Evaluating The Correlational Research Design Ho
Evaluating the Correlational Research Method
Strengths
There is little manipulation of variables. Measures are often taken of existing situations with few controls needed, which can make for a straightforward design. The two measures are taken and the scores tested to see if there is a relationship. This is quite straightforward compared with some experiments, observations and surveys.
Correlations can show relationships that might not be expected (such as stress Vs. insomnia) and so can be used to point towards new areas for research.
Weaknesses
A relationship is found but without finding out whether the two variables are causally or chance related (“correlation does not imply causation”). When looking to build a scientific body of knowledge it is usual to claim cause and effect relationships between things. So therefore we may not be able to draw a clear conclusion that supports Freuds theory, that Stress will cause insomnia, may in fact not be correct
Correlational designs tend to lack validity because at least one of the variables often has to be operationalised, which tends to make it unnatural. Examples include IQ and mental health scores (or self-report measures of stress and insomnia for that matter). Whenever a score is manufactured there is always the chance that it is not really measuring anything useful. This is because, when asking someone to rate a variable on scale, one person’s opinion on something has a high chance of being different for someone else, for example two people could be under the same level of stress. However one person may place this level of stress as 8 on scale, with 10 being high, and the other person may place this level of stress as 4 on a scale.
Strengths
There is little manipulation of variables. Measures are often taken of existing situations with few controls needed, which can make for a straightforward design. The two measures are taken and the scores tested to see if there is a relationship. This is quite straightforward compared with some experiments, observations and surveys.
Correlations can show relationships that might not be expected (such as stress Vs. insomnia) and so can be used to point towards new areas for research.
Weaknesses
A relationship is found but without finding out whether the two variables are causally or chance related (“correlation does not imply causation”). When looking to build a scientific body of knowledge it is usual to claim cause and effect relationships between things. So therefore we may not be able to draw a clear conclusion that supports Freuds theory, that Stress will cause insomnia, may in fact not be correct
Correlational designs tend to lack validity because at least one of the variables often has to be operationalised, which tends to make it unnatural. Examples include IQ and mental health scores (or self-report measures of stress and insomnia for that matter). Whenever a score is manufactured there is always the chance that it is not really measuring anything useful. This is because, when asking someone to rate a variable on scale, one person’s opinion on something has a high chance of being different for someone else, for example two people could be under the same level of stress. However one person may place this level of stress as 8 on scale, with 10 being high, and the other person may place this level of stress as 4 on a scale.