Correlations

CORRELATIONS

Description

- An analysis of association between continuous co-variables.

- Correlational hypothesis can be directional (positive or negative correlation) or null (zero correlation).

- Correlation coefficient is a number between -1 and +1 to show strength of correlation.

Positive correlation - dots on scattergram from bottom left to top right, co-variables increase together.

Negative correlation - dots on scattergram from top left to bottom right, as 1 co-variable increases the other decreases.

Zero correlation - no significant association.

Evaluation

​​​​​​- ​In an experiment, causal conclusions can be drawn, but not in a correlation.

- People may act on incorrect causal conclusions, which may be dangerous in some circumstances or a worst, misguided.

- Apparent correlations may be due to intervening variables.

- Measurement of variables may lack validity, poor sampling may mean low generalisability.

- Correlations permit a researcher to identify a relationship that may justify further investigation or may rule out any causal link.