Statistical Analysis Test(s) Selection  ?

Im studying the relationship between the provision Public Toilets and marginalization  in 5 Canadian cities. I need help in the selecting a statistical approach to test my hypotheses.  

Research question 1: Does the degree of marginalization influence the frequency of 

H1: As quintile scores for a given dimension increase from least to most marginalized, normalized Public Toilets frequency will decrease. 

H2: Areas with the greatest degree of Residential Instability and Material Deprivation will have the lowest frequency  of Public Toilets.  

marginalization is expressed as quintiles (ordinal & discrete) ranked from one (least marginalized) to five (most marginalized). Each group contains a fifth of the geographic units. E.g. if an area has a value of five on the material deprivation scale, it means it is in the most deprived 20% of areas in Ontario. Public toilet data are discrete points. Using the image attached to explain, im using Census Tracts as my geographic units. Census tracts will range from 1 (least, lightest color) to 5 (most, darkest color) based on their degree of marginalization. To get public toilet frequency i've summed all the census tracts of a given degree of marginalization (1,2,3,4 or 5) and normalized by the total population of all census tracts at a given level. This is shown in the bar chart.Note, the example below is only 1 city. This was repeated for 4 other cities. What are some suggestions on how i would test my hypotheses? 

    

      

Attachment image
There are no answers yet.
Be the first to answer this question.