The Research Competition
Here you will be making concrete decisions about the forms, techniques and instruments required to collect your data/information. Research designs often involve choosing multiple items (mixed-methods design).
For instance, if you were planning a history paper on the impact that Gandhi had on religious conflict in pre-independence India, you would adopt a mixed-methods design:
This decision board is unique in that it ranks data/information by the researchers’ level of direct involvement with human subjects.
The word “data” refers to raw facts or scores that have not been processed. Interview transcripts, speeches and test scores are all forms of raw data. Information refers to data that have been processed, grouped, coded or interpreted in a way that transforms the raw data into more meaningful information.
Forms of data/information are represented by numbers or quantities in quantitative forms of data and by words, concepts or images in qualitative forms of data.
It is a misconception to presume that “real data” are obtained only using direct methods of experiment or surveys and that they are exclusively in the forms of numbers.
All forms of inquiry in the social sciences – for anything from a historical essay to a psychological report, in qualitative or quantitative form – require the use of evidence, meaning forms of data/information that are appropriate for addressing the question.
Interestingly, most social science writing uses various forms of data/information that are obtained without direct human contact, as listed in the last column of item 2.1. Direct forms obtained through experimentation, surveys or fieldwork are not common in post-secondary student research. Gathering data directly from human subjects is time-consuming, expensive and ethically questionable, and it requires high levels of training and skill to perform properly. As well, informed and voluntary consent of adult subjects must be secured.
Data derived from experimentation is usually in the form of quantitative observations regarding behaviour that is measured in a standardized way so that the differences between pre-test and post-test results, for instance, or between groups can be tested statistically.
This category refers to experimental data that you plan to obtain, not information about experimental data that others have obtained.
Data derived from survey questionnaires are intended to provide you with an aggregate picture from a sizeable sample. As such, the data are usually quantitative in form. Though the questions can be forced response questions or open-ended questions, for ease of processing and analysis, most questions in a survey questionnaire use forced-response questions.
This category refers to data that you plan to obtain directly from human subjects of your choosing, not information about survey questionnaire findings from published sources.
Recorded and transcribed interview data are intended to provide in-depth information, rather than a large volume of aggregate data. One-on-one semi-structured or unstructured interviews or even oral histories are particularly useful for discovering people’s thought processes and for hearing about life-changing stories.
Focus groups are often used by marketing firms or political parties to assess reactions to a new campaign or a unique product or policy. The members of a moderated focus group dynamically exchange ideas and concerns. Focus groups, sometimes referred to as group interviews, can generate qualitative as well as quantitative forms of data.
This category refers to data that you plan to obtain directly from human subjects of your choosing, not information about interview or focus group findings from published sources.
Field research (participant observation or ethnography) generates many forms of data which are usually contained in a field notebook. This may include details of onsite observations, critical reflections, jotted notes from informal discussions, photographs, drawings, social maps, recordings of performances such as recitations, dancing, singing or ceremonies, as well as collected artifacts such as flyers, recipes…
This category refers to data that you plan to obtain directly from field sites of your choosing, not information about fieldwork or ethnographic findings from published sources.
Data derived from observing people in public places without their knowing they are being observed is one step removed from direct field observations where the researcher actively interacts with research subjects in the field.
Non-participant observation is a form of unobtrusive observation; there is no direct contact or interaction. Research subjects are unaware they are being observed.
This is useful for behaviour that people may not reliably be able or willing to share with an interviewer. Some examples of behaviours not reliably measured with reactive methods are socially undesirable behaviour such as littering or eating junk food. The observations are usually recorded on some sort of observation or code sheet. This form of observation is ethically restricted to public places and to observing behaviour of adults that would not directly jeopardize their professional, personal, social or mental well-being as individuals or as an identifiable group.
This is data derived by recording signs or indicators of behavioural patterns by examining materials or objects that people may have used, left behind or worn down through repeated use. Instead of asking people which foods they prefer, for instance, you would take stock of their recycling bin or trash can. The observations are usually recorded on some sort of observation or code sheet.
This refers to forms of data that have been gathered and formed into a collection or a production, such as academic books, archival collections or documentary films.
With advances in information and computer technology, vast stores of high-quality data are readily accessible to the public. Student researchers are thus hard-pressed to justify going out to collect their own raw data.
The Diary of Anne Frank is a classic example of a source of information that is readily available. Frank’s story provides insight into the personal experiences and inner thoughts of an adolescent while she was living in hiding for two years in the Nazi-occupied Netherlands.
Using available data is often a default position for certain topic areas as it is unethical for researchers, especially student researchers, to directly interview vulnerable, traumatized subjects – those who attempt suicide, lose a spouse or battle with drug addiction or childhood abuse, for example.
Data that have been collected by government agencies and organizations (e.g., official statistics, reports, articles, budgets, policy statements, public records such as birth, graduation and death…) are usually of very high quality. This type of data has usually been processed (classified, indexed, grouped, graphed and/or analyzed) by researchers and other professionals and is made available as information to the public. Statistics Canada is a well-known example of a national statistical agency. Most countries support nationwide statistical organizations. Government agencies are prolific data producers especially when it comes to variables that directly impact the provision of government services. Health, education, socio-economic status and employment are typical subjects covered.
The World Bank is a prime example of such an organization. Immense amounts of country-based data are available for analysis in easy-to-navigate and user-friendly formats (e.g., reports, records from meetings, proceedings or conferences…). Other popular examples are the Royal Statistical Society and the World Food Program.
Polling firms such as Léger Marketing and PEW are but a few of the many firms worldwide that collect mostly quantitative forms of data on such topics as voter intentions, consumer behaviour and public policy choices. Summaries, as well as full reports of many of their findings, are readily available online.
The results of research findings that have been deemed of high-quality (e.g., published in books/journal articles/monographs)through some form of professional peer review are typically communicated in published books, journal articles, monographs and even government reports.
Useful data can be culled from a book written by an academic or a person with status and experiential knowledge, such as a diplomat who helped negotiate a peace settlement or a doctor writing about clinical practice. One such example is an e-book published in 2006 by Jeff Ferrell, a sociologist and self-avowed dumpster diver, titled Empire of Scrounge: Inside the Urban Underground of Dumpster Diving, Trash Picking, and Street Scavenging in which he provides firsthand, detailed accounts from the street.
Detailed descriptions, firsthand accounts or interview excerpts can be found in published studies and extracted for use in your own study. For example, a student researching female fighters in recent Western African civil wars found an existing fieldwork study on Sierra Leone containing detailed interview and testimony excerpts as well as a link to a treasure trove of statistics in a 2005 Save the Children publication titled “Forgotten Casualties of War: Girls in Armed Conflict.”
Primary sources are used to gain insight into an individual, group, event or particular period of time. (e.g., recordings, constitutions, declarations, bills, treaties, letters, speeches, personal correspondence, diaries, memoirs, notes, photographs, scrapbooks, portfolios, schedules, recipes… often stored in digital archival collections or remnants found on site such as inscriptions, clothing, tools, furniture, logs, photographs…)
Primary sources and artifacts are typically available in archived or private collections. Archives are classified or catalogued collections of articles, letters, photos, documents, films, etc., that are stored electronically or physically. Many organizations and government agencies maintain and support such archive collections. Hundreds of online collections are used by social scientists on a daily basis.
Data take numerous forms under this particular banner. Anything to do with communications – official or unofficial, digital or print, image or text – is eligible for collection and analysis. These varied forms (e.g., photos, videos/documentaries from websites, news sources, radio, television, films, advertising, billboards, music, documentaries, video games, Internet, listservs, blogs, advertising, announcements, press releases…) provide insight into the messengers (e.g., journalists, advertisers, documentary filmmakers…) and the messages.
For instance, photographs, often referred to as visual texts, are representations that can reveal much information about the subject matter, the photographer and the context in which the images were produced. Photos are typical forms of data for content analysis, an unobtrusive research method.
Video documentaries, TV and radio talk shows provide access to worlds inhabited by all sorts of people from a variety of backgrounds and professions, from ballet dancers to criminals. Documentaries such as Woodstock (1970) or Michael Apted’s series of films 28 Up (1984), 35 Up (1992) and 42 Up (1999) provide video views of lives, lifestyles and expert analysis.
Expressive artistic productions (e.g., paintings, poems, novels, lyrics, folk tales, legends…)are legitimate sources of data for analyzing aspects of a movement or a sector of society at a particular time. The data are usually ordered into anthologies or coded into genres.
Ghost stories, nursery rhymes and even urban legends or conspiracy theories are legitimate sources of data, especially if the goal of your study is to reveal themes or cultural markers that express a way of life or way of telling tales about a way of life. Folklorists, for instance, systematically study the meanings that can be derived from such tales.
Scientific norms and rules govern how to collect data. Text books and professional guides detail how each of these techniques should be used. The respective strengths and weaknesses of each technique selected must be understood and recognized.
Experiment is a technique used to test for causation or association between X (independent or explanatory) and Y (dependent or response) variables.
Used mostly in the field of experimental psychology, it is considered one of the most intrusive and reactive techniques.
There are dozens of experimental designs. The classic design is a randomized comparative experiment in a highly controlled setting. It typically involves randomly assigning subjects to groups, usually an experimental group and a control group, to measure for differential reactions to an administered treatment. A pre-test/post-test design is also classic.
Only repeated trials of the most rigorous and controlled experiments can provide standard proof of a cause-effect relationship. It took over 60 years and 300+ experiments to finally “prove” that cigarette smoking “causes” lung cancer. For this reason, do not assume that any single experiment can prove a cause-effect relationship.
There are also quasi-experimental techniques that are less rigorous and controlled than so-called true experiments. They are not designed to determine statistical significance or causation. Instead, quasi-experiments are used to better understand changes as a response to controlled/uncontrollable treatments, treatments that cannot be prearranged. Of the many possible designs, one popular one is the natural experiment, in which the researcher measures changes in a post-hoc (after-the-fact) test for differences. Childhood malnutrition is a typical example of when a treatment (i.e., imposed starvation) cannot be administered and then tested.
Surveys are generic for a range of techniques for questioning people: ranging from questioning a large number of people, as in a census or poll, to unstructured one-on-one interviews.
Quantitative surveys gather aggregate data on opinions, beliefs, habits and knowledge, using a questionnaire. Since the aim is to obtain a large quantity of data that can be uniformly input using software, forced-response categories are the norm. The data are then usually grouped into tables and graphs and number summaries. Statistical analyses such as chi-square, correlation coefficients and t-tests can also be conducted on data drawn using a quantitative survey technique.
A focus group is essentially a group interview of approximately 5 to 10 people. It is one of several survey method techniques for gathering data by questioning people. Quantitative or qualitative data can be derived from this technique. Popular with marketing and polling firms, it can be used to ascertain the needs and concerns of consumers with regard to a trial product or a new political candidate or policy.
Conducted mostly with open-ended questions and probes in a semi- or unstructured way, it aims to produce detailed explanations and rich descriptions, usually from a small number of individuals. The responses are usually transcribed from a recorded tape of the interview into a verbatim (word-for-word) written transcript. It is one of several survey method techniques for gathering data by questioning people. Qualitative interviews are often used in conjunction with other techniques such as case studies. They provide descriptive accounts that are rich in detail and particular to the person being surveyed.
This technique involves unobtrusive observation in a natural setting. Since the research subjects have no knowledge of being observed, there is no interviewer bias. Ethical rules restrict such observations from taking place anywhere other than open, well-populated public places.
Field research or fieldwork is a very involved, multi-method design. The researcher becomes immersed in a natural field setting over a period of time and uses any number of data gathering techniques, ranging from field interviews to unobtrusive observation of behaviour. The written account of the research is often referred to as ethnography, a rich descriptive account of the field experiences typically incorporating photographic images and diagrams, maps, stories and so on.
One famous field study involved pool room hustling and was conducted by Ned Polsky in the 60s. Most commonly used in anthropology, it is also widely used in sociology and non-experimental psychology.
“Doing history” generally involves the analysis of a collection of primary and/or secondary data relative to particular periods, people or events in the past. Historical data can be quantitative, as in census data, for instance, or qualitative, as in diaries. Historical quantitative data can be analyzed by either tracking trends or comparing cases over time or by identifying or associating distinct patterns in aggregate data sets.
It also involves appreciating historical data for what it offers: often incomplete, selective artifacts or accounts from which very limited inferences can be drawn. It requires an evaluation of the previous research questions and the tentative answers generated, because knowing the source of the information and understanding how to evaluate its veracity is as important as the content of the data itself. As humble and limited as the analysis appears, historical analysis demands careful and guarded inferences, from the specific to the general, and an appreciation of the multiple factors involved in analyzing history. Comparing one period to another or one place to another provides some weight to the analysis.
The case study technique involves focusing on a particular individual, organization or group, such as a corporation, non-profit agency or religious cult, to name a few. The goal of a case study is limited to descriptively detailing how a particular case operates or develops within the specific parameters of the environment. A number of techniques are typically used to collect the data/information, ranging from available data and information to interviews with key stakeholders or informal field studies involving attendance at events, ceremonies or meetings.
“Physical traces” is a roundabout way of gathering data about human behaviour. Instead of asking people to tell you what they do or how they do it, it takes note of a collection (accretion) or erosion of materials as “readings” of actual behaviour. This is particularly valuable when measuring behaviour that is not reliably measured using the survey technique. Survey respondents are prone to provide unreliable responses to socially displeasing behaviours, such as poor eating habits or smoking and drinking. Instead of asking respondents whether they make healthy eating choices, an analysis of the contents of the garbage might register more reliable findings.
Content analysis refers to the systematic analysis of communications, whatever form they may take, whether in print form, such as news articles or advertising, music form, such as lyrics, or electronic form, such as Twitter feeds. Categorized as an unobtrusive, non-reactive way of gathering data, this is very popular among student researchers interested in understanding media messages.
Measures are usually focused on identifying techniques of persuasion or cultural characteristics, message traits, inherent bias or defining features of the particular “communication community” being analyzed. Content analysis has been instructive in studying bias in news media articles with regard to such controversial subjects as the Middle East conflict or global warming, or in revealing the political positions in pamphlets of little-known groups such as sex workers.
Though this is called a type of analysis, which it is to a certain extent, it is categorized as a method or technique. It is difficult to separate the technique of obtaining the data from the actual process of analyzing it.
This involves interpreting documents such as court rulings or letters in order to gain insight into the thought processes or ideas surrounding a particular issue, person or event. The “reading” of the document involves a series of critical questions such as the purpose, audience, authenticity and significance of the author and the document. Code sheets for categorizing the data derived from a careful “reading” are sometimes designed for this technique. It is used mainly by historians using primary sources and is often used in conjunction with other data collection techniques.
Though this is called a type of analysis, which it is to a certain extent, it is categorized as a method or technique. It is difficult to separate the technique of obtaining the data from the actual process of analyzing it.
Referred to as “desk research” and popular in college and university student circles, it involves using the primary research of others found mostly in published books, peer-reviewed journals and monographs to address a research question. It is also a technique that few studies can do without. Though it can stand alone as a single technique, it is regularly used to provide context and corroboration for almost every other technique. For instance, a case study or a document analysis requires the input of secondary analysis to contextualize or situate the case or document.
Be sure to read up on its strengths and weaknesses.
Though this is called a type of analysis, which it is to a certain extent, it is categorized as a method or technique. It is difficult to separate the technique of obtaining the data from the actual process of analyzing it.
Also known systematic review or best-evidence synthesis and very closely related to secondary analysis, this technique involves pooling a collection of high-quality published studies and systematically reviewing the combined evidence. The aim is to identify patterns, problems or inconsistencies regarding the state of knowledge in a particular area.
Though this is called a type of analysis, which it is to a certain extent, it is categorized as a method or technique. It is difficult to separate the technique of obtaining the data from the actual process of analyzing it.
Researchers use a range of instruments for many research techniques. These instruments help them obtain and record ethical consent, manage the materials or organize the data into uniform and meaningful categories. It is advisable to make use of an existing instrument and to modify it to meet the particulars of the method plan. The Inventory of Information Sources, for instance, is very useful for most student papers, as it relates to the widely used “secondary analysis” method.
A questionnaire is the actual form used to question or interview research participants. A questionnaire form consists mostly of forced-response questions with few, if any, open-ended, qualitative questions. Typically used by polling and marketing firms to determine a large number of voter or consumer preferences, questionnaires are comprised of questions and scales that are designed, tested and validated by specialists. Student researchers are well-advised to borrow measures and validated scales from reputable organizations and academic research publications when designing their own questionnaires.
Standardized tests or scales are typically used in psychology and education where successive groups of test takers are subjected to the same questions under standard time limits and results are tallied to determine a standardized score against which other test takers are measured. Personality and intelligence tests are typical of standardized tests. Such testing is not without controversy, as is the case with IQ tests and itinerant testing of complex medical conditions.
Tests to determine whether someone suffers from a disorder, such as pathological gambling using the Gambler Addiction Index (GAI), should only be administered by trained and accredited specialists. Do not attempt to use a standardized test or scale without first reading about the terms of use and without the full permission of your teacher and an institutional review board, should you have one at your institution.
In the event that you use one, in whole or in part, be sure to credit the source.
Though it is not usually required to submit your data spreadsheets (Excel/SPSS), it is a proper form to briefly refer to how the quantitative and qualitative data inputs will be processed. If the confidentiality of participants is an issue, explain how it will be protected.
Popular with marketers and political campaigners, focus groups are task-oriented interview sessions with a group of between 5-10 individuals. The schedule includes the timetable, setting, sitting arrangements, list of required props/materials, questions/prompts, goals and plans for recording the event. A brief letter of intent and a consent form are usually included in this schedule package.
Code sheets are usually tabular and list-like in format and intended to systematically record observations at a desk or in a field-like setting. They are useful for non-participant field observations, meta-analyses and content analyses. Code sheets are heuristic devices that make the researcher’s life easier and generate more consistent results, especially when there are a number of different observers.
There are many devices for capturing data – from paper and pen to computers, digital cameras (photos and video), digital sound recorders, cell phones and even field notebooks or scrap paper. Select according to what will work best under the particular circumstances of your research. For instance, do not videotape an interviewee if you are not interested in the visuals. The video camera will only distract and focus attention away from the interview. Fully test out devices, especially complicated digital ones, before actually using them.
Informed and voluntary consent are the backbone of research involving human subjects. Without exception, when you have direct contact with human subjects, you must obtain their approval before gathering data. For those who are under 18, you must also obtain the consent of a parent or guardian, perhaps even the institution to which the subjects are attached (school...). Depending on the particulars of the case, you may be asked to draw up a consent form and attach it as an appendix item in the research proposal. At the least, the actual proposal will have to describe the procedure for explaining the terms of participation and obtaining consent.
Student researchers have restricted access to minors, medically or socially disadvantaged individuals (gamblers, alcoholics, eating disordered individuals, chronically stressed or clinically depressed, suicidal, mentally disabled).
Should you need access to photos, personal mementos, letters or other belongings, you must draw up a permission slip that lays out the terms of use for these items.
Most colleges and universities have templates for consent and permission forms and may even require going through an institutional review board (IRB) for permission in advance. It is your duty to be informed of these matters. Your teacher should be able to direct you in this regard.
Organizations and gatekeepers have a responsibility to protect people such as employees, residents, students or guests who are under their care. If a researcher wants access to elderly people in a residential home, they must obtain the permission of the family and the person in charge of the home. A permission slip can be as simple as a brief letter with the letter head of the institution sponsoring your research and the signature of someone in a position of authority, explaining the request.
Though this tool is not well-known, it is useful for those using primarily document sources. Simply identify the main types of sources used and briefly explain the relevance for the study of each of the main types. For instance, if your research study is a descriptive account of the recent conflict in Mali, you might want to indicate the following:
The inventory demonstrates the seriousness of your intent to embark on a study that does not appear to have much “conventional data.”
A field notebook is an accessible and portable notebook where all your thoughts, ideas, diagrams and mapping can be kept together. Used mostly in anthropology, geography and sociology, it is essentially a sequential record of research in the field and data gathering. Each entry should be dated to keep track of what was accomplished and when. It may be required post-report as evidence of work completed or to back up a claim or interpretation at a later date.
A qualitative interview is usually intended as a one-on-one between the interviewer and the interviewee. The schedule should include the timetable, setting/staging, intended questions/prompts, goals and plans for recording and transcribing the interview. A brief letter of intent and a consent form should also be included in this schedule package.
The purpose of social science investigation is typically to discover what people think or do or what objects signify. The main unit or entity that is to be analyzed is considered to be the focus. An e-business might be the focus of a case study, for example. Sometimes the focus of an intended study is a number of different types of units, and in this case, a sampling strategy must be determined for each. For instance, multiple units could be sampled to do a study on a suicide prevention program in Nunavik, Québec. The program itself could be a unit or Nunavik could be a geographical unit.
The important thing is to clearly identify your main unit of analysis. Is it a gangster (individual) or a gang (group)? A CEO or a corporation? A criminal or crimes? Stand-up comedians or jokes? A homeless person or homeless shelters?
Many people wrongly assume that units of analysis are exclusive to people, never places or things such as programs.
The unit is a particular person, such as the president of a country or a gangster, or the psychological or personal qualities of individuals, such as a stress score of an anxious individual.
The unit is an occupational group such as doctors, students, a street gang or a family unit. Not to be confused with looking at individuals and how they function within groups or social structures.
This refers to what happens when two or more individuals or groups interact in situations such as intimate relationships, weddings, religious ceremonies, sports events, terrorist attacks, demonstrations…
A geographical unit is a spatial location, such as a suburban district, country or island. For example, you might be intending to study the impact of climate change on small island nations which are collectively witnessing a slow and steady loss of landmass.
This refers to programs operating in policy areas such as health, welfare, education, finance, justice, culture or entertainment, to name but a few. One example of a program in the area of education is an anti-bullying program.
The unit could be an organization from any number of sectors or levels, such as a university, a corporation, a non-profit organization, a non-governmental organization (NGO) or an international governmental organization (IGO).
The units are things or objects, not people. Examples range from toys, cell phones and cars to homes, pottery, jokes and the like.
A sample of a population is drawn when the population is either too large or unavailable for study in its entirety. A sampling strategy is the process of identifying your population and then determining how to best select a sample from it. Choose a feasible plan and recognize limits. Populations do not have to be people. They can be objects such as businesses, countries, parks, etc.
The list below several types of fairly chosen samples of significant size that can be considered representative of the larger population to which they refer. Other common sampling types are random, probability and quantitative. To qualify as a random sample, each unit of the target population must be given an equal chance of being selected, much the same as in a lottery draw. Selection is based on the laws of probability. Randomly drawing the requisite sampling proportion from the target population using a sampling frame makes inferential statistical analysis and tests of statistical significance possible. Using these, you can calculate the probability that the sample statistic derived from a relatively small sample would apply to the entire population if a census were taken. Estimates of possible errors (random sampling errors) can also be estimated using probability or chance.
This stands for Simple Random Sample, the best known of the four basic types of random sampling techniques. SRS gives each unit in the sampling frame (the list from which the sample is drawn) an equal chance (probability) of being selected. Drawing names from a hat or using the table of random numbers are two ways to select a simple random sample. It is only feasible if a list can be generated. For confidentiality purposes and other reasons, lists are often not available.
Systematic random sampling is most useful when the sampling frame cannot be easily listed in a document. As a probability-based selection technique, it guarantees that each unit in the sampling frame is given an equal chance of being selected. The technique involves selection of units at regular intervals with a random start. A perfect example is systematic sampling library books in the library’s collections. A hundred books could be selected in this way by starting with a random number and selecting every twentieth book until you get a hundred books. Human selection bias is avoided and random sampling error can be calculated based on probability or the random chances of selection bias.
This technique is combined with one other random technique, either simple random or systematic. Proportions, both directly proportional to the target population (30/70) or equally proportional groupings (50/50), are set in advance and then within each of those proportional groupings, either simple random or systematic sampling is applied.
Usually called multi-stage cluster random sampling, this is a combination of the three other random sampling techniques. It is done in multiple stages and is most useful for drawing a random sample from a very large, diverse sampling frame. Taking a random sample of adult Canadians requires multiple steps to select a sample that represents all the regions and various sectors of Canadian society. The map would most likely select an equal proportion of adults (stratified) from each of the ten provinces and three territories, and then by rural, suburban and urban areas (stratified), and then broken down into neighbourhoods (systematic or simple random) and then finally households (systematic or simple random until the requisite sampling proportion is drawn). Most country-wide polls select using this multi-stage cluster sampling technique and the sample size is usually around 1200-1500.
The list below describes samples that are small and selectively chosen and do not represent the population from which they are drawn. Other techniques from this general category are non-random, non-probability or qualitative. Non-random selection techniques, which selectively draw the sample from the target population, are very popular and practical. Non-random sampling is typically used in most research studies, as randomization is difficult, time-consuming, expensive and sometimes not feasible given the parameters of most student research timetables and budgets. It is often impossible to locate a statistically significant portion of very specialized populations, such as female mountain climbers or musical prodigies.
The name itself provides an accurate picture of this type of non-representative sampling as “easy” or “conveniently available” for the researcher. Sources of selective bias must be recognized by the researcher. If the researcher selects a convenience sample consisting of a few close friends, then the researcher is obliged to reveal potential sources of bias such as similar educational and socio-economic backgrounds. Accidental samples are closely related to convenience and often used by historians and anthropologists. Often only a few artifacts survive the tests of time, so whatever artifacts remain must suffice, thus making results highly tentative and specific to the reasons for the survival of these few remaining traces.
Purposive sampling a common non-probability sampling technique useful for obtaining access to individuals (not always people) that are not easy to locate in the general population. Also referred to as judgmental sampling, it gives the researcher the chance to pick and choose units that qualify when there is a limited or specified pool to draw from. If your target population were amateur chess players, for example, you would be well-advised to visit locations such as a college or university chess club, where you may “purposively” go to the club area to locate a few members of this community.
Snowball sampling is a practical qualitative sampling technique for difficult-to-find research subjects or units. It involves accessing subjects or units through network connections. One person recommends other people for inclusion in the sample and it grows exponentially from there. Studying hobby farmers is made easy; once you locate one hobby farmer, you can ask them to recommend a few other hobby farmers they know. Gaining access through ready-made networks could lead to systematic bias, so be aware that no generalizations to the population of hobby farmers can be made, only surmised or suggested.
Theoretical sampling is a typical qualitative sampling technique that fits well with an open-ended, exploratory design. The actual number and type of the sample is determined in an ad hoc way over the course of the research study. The researcher has a clear goal but does not start off with a pre-set, precise sampling plan. Instead, it sets a tentative plan to sample a certain number of units until no new information is being revealed and a saturation point has been met.
This is usually combined with any of the other non-representative sampling techniques to ensure representation by gender, political party affiliation or any other criterion that may be of relevance to your study.