Help with correct statistical analysis?

#1
I am conducting an audit into vitamin D deficiency in children.

I have the mean serum concentrations of vitamin D in specific areas (postcodes) as well as the percentages of individuals in those postcodes that hold a degree or professional qualification and would like to see if there is a correlation between the two.

I would also like to see if there is any correlation between mean serum vitamin D concentrations in a postcode and the percentage of the population that is non white.

I appreciate any help as my med school have been very unhelpful in this matter.

Thanks.

BRYAN.
 

Karabiner

TS Contributor
#3
Do you also have individual data?

For aggregated data, you could perform correlation analyses (Pearson correlation and/or Spearman's rank correlation) between vitamin D level and percentages. Maybe you could include additional variables which culd help explain any (non-)associations found (confounding variables, moderators), but this depends on sample size (=number of areas included).

With kind regards

Karabiner
 
#4
Do you also have individual data?

For aggregated data, you could perform correlation analyses (Pearson correlation and/or Spearman's rank correlation) between vitamin D level and percentages. Maybe you could include additional variables which culd help explain any (non-)associations found (confounding variables, moderators), but this depends on sample size (=number of areas included).

With kind regards

Karabiner
Hi unfortunately I only have means .
 

hlsmith

Omega Contributor
#5
Can you provide an example of data you have? Ideally you would also control for postal codes next to each other (spatial correlation).