What is a correlation?
Correlational research looks for relationships between variables. Correlation means that two variables rise and fall together, or that one rises as the other falls - but not always that one variables causes a change in the other - you cannot establish cause and effect. Correlation refers to a measure of how strongly two or more variables are related to each other.
Correlation means association, more precisely it is a measure of the extent to which variables are related. If an increase in one variable tends to be associated with an increase in the other then this is called a positive correlation. If an increase in one variable tends to be associated with a decrease in the other then this is called a negative correlation. When there is no relationship between two variables is known as a zero correlation.
Correlation can be expressed visually by drawing a scattergram. Instead of drawing a scattergram a correlation can be expressed numerically as a coefficent.
An experiment isolates and manipulates the IV to observe its effect on the DV, experiements establish cause and effect. Whereas a correlation identifies variables and looks for a relationship between them. A correlation can only predict a relationship, as another extraneous variable may be the cause.
Correlation (Strengths and Weaknesses)
Strengths-Correlational analysis can give ideas for future research, because correlational research does not involve controlling any variables it can be done when for practical for ethical reasons you couldn't do a controlled experiment, good for showing possible relationships.
Weaknesses-Correlational analysis cannot establish 'cause and effect' relationships it can only show that there is a statistical link between the variables as only a controlled experiment can show cause and effect relationships, care must be taken when interpreting correlation coefficients - high correlation may be down to chance.
Correlation (Hypotheses for correlational analysis
A hypothesis is a testable, predictive statement. The hypothesis will state what the researcher expects to find out. It is important that the two variables are clearly stated in the hypothesis. When a hypothesis predicts the expected direction of the results it is callled one-tailed. e.g there will be a signficiant positive correlation/relationship between average GCSE scores and performance on a memory test.
When a hypothesis does not predict the expected direction it is referred to as a two-tailed hypothesis. e.g there will be a significant correlation between average GCSE scores and performance on a memory test.
The hypothesis states the expected results is called the alternate (correlational) hypothesis as it is alternative to the null hypothesis. When conducting a correlation it is important that we have an alternate hypothesis and a null hypothesis. The null hypothesis is not the opposite of the alternative hypothesis it is a statement of no relationship/no significant relationship. The reason we have a null hypothesis is that the statistical tests that we use are designed to test the null hyptohesis.
Never write a hypothesis for correlation that includes the words, difference, cause or effect.
Every correlation has two qualities: strength and direction.
A correlation coefficient refers to a number between -1 and +1 and states how strong a orrelation is. If the number is close to +1 then there is a positive correlation, if the number is close to -1 then there is a negative correlation, if the number is close to 0 then the variables are uncorrelated. The size of the number shows how closely they are related - weak or strong.
We determine the strength of a relationship between two correlated variables by looking at the numbers. A correlation of 0 means that no relationship exists between the two variables, whereas a correlation of 1 indicates a perfect positive relationship. It is uncommon to find a perfect positive relationship in the real world. Chances are that if you find a positive correlation between two variables that the correlation will lie somewhere between 0 and 1.
The further away from 1 that a positive correlation lies, the weaker the correlation. Similarly, the further a negative correlation lies from -1, the weaker the correlation. A correlation of 0.5 is not stronger than a correlation of 0.8. A correlation of -0.5 is not stronger than a correlation of -0.8.
Two correlations with the same numerical value have the same strength whether or not the correlation is positive or negative. This means that a correlation of -0.8 has the same strength as a correlation of 0.8.
Correlational analysis always involves quantitative data. Carrying out a correlation involves a lot of data - so there needs to be a knowledge of statistics and statistical tests as to make conclusions about the data.
Descripitive statiitcs give us a way to summarise and describe our data but do not allow us to make a conclusion related to our hypothesis.
When carrying out a correlational analysis the data is summarised by presenting the data in a scattergram. It is important that the scattergram has a title and both axes labelled. From the scattergram we may be able to say whether there is a strong positive correlation, a weak positive correlation, no correlation, a weak negative correlation or a strong negative correlation but we can not make a conclusion about the hypothesis.
Two main ways of summarising the data using descriptive statistics - measure of central tendency, summarising and describing data by calculating a measure of dispersion (range).
Inferential statistics - make an inference about the data, which hypothesis offers the best explanation.