Data Collection and Sampling
Primary Data There are various methods for collecting primary (original) data –Eg questionnaire, survey, interview, observation Control over investigation much greater Can more easily avoid “data-driven” research Cost can be prohibitive Pilot studies can be very helpful
Choice of method Shipman: choice often between sampling and case study Intensive versus extensive research design Qualitative versus quantitative data Interpretivists favour the former; positivists favour the latter All primary research involves selection Most methods require sampling
Sampling: general principles No a priori superiority of any method Trade-offs: standardisation versus control, generalisability versus flexibility Shipman: sampling method used dependent on nature of study undertaken Basis for sample must be transparent Cost of surveying entire population is prohibitive (e.g. census) Constraint of feasibility
Sampling: definitions Population: must be defined Finite population: e.g. voters Sampling unit: single potential member of sample Sampling frame: list of sampling units (NB 1936 US Presidential election) Sample: drawn from sampling frame
Probability Sampling Probability of each sampling unit being chosen is known (often equal probability) Simple random sampling: classic method, regarded as most reliable, least biased List numbered sampling frame members and select via random number generator Other probabilistic methods are available
Systematic sampling List members of sampling frame Choose first sample member randomly Then choose every K th unit, where K=N/n More convenient than SRS for large pop n Can be a systematic pattern in sample list, leading to bias; e.g. corner shops
Stratified sampling Divide population into groups of alike members Strata sizes usually proportionate to pop n Draw randomly from groups Cost effective Ensure representativeness Can lead to excessive number of sub-groups
Cluster Sampling Select large groups Select sampling units from clusters randomly Example: take a city, divide into areas, number areas, select areas randomly, number units within areas, select units randomly Very cost-effective Very good if sampling frame poorly defined
Non-probability Sampling Convenience sampling: select whoever is available Quota sampling: collect data according to proportions of the population Selection of subjects absolutely crucial Requires great skill of interviewers Snowball sampling: select next subject from previous subject
Non-Probability Sampling Theoretical sampling: select those most likely to be affected by an issue Can ignore things which do not fit Can interpret observations according to the theory Non-prob sampling cannot claim representativeness as easily but gives much more discretion and control
Response Rates Another possible trade-off is on response rates R = 1 - (n-r)/n Even if initial sample size is appropriate (n’ = n/(1+(n/N)) where n = s 2 /SE 2 : see F-N and N: 194-9) response rates can be low Postal questionnaires: typically 20-40% Non-response bias
Response Rates Non-respondents could affect findings If reason for non-response is related to issue: e.g. reluctance to interview drunks hampers study on alcoholism Response rate can be improved by cover letter, callbacks, skill of researcher, length of questionnaire, types of question
Conclusions All types of primary data require selection If sampling used: various methods possible Sampling method relates to research tool Different data collection techniques: questionnaires, interviews, etc. - all to be studied in Research Methods 2 - all have advantages and disadvantages
Secondary Data
Introduction Primary quantitative data has several advantages, particularly control; qualitative data too Do not equate primary and qualitative Today: advantages of secondary data Searching on electronic data sources including the Internet
Secondary data Primary/secondary is not = qualitative/quantitative Qualitative can include secondary data sources such as personal documents, auto/biographies, etc. Secondary: collected by someone else, e.g. another academic researcher, business, government agency, etc.
Secondary data Used extensively in social science –Durkheim: suicide –Marx: wages, incomes, prices –Weber: church records Economists mainly use secondary data
Advantages of Secondary Data Might be the only data available Enables longitudinal /time series work Cheaper (cost and time) and more convenient than primary data Aids generalisation Arises from natural settings (nonreactive/unobtrusive data) Allows replication and checking - validity
Disadvantages of Secondary Data May be not exactly the data required Differences in underlying sampling, design, questions asked, method of ascertaining information, etc. Differences lead to bias Method of data generation crucial to econometric studies
Electronic Data Sources Through the library system Through the internet Known versus unknown sources Known sources via library catalogue Problem of reliability/credibility is common to all electronic sources (more than non- electronic sources)
Electronic Data - Literature You can search by author or subject across journals, via several static websites/portals:
Electronic Data: Databases There are many databases available online Most have standardised, national data free to download in various formats Common file format is.csv; but.html and even.xls files also common
OECD: ONS: UN: Penn World Tables: BEA (US): Ameristat: Eurostat: World Bank: CIA: US Statistical Abstract: See Dissertation homepage/hb
Conclusions Secondary data has many advantages and disadvantages relative to primary There is a wide range of secondary data available Much data is available on the internet Internet sources must be scrutinised more closely than other sources
Qualitative Data
Introduction Principals of research design and sampling basically hold for quantitative and qualitative data However, they apply most easily to quantitative analysis Qualitative analysis has different foci Qualitative analysis relatively (to quant; other soc sci) unused in economics
Qualitative techniques: types Case study Fieldwork (ethnography) Observation Unstructured interviews Analytic induction/grounded theory Discourse analysis Theoretical sampling
Qualitative techniques: principals Qual often = not quantitative Can use quant for pattern detection, qual for causal analysis Or use qual and quant as equals in inference (triangulation) Quantification often inappropriate
Qualitative techniques: principals Interpretivism, verstehen Used to be associated only with using autobiography, letters, personal documents, diaries Ethnography fairly recent: Focus on cases rather than generality
Qualitative techniques: principals Analysis not really a separate stage of research Design, data collection and analysis all simultaneous and continuous Open-ended approach: Theory and conclusions formed iteratively Imagination is crucial Recognise importance of exceptions Context is crucial
Fieldwork Study of people acting in their daily lives Access a group but remain somewhat detached Approach with key questions Teams get range of perspectives Danger of self-perception and bias
Participant Observation Adopt perspectives of subject group in order to understand them Learning language, customs, behaviours, work, leisure, etc. Hanging around and learning the ropes Being an outsider can changes subjects’ behaviour Complete participation - researcher wholly concealed – contamination and artificiality
Participant Observation Researchers can go native (internalise group lifestyle) Covert researchers can be in danger or create detrimental behaviour Researchers can be “piggy in the middle” Covert: recording observations can be difficult (e.g. need hidden cameras) Serious ethical issues with covert observation
Employ analytic induction Go in with prejudices and theories Revise theory in light of evidence Generate new theories until evidence seems to fit Flexibility accorded but also required by the researcher Need to be open to disconfirming cases
Grounded theory Data collected Develop categories (with inevitable theoretical priors and language) Categories checked by data Once categories seem secure and grounded in the evidence, formulate interconnection between categories
Evaluation Broad range of qualitative techniques Control over the investigation; less data driven; flexibility much greater than quantitative studies Logistically difficult: Huge amounts of data produced and problems with manipulation (although Nvivo will help with this) Must be careful to collect evidence widely to avoid bias Can be ethical issues re: data collection and reporting