Presentation on theme: "1 Language of Research Partially Adapted from: 1. The Research Methods Knowledge Base, William Trochim (2006). 2. Methods for Social Researchers in Developing."— Presentation transcript:
1 Language of Research Partially Adapted from: 1. The Research Methods Knowledge Base, William Trochim (2006). 2. Methods for Social Researchers in Developing Counries, The Ahfad University for Women 3. Online Statistics Education: A Multimedia Course of Study, David M. Lane, Rice University 4. What is Research? Dr Catherine Heffernan. Retrieved from http://www.drcath.net/toolkit/research.ppt.
2 Agenda Useful Terms What is Research? What is Social Science Research Types of Research Time in Research Types of Relationships Variables Hypotheses Common Fallacies 2
3 Useful Terms Social research is theoretical and empirical -Theoretical: concerned with testing theories or ideas about how the world works -Empirical: based on observations and measurements of reality Probabilistic –Inferences we make in social research have probabilities associated with them –Part of the reason statistics is so dominant in social research is that it allows us to estimate probabilities for the situations we study.
4 Useful Terms Causal –Cause-effect relationships. –For example, attempt to see whether there is a relationship between gender and salary. Probably the vast majority of applied social research consists of these descriptive and correlational studies. –If we want to change the world in an organized, scientific way, to improve it and eliminate some of its major problems, we are automatically interested in causal relationships -- ones that tell us how our causes (e.g., programs, treatments) affect the outcomes of interest.
What is research? Research is the systematic process of collecting and analysing information (data) in order to increase our understanding of the phenomenon with which we are concerned or interested. Research is a set of questions being answered within a clear framework where: –Procedures and techniques that have been tested for their validity and reliability are used –The process for answering questions is unbiased and objective Research involves three main stages: - planning - data collection - analysis. 5
What is social science research? It is research involving social scientific methods, theories and concepts, which can enhance our understanding of the social processes and problems encountered by individuals and groups in society. It is conducted by sociologists, psychologists, economists, political scientists and anthropologists. It is not just common sense, based on facts without theory, using personal life experience or perpetuating media myths. It involves the systematic collection of methods to produce knowledge. It is an empirical research – i.e. facts are assumed to exist prior to the theories that explain them. 6
7 Types of Research Research studies can be –Descriptive: describes a phenomenon, situation or program. –Correlational: attempts to establish relationship/interdependence between 2 or more aspects of a situation –Causal: attempts to clarify the why and how of an observed relationship
8 Types of Research 3 rd variable problem: –Correlation does not imply causation. –Complan kids are taller maybe because of their socio-economic status (and better nutrition) and not because of the drink itself
9 Time in Research Longitudinal Study –Repeated measures or time series. –Involves studying the same group of participants over a particular time period –Researcher performs repeated observations or testing at specified points during the participants' lives, thus allowing the observation of development. Tracking the reading ability of successive cohorts
10 Time in Research Cross-Sectional Study –Involves studying groups of participants at the same point in time. I.e. we are taking a cross-section of whatever we’re observing or measuring Tracking the learning levels among 6-14 year old Indian children
11 Types of Relationships Nature of relationship –Correlational ≠ Causal –Third variable problem Patterns of relationship –None –Positive –Negative
12 Variables A variable is any entity that can take on different values –Age –Gender –Agreement An attribute is a specific value on a variable –Age: 1,2,3 –Gender: Male & Female –Agreement: 1 = strongly disagree; 5 = strongly agree
13 Variables Variables can be independent or dependent –Independent variable is what you manipulate (treatment, program, cause) –Dependent variable is what is affected by the independent variable (effects, outcomes)
14 Hypotheses A tentative expression of expected relationship between 2 variables Alternative and Null –A: The hypothesis that you support: A & B are related –N: The hypothesis that describes the remaining possible outcomes: A & B are not related One-tailed and two-tailed –Direction specified. Null: >5 Alternative: <5 –No direction specified. Null :5 Alternative: ≠5 14
Common Fallacies Ecological Fallacy: Conclusions about an individual based on group data. Per-capita income in Bihar is low. This does not mean a given individual has to be poor as well 15 Art Credit: Satish Acharya
Common Fallacies Exception Fallacy: General conclusions based on exceptions (caste/religion/gender biases – eg women drivers) 16