Data Analysis, Modelling and Research Methods: Qualitative Methods I UNIVERSITY OF DUBLIN TRINITY COLLEGE Department of Sociology MSc in Economic Policy.

Data Analysis, Modelling and Research Methods: Qualitative Methods I

UNIVERSITY OF DUBLINTRINITY COLLEGEDepartment of Sociology

MSc in Economic Policy StudiesDr. Daniel Faas6th March 2015

20.04.23 MSc in Economic Policy Studies: Qualitative Methods I Dr. Daniel Faas 2

Agenda

• Research design: case studies and comparative designs

• Non-probability (purposive) sampling

• Asking questions and conducting interviews

• Discussion of interview exercise for workshop


(a)Design(b)Access and sampling(c)Data collection tools (research methods)(d)Data analysis technique(e)Ethical issues

Also reflect on your own positioning and reflect on the fieldwork process and design overall: reflexivity is key.

How to structure a methodology chapter?

Source: Thomas, G. (2009) How to do your Research Project, London: Sage.


• A structure or framework to guide data collection and analysis. There are five main research designs: experimental, cross-sectional, longitudinal, case study and comparative

• e.g. search for causality, understanding, or generalization

• Research paradigm --> research design --> research method

• Research method refers more to data collection tools/instruments such as interviews, questionnaires, observations

What is a research design?


Five main research designs:

1. experimental2. cross-sectional / survey3. longitudinal4. case study5. comparative

Types of research designs

Source: Bryman, A. (2008) Social Research Methods (Chapter 2)


What is a case study?

A case study is an empirical enquiry that investigates a contemporary phenomenon in depth and within its real-life context, especially when the boundaries between phenomenon and context are not clearly evident. The case study inquiry copes with the technically distinctive situation in which there will be many more variables of interest than data points, and as one result relies on multiple sources of evidence, with data needing to converge in a triangulation fashion, and as another result benefits from the prior development of theoretical propositions to guide data collection and analysis.

Source: Yin (2009) Case Study Research: Design and Methods, London: Sage


The role of theory in case-study research

The complete research design embodies a theory of what is being studied. This theory should by no means be considered with the formality of grand theory in social science, nor are you being asked to be a masterful theoretician. Rather, the simple goal is to have a sufficient blueprint for your study, and this requires theoretical propositions. (…) Then, the complete research design will provide surprisingly strong guidance in determining what data to collect and the strategies for analysing the data. For this reason, theory development prior to the collection of any case study data is an essential step in doing case studies.

Source: Yin (2003): 29; Yin (2009): 35f.


Different types of case studies

Single or multiple case studies

Descriptive

provide narrative accounts

Explanatory

test existing theories

Exploratory

help to generate new theories

Discipline or area-based typology(Historical, psychological, sociological,

ethnographic )

Source: Yin (2009) Case Study Research: Design and Methods, London: Sage


Ambiguities and opportunities in case studies I

• Some say that only qualitative methods should be used in a case study (e.g. John Creswell) whilst others also advocate the use of quantitative methods (e.g. Robert Yin). Case studies are more holistic.

• most frequent objection to case studies is its low generalisability (i.e. external validity) given that only one or a few cases are studied.

• Some question the researcher’s role in relation to the results because of the methods used which can be linked to the personality of the researcher (e.g. participant observations, in-depth interviews).

• The use of a single case can have severe limitations, both in terms of data analysis and generalisability, hence the tendency to compare.

Source: Verschuren (2003) ‘Case study as a research strategy: some ambiguities and opportunities’, International Journal of Social Research Methodology 6(2): 121-139.


Ambiguities and opportunities in case studies II

• Triangulation an important aspect of a case study; and the holistic approach includes looking at the object as a whole and the open-ended approach of the researcher (i.e. questions).

• no a priori codes for interview guides but these gradually emerge from your data analysis and you can either do content analysis or discourse analysis (as we shall discuss later).

• research design emerges and evolves and researcher carries out many activities in a rather unplanned way depending on how things go rather than in a linear-serial structured way as in an experiment or survey. You continuously move back and forth in your design and project stages.

Source: Verschuren (2003) ‘Case study as a research strategy: some ambiguities and opportunities’, International Journal of Social Research Methodology 6(2): 121-139.


• Using the same methods to compare two or more meaningfully contrasting cases;

• Can be qualitative or quantitative;

• Often cross-cultural comparisonse.g. Faas (2010): political identities of ethnic majority and Turkish minority youth across different schools in Europe

• Includes multiple case studies;

• Problem of translating research instruments and finding comparable samples

Comparative design


Equivalence in comparative case studies

• What sort of compromises are necessary to achieve equivalence?• Can we compare like with like in cross-national case studies? • Is equivalence different from notions of comparability?


Different types of equivalence


Toward linguistic equivalence

• Particular care is needed when translating questionnaires and interview schedules; importance of piloting and paraphrasing

• What are you a citizen of?Wo fühlt ihr euch als Bürger zugehörig?

• Do you have friends from other ethnic backgrounds?Habt ihr Freunde, die anderer Herkunft als ihr seid?

• To what extent should minority ethnic people give up part of their customs and traditions to fit in?

Inwieweit sollten Migranten einen Teil ihrer Kultur und Tradition aufgeben um in die deutsche Gesellschaft zu passen?


Toward equivalence of measurement

• Different organisational structures of the German (three-tier system in Baden-Württemberg) and English secondary school system (two-tier system of comprehensives and grammar schools

• Germany has mainly recorded data based on nationality (some changes since 2005 microcensus law). England has collected data based on ethnicity and race (e.g. Chinese, white)

- From ‘white youth’ to ‘native youth’ and national majorities - ‘What about Karagöz? He is German!’; different school databases


Toward conceptual equivalence


Example of comparative case study design

The European and national educational responses to the European and multicultural political agendas

MultiethnicStadtbezirk in Stuttgart

Multiethnicborough in London

Millroad Comprehensive

GoetheGymnasium

Darwin Comprehensive

Tannberg Hauptschule

School policy documents

Questionnaire survey

Focus group interviews

Semi-structured interviews

Level 2: Region

Level 3: Institution

Germany England

Level 1: European and nation-state


Non-probability (purposive) sampling I

1a. Convenience/opportunistic sampling

• the most easily accessible individuals • useful when piloting a research instrument • may be a chance to collect data that is too good to miss

1b. Snowball sampling

• researcher makes initial contact with a small group• these informants lead you to others in their network• useful for qualitative studies of deviant groups


Non-probability (purposive) sampling II

2. Sampling special or unique cases

• critical cases (single archetypal case)• criterion sampling (must have a certain feature)• sampling politically important cases

Note that mixed methods sampling can creatively combine both purposive and probability sampling techniques (e.g. qualitative and quantitative strand of a multi-phase study)


How do social scientists get their data?

Source: http://www.survivalinternational.org/tribes/yanomami


Different kinds of ‘truth’

• Key activity in the humanities is to understand, key activity in the natural sciences is to explain or describe.

• Distinction between the sciences (true/false criterion) and humanities (appropriate, convincing/non-appropriate, non-convincing criterion) since the second half of the 19th century.

• Similar dichotomy between quantitative and qualitative methods; today, a number of academics are in favour of uniting these two fields again; hence our focus later on mixed methods research.


Deductive and inductive approaches


Quantitative and qualitative approaches


• Know your way around the schedule

• Introduce the research- spoken or written rationale- identify yourself, your employer, purposes of research and procedure of interview- ethical issues: anonymity, confidentiality, right to withdraw- opportunity for interviewee to ask questions

• Building rapport- can be difficult if limited time and little opportunity for discussion (closed questions)

Conducting (structured) interviews I


• Asking questions (see slides below)-keep to the schedule: even small variations in wording can affect responses in structured interviews only

• Recording answers-write exact words used by interviewee, or use fixed choice questions in structured interviews only

• Question order- every interviewee must get questions in the same order- general questions before specific questions- first questions should be directly related to the topic- potentially embarrassing or sensitive questions towards the end

Conducting (structured) interviews II


• Probing- when respondent does not understand question or gives insufficient answer- non-directive probes: “mmm”, “can you say a bit more about that?”- repeat fixed choice alternatives

• Prompting- interviewer suggests possible answers- show cards

Conducting (structured) interviews III


• Leaving the interview- thank the interviewee- debriefing should be minimal

• Training and supervision- if researcher hires interviewer(s)- ensure that interviewers know the schedule and follow standardized procedures- assessment: examine completed forms, tape record a sample of interviews, call-backs to respondents

Conducting (structured) interviews IV


Asking questions: Open questions


Closed questions


• Remember your research questions

• Decide exactly what you want to find out

• Imagine yourself as a respondent- how would you answer the questions?- identify any vague or misleading questions- think about questionnaire length, style and attractiveness

Designing questions: basic rules


• Avoid long questions, technical terms, jargon and acronyms

• Avoid double-barreled questions- people may have different answers to each part- no necessary correspondence between partse.g. ‘How much time do you spend on going to concerts and the cinema?’

• Avoid leading questions- suggest that a particular response is desirede.g. ‘Do you think that tuition fees make students less keen to go to university?’

• Include a ‘don’t know’ option

Designing questions: more rules

Data Analysis, Modelling and Research Methods: Qualitative Methods I UNIVERSITY OF DUBLIN TRINITY COLLEGE Department of Sociology MSc in Economic Policy.

Documents