Social Science Research Methods, Exams of Social Work

Download Social Science Research Methods and more Exams Social Work in PDF only on Docsity! Social Science Research Methods Research - Process of finding reliable answers to important questions 7-Step Research Cycle - Questions, Theory, Design, Data Collection, Data Analysis, Inference, Presentation Research Question (RQ) - "Question about one or more topics or problems of social importance that can be answered through research" RQ: Unit of Analysis - Micro, Macro, and Meso Individuals, Communities, Institutions, Societies RQ: Scope - Local, Global, National RQ: Immediacy of Application - Applied v. Basic RQ: Mode of Investigation - Qualitative vs. Quantitative, Structured vs. Unstructured, Deductive vs. Inductive RW: Basic Purpose - Exploration, Description, Comparison, Trend, Projection, Explanation, Impact Evaluation Deductive Reasoning - Reasoning that moves from more general to less general statements Inductive Reasoning - Reasoning that moves from less general to more general statements RQ: Design (Time and Space Configuration) - Longitudinal, Cross-Sectional, Multi-level Purpose: Descriptive - To describe groups, activities, situations, or events. No interest in WHY outcome exists. Purpose: Comparative - To describe differences between groups, activities, situations, or events. No interest in WHY outcome exists. Purpose: Trend - To describe changes over time. Descriptive, but with a temporal dimension. Purpose: Explanatory - To explain why subjects vary in one way or another. X→Y, describes why a trend exists. Asks WHY or HOW. Purpose: Evaluative - To assess the impacts of programs, policies, or legal changes. X(policy)→Y, how policy affects Y. Asks WHY or HOW. Unit of Analysis: Micro - Researching individuals. If you need to ask an individual a question to get your answer, the UoA of Micro Probability Sample - Sample drawn in a way to give every member a known chance of inclusion Coverage error - Difference between sampling frame and target population Nonresponse Error - Error due to differences in responders and non-responders Sampling Error - Difference b/w sample characteristics and equiv. characteristics of a sampling frame when difference isn't due to nonresponse error Parameter - summary of variable characteristic in a population Statistic - summary of variable characteristic in a sample Simple Random Sample - Completely randomized sample, lottery-like Systematic Sampling - probability sampling procedure that involves selecting every 'k'th element from a list of population elements, after the first element has ben randomly selected Stratified Sampling - probability sampling procedure that involves dividing the population in groups defined by the presence of certain characteristics and then random sampling from each group. Ex stratify by gender Cluster Sampling - probability sampling procedure that involves randomly selecting clusters of elements from a population and subsequently selecting every element in each selected cluster for inclusion in the sample Multistage Sampling - a probability sampling procedure that involves several stages, such as randomly selecting clusters from a population, then randomly selecting elements from each cluster. Purposive sampling - non-probability sampling procedure that involves selecting elements based on the researchers' judgement about which elements will facilitate his/her investigation Quota Sampling - non-probability sampling procedure that involves describing the target population in terms of what are thought to be relevant criteria and then selecting sample elements to represent the relevant sub- groups in proportion to their presence in the target population Snowball sampling - non-probability sampling procedure that involves using members of the group of interest to identify other members of the group Convenience sample - non-probability sampling procedure that involves using elements readily available to researcher (ex. prof using students) Cross-sectional study - "snapshot", 1 group, 1 time Rationale for cross-sectional study - useful for describing samples and relationships b/w variables. useful for for explanatory purposes especially if the time order is known. Panel Study - one sample, 2+ times Rationale for panel study - useful for describing changes in individuals/groups over time. useful for explanatory purposes. Trend studies - 2+ samples, 2+times Rationale for trend study - useful for describing changes in populations over time Requirements for causality - pattern or relationship between ind. and dep. variable, determination that ind. variable occurs first, support for conclusion that apparent relationship is not caused by confounding variable Internal Validity - agreement between a study's conclusions about a causal connection and what is actually true Panel attrition (in panel study) - participants drop out, cannot be found, etc. Panel conditioning (in panel study) - Effect of repeatedly measuring variables on members of a panel study