Rabia Butt and Klara Valentova are our Q-Step interns from the University of Manchester. Q-Step is a £19.5 million programme designed to promote a step-change in quantitative social science training, funded by the Nuffield Foundation and the ESRC. We asked Rabia and Klara to tell us a bit about themselves and their journey to this internship.
As a second-year undergraduate student, who is currently studying Sociology at the University of Manchester, research, data collection and statistics are a large part of my course resulting in a new-found appreciation for quantitative methods.
The survey method in social research module introduced me to social statistics and the basic statistical concepts required for working with numeric survey data. This module enabled me to participate in the amazing Q-Step programme, which provides placement opportunities for students from the University of Manchester.
I stumbled across the UK Data Service, when I was exploring internship options for the summer. Through this programme I was lucky enough to be selected for a summer internship at the UK Data Service.
I was very interested and curious about where the data originates from and how data it is produced for researches, which is why I choose to do my summer internship here. I am delighted to work for the UK Data Service as I will be learning many new skills, allowing me to gain invaluable experience of a working environment, as well as helping me determine what type of job I would like to go into after I graduates.
I and my fellow intern (Klara) are working together on a project that we will be creating ourselves and presenting it at the end of our internship. The project requires us to calculate the deprivation measures of England, Scotland, Wales and Northern Ireland using the data from the Census of 2011, 2001, 1991,1981 and 1971.
The methodology is Carstairs which is an index of deprivation used in spatial epidemiology to identify socio-economic measures. A definition of deprivation is the damaging lack of material benefits considered to be necessities in a society.
The Carstairs index is based on four Census variables:
- low social class,
- lack of car ownership,
- male unemployment
The overall index reflects the material deprivation of an area.
We will be using the data to calculate the population-weighted mean percentages and standard deviations (SD) for each component variables. Also, to confirm that all components have an even impact on the final score, each variable will be standardised to have a population-weighted mean of zero and a variance of one. Standardising contains subtracting the population mean from each variable and dividing the result by the SD (z-score method).
The variables Carstairs uses are outdated, since it was originally developed in the 1980s. After discovering an article that introduced some new variables into their research, for an example they suggested replacing male unemployment in the Carstairs score with overall unemployment. The reason is to consider the participation of female labour force. We decided to this to our research as well, so we will be using old methodology and including overall unemployment and qualification levels as well.
After we have collected all the data we need, the next step will be learning R language, as we will be using this for our analysis.
Finding and downloading data at first, I thought would be quite easy. However, this was not the case because each census was different from each other, especially the previous ones.
For example, the census for 1991,81 and 71 the social class variable was in 10% for all the countries apart from Northern Ireland. This would cause difficulties when comparing the census with different geographical areas. This was just one of the problems we encountered with the census.
I will be using R to calculate the mean, standard deviations and the z-score for each variable of each year and area. This is a task which I am quite excited about because learning a programming language, would appear quite skillful on my CV and I have never done this before.