Year 12 Psychology: Psychodynamic Approach (AJW)



How science works: Research Methods 2

Correlational Studies

describe ...(ao1)

• A non-experimental design which tests whether there is an association or relationship between two measured variables called co-variables (there is no independent or dependent variable)

• Pairs of scores (quantitative data) are taken from each participant

• The strength and nature (i.e. positive or negative) of any relationship can be seen in the form of a correlation coefficient

• A correlation coefficient is a number between -1 and +1 where ...

o the sign represents whether the relationship is positive (+) or negative (-): this is called the direction of the relationship

o the closer the number is to 1 (+/-), the stronger the relationship: this is called the strength of the relationship

• Negative correlation (-): if one score is high, the other is low

• No correlation: there is no pattern in the data; the variables are uncorrelated

• The hypothesis in a correlational study could be ...

o directional - “there will be” either a positive or a negative correlation

o non-directional – “there will be a significant correlation”

• Just because two variables are correlated this does not mean that one caused the other

• The media and politicians sometimes quote correlational data and imply causation but this is inappropriate, some mother factor may be affecting both variables

| |

|examples... (ao1) |

| |

|Suggest 2 examples of pairs of variables which are likely to show a positive correlation |

|........................................................... and ........................................................... |

|........................................................... and ........................................................... |

| |

|Suggest 2 examples of pairs of variables which are likely to show a negative correlation |

|........................................................... and ........................................................... |

|........................................................... and ........................................................... |

evaluate ...(ao2)

Strengths:

• May be possible to explore unexpected relationships which can later be followed up in a more controlled way

• Same Pps provide both scores and thus the results are not affected by participants variables

Weaknesses:

• Causality cannot be established as there is no attempt made to control confounding variables (thus not scientific)

• Correlational findings may lack credibility if the scores are taken from scales which are not valid and/or reliable

|Task |

|Suggest 1 example of two variables which may be positively correlated and suggest a third variable which may cause the change in the other|

|two, i.e. Variable 1: number of cases of sunburn is likely to be positively correlated with Variable 2: icecream sales on any given |

|summer day but both variables are likely to be determined by variable 3: temperature. |

| |

|Variable 1: ............................................................ may be positively correlated with |

|Variable 2: ............................................ ......................but both variables may be                determined by |

|variable 3: ........................................................................... |

Analysing correlational data

• Descriptive statistics help to summarise the data; once pairs of scores have been collected they can be plotted on a scattergraph (AKA scatterplot or scattergram) to see whether they points form a trend.

• It is not necessary to calculate measures of central tendency (averages) or dispersion as these are used when looking for a difference between two conditions or groups;

• a correlation looks for an association or relationship between two scores taken from each person and therefore the averages of each set of scores are not of interest

• it may be possible to draw a line of best fit on the scattergraph and this will suggest the direction and strength of any relationship.

• A Spearmans’s Rho is the appropriate inferential stats test to measure the strength and direction of the relationship; this is because it is

o a test of association

o suitable for ordinal or interval data

• This test will produce an observed value (r) a number between -1 and +1 (the correlation coefficient as described above); this is then compared with the appropriate critical value

• When looking up the critical value, you will need to know

o whether you are doing a one or two tailed test

o the number of participants used

o the chosen level of significance, (usually p ................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download