Stats Topic 2 Flashcards
Correlation
measures the strength and direction of the relationship between two numerical variables.
Positive correlation
Both variables increase together.
Negative correlation
One variable increases while the other decreases.
No correlation
No systematic relationship between variables.
correlation coefficient (r)
quantifies this relationship, ranging from -1 (perfect negative correlation) to +1 (perfect positive correlation). A value close to 0 indicates little or no linear relationship.
Sampling variability
refers to the natural fluctuations in statistical measures when different samples are taken from a population.
Affecting Sampling Variability
- It affects the stability of correlation coefficients—smaller samples show more variability.
- Larger samples reduce sampling error and yield correlation estimates closer to the true population value.
- Research relies on inferential statistics to estimate population patterns based on sample data.
Statistical tests
assess whether an observed correlation is likely to exist in the population or if it occurred by chance.
The null hypothesis (H₀)
states there is no correlation in the population.
The alternative hypothesis (H₁)
suggests a real correlation exists.
p-value
indicates the probability that the observed correlation is due to random chance
Degrees of freedom (DF)
in correlation tests are calculated as N - 2, where N is the sample size.