correlations

Question 1

correlation

Answer 1

is a statistical technique used to measure or quantify the strength of a relationship between two variables

Question 2

Positive correlation

Answer 2

In a positive correlation the two variables increase together but not necessarily at the same rate.

Question 3

Negative correlation

Answer 3

In a negative correlation as one variables increase the other decreases but not necessarily at the same rate

Question 4

No correlation

Answer 4

There is no correlation between two sets of data

Question 5

correlation coefficient

Answer 5

a measure of the extent of the correlation that exist
when it is calculated it is a number that falls between +1 and -1
The plus or minus sign shows weather it is a positive or negative correlation
+1 is a perfect positive correlation
-1 is a perfect negative corelation
0 would be an example of a no correlation
e.g.
+0.3 weak positive
+0.8 strong positive
+0.5 moderate positive
-0.3 weak negative
-0.5 moderate negative
0.8 strong negative

Question 6

Strengths of correlation

Answer 6

Quantitative data
-provides information about patterns and trends so that if a correlation study indicates a presence or absence of a relationship then further investigation using an experiment can be justified
-can be conducted on variables that can be measured but not manipulated, cab be used to research topics that are sensitive/otherwise would be unethical
-procedures in correlations can be repeated, findings can be confirmed to cheak reliblity

Question 7

Weaknesses of correlations

Answer 7

-cannot be taken to imply causation, even if very strong association between two variables, cannot assume one causes the other
- show linear relationships but not reflect curvilinear once, findings not always valid as they don’t reflect the full picture
-‘third variable may be a intervening variable that can explain the co-variables being studied are linked

Question 8

Reliability in correlations

Answer 8

-can be repeated to get the same or similar results so is consistent
-concerns about the consistency of the measures used, findings of correlations analysis will only be reliable if measures of both DV are consistent
-some correlations like scientific scales (volume, time) measures will be reliable
-other cases self reports method rating scale estimate, observations the reliability will be lower

Question 9

validity in correlations

Answer 9

to be valid correlations need to be reliable
- correlations will only be valid if measures of both variables measure real phenomena in effective ways, to achieve this the DV must be defined and measured effectively