Quantifying categories

#1
As part of academic coursework*, I will be using the earliest UK Census data to attempt to derive an economic performance indicator per region (local authority) in England. The intention is to compute a number per region indicative of its economic performance but I am unsure if this should be an index of some sort or whether a computed average income would be more correct. Then, I intend to use the derived economic performance indicator to predict (or not) primary school achievements (KS2).

The dataset contains the number of people per region and occupation. The problem I have is the occupations do not have associated income bands that I know of; I was certainly unable to find information on this or any official guidance.

What is the best way of quantifying the categories below? Are there median income values associated with each and, if not, can one be derived somehow?

1. Higher managerial, administrative and professional occupations
2. Lower managerial, administrative and professional occupations
3. Intermediate occupations
4. Small employers and own account workers
5. Lower supervisory and technical occupations
6. Semi-routine occupations
7. Routine occupations
8. Never worked and long-term unemployed
9. Not classified

EDIT
Some additional information. Each row in the census dataset I was provided with looks like the following:

"Darlington","E06000005",85357,6993,16990,12350,6424,6699,14235,11702,5380,4584

The first column refers to the region name, which is followed by a code that identifies it in the second column. The fourth and following columns refer to the categories listed earlier and each contains the number of people who reported having the occupation. Finally, the third column contains the sum of all people (sum of fourth to last columns) who completed the census in a given region.

Back to my original question, what is the best way of deriving an economic indicator or overall income, per region?

--
* My course is on data management & analysis and not statistics.
 
Last edited:
#3
Unfortunately I'm constrained in the datasets that I can use. I must specifically use the UK Census dataset I was provided with, however I can ask what I please from the data. I chose to derive an economic performance indicator from it but, as stated in the OP, I'm not really sure how to do this given that there is no official guidance (that I can find) on a mapping of income to occupation.

I will update the OP with additional details.
 

j58

Active Member
#4
Unfortunately I'm constrained in the datasets that I can use. I must specifically use the UK Census dataset I was provided with, however I can ask what I please from the data. I chose to derive an economic performance indicator from it but, as stated in the OP, I'm not really sure how to do this given that there is no official guidance (that I can find) on a mapping of income to occupation.
You said you could compute "average" (which I assume means per capita) income of each region. My question was, isn't that, by definition, the economic performance of a region. If so, then why do you care about the distribution of occupations in each region.
 
#5
You said you could compute "average" (which I assume means per capita) income of each region. My question was, isn't that, by definition, the economic performance of a region. If so, then why do you care about the distribution of occupations in each region.
Oh, I see. Apologies, I misunderstood your comment!

It seems I have not made my original post very clear because I meant to express uncertainty on whether I should aim to compute an economic indicator or an income (per capita or not) per region. As to how either of these should be derived, I do not know, and was hoping someone might show me a way forward. All I have are the occupations and number of people for each of these, all of which on a per region basis.