correlations Flashcards
what is a correlation?
a correlation is the measurement of the extent to which pairs of related values on two variables tend to change together, they simply describe the relationship between two variables in statistical terms
what research methods can we collect correlational data from?
observations, questionnaires (self report methods), etc
what are correlations describes in terms of?
co-variables, this is because both variables in a correlation vary and are measures, and neither one is set or controlled by the researcher
what is a correlation coefficient?
this is how the strength of a correlation is described, they range from -1.0 to +1.0, with a coefficient of less than zero describing a negative correlation and one above zero describing a positive correlation. you should consider 0 - 0.3 as weak, 0.3 - 0.7 a moderate and above 0.7 as strong
what is a scatter gram?
this is one way to investigate the relation ship between two variables (by plotting a variable on each axis). they have one co-variable on the x-axis and the other on the y-axis and a line of best fit is drawn, it is also possible to get an anomaly in your results
what is a positive correlation?
this describes a relationship in which both variables increase together, making. straight line of closely plotted points that slope up from left to right. the stronger he positive correlation, the closer together the points will be
what is a negative correlation?
when points slope down from the top left to the bottom right. the stronger the correlation is, the closer together the points will be
what is a zero correlation?
this is when there is no relationship between the two co-variables as there is no clear pattern showed with plotted data
what is a curvilinear relationship?
a curve shaped correlation (like an n shape), e.g. this can represent exam sore and anxiety, both high and low anxiety could lead to a lower exam score
strengths of correlations
- one strength is that they control for ppt variables. because both sets of data are provided by the same person, each ppt effectively acts as their own control. therefore, individual differences won’t occur meaning that results will be more valid sa they’re less likely to be skewed
- correlations are a practical method of data collection, they are carried out with relative ease and nothing needs to be artificially set up as they use self report methods. therefore they can be easily carried out and may lead to further research on relationships between two co-variables, this can give us a greater understanding of the world
weaknesses of correlations
- one weakness is that thy cannot infer cause ad effect. correlations can only identify links between variables and it may be possible that there is a 3rd unknown variable that has impacted the results. therefore, thee is low internal validity that may lead to incorrect conclusions being drawn
- there are problems with using secondary data, correlations a use secondary data e.g. hospital records and these may be out-dated or have been subject to bias interpretation. therefore, conclusions made on relationships between co-variables will have decreased validity
