{1}{2}ln\frac{1+R}{1−R} }[/math]
- follows an approximate normal distribution with mean [math]\displaystyle{ E(W)=\frac{1}{2}ln\frac{1+\rho}{1−\rho} }[/math] and variance [math]\displaystyle{ Var(W)=\frac{1}{n−3} }[/math].
- The theorem, therefore, allows us to test the general null hypothesis H0:ρ=ρ0H0:ρ=ρ0 against any of the possible alternative hypotheses comparing the test statistic:
- [math]\displaystyle{ Z=\frac{\frac{1}{2}ln\frac{1+R}{1−R}−\frac{1}{2}ln\frac{1+\rho_0}{1−ρ0}}{\sqrt{\frac{1}{n−3}}} }[/math]
to a standard normal N(0,1) distribution.