460 likes | 784 Views
Seminar on Research Methods: Introduction to Quantitative Methods. Instructor: Coye Cheshire Lecture 1: The Elements of Research. About your instructors:. Coye Cheshire Office 305A Office Hours Tues and Thurs 3-4pm Class Location Change: 202 Yuri Takhteyev
E N D
Seminar on Research Methods: Introduction to Quantitative Methods Instructor: Coye Cheshire Lecture 1: The Elements of Research
About your instructors: • Coye Cheshire • Office 305A • Office Hours Tues and Thurs 3-4pm • Class Location Change: 202 • Yuri Takhteyev • Hal Varian (guest lecturer for some topics)
Course Website • http://sims.berkeley.edu/courses/is296a-4/s06/
Course Design • Part lecture, part skills development • One major topic per week • Some time devoted to working with statistical software packages • Two major course sections • Research Methodology (weeks 1-6) • Quantitative Methods (weeks 7-15)
Course Readings • Readings: • Links to online readings on course website • List of recommended readings also on course website
Statistical Software • My class examples will use SPSS and STATA • SIMS lab has SPSS; you are not required to purchase a statistical package for this class. • If you are interested, both STATA and SPSS have grad versions (cheaper)… or you could rent SPSS software through • www.e-academy.com • You can purchase a one-year or perpetual STATA license with the grad plan: • http://stata.com/order/new/edu/gradplans/gp-campus.html • SPSS can be purchased through the Scholar’s Workstation: • https://www.tsw.berkeley.edu/
Software and Computers • I encourage you to bring your laptop to class. • I will devote some class time in many sessions to working with statistical software. • I encourage you to sit with anyone who has a statistical software package when we begin to use it in class.
Course Assignments • Three assignments • First assignment • Exercise on research methodology (20%) • Second assignment • Using a statistical software package to do some basic statistical tests on an existing dataset (20%) • Third assignment • Group project: 4-6 person teams (60%) • Find and work with dataset • Short paper (5-8 pages), short class presentation
Final Presentations • Last day of class (May 8th) • One paper turned in for each group • Contribution breakdown for each group member (includes paper and presentation)
Course Topics • Defining and justifying research problems • Theory and Measurement (causation, validity, reliability • Secondary data analysis • Experimental design
Course Topics (continued) • Descriptive univariate statistics • Bivariate statistics • Exploratory data analysis • Analysis of variance (ANOVA) • General linear model (linear regression)
Course Topics (continued) • Regression for discrete outcomes (logistic regression) • Advanced topics • Social Network Analysis • Time Series Forecasting
Overall Course Goals • You will have an understanding of research method terminology. • You will have good knowledge of common research methods used in quantitative research (surveys, experiments) • You will understand basic univariate and bivariate statistics, and have an introductory knowledge of common mulitivariate statistics • You will be able to use a general purpose statistical package to conduct univariate, bivariate, and multivariate statistics
Class Survey • We will email you a link to a short survey for use in this class. Please fill it out this week.
Today’s Introductory Lecture • The Elements of Research: Research Design Process and Common Terminology
Why quantitative research? • Standardized methodologies • Methods are public • Theoretically, anyone should be able to duplicate your findings • Forces the investigator to think about the measurement of key factors (i.e., variables)
A Primer for Thinking About Research • Three general questions when thinking about designing research (Creswell 2003): • What knowledge claims are being made by the researcher? • What strategies of inquiry will inform procedures? • What methods of data collection and analysis will be used?
Knowledge Claims • Positivism/Post-positivism • Often starts with theory; deductive • Constructivism • Often does not start with theory; inductive • Advocacy/Participatory • Literally advocates action in a specific area • Pragmatism • The ‘problem’ is the key issue; specific methods chosen based on the nature of the problem(s)
Strategies of Inquiry • Qualitative • Ethnographies • Case studies • Narrative research • Quantitative • Surveys • Experiments
Research Methods • Qualitative • Instrument-based questions • Statistical analysis • Quantitative • Emergent methods • Open-ended questions • Interviews • Mixed-Methods Approaches • Both quantitative and qualitative methods used
Elements of Inquiry Knowledge Claims Strategies of Inquiry Methods Approaches to Research Design Process Questions Data collection Data analysis Qualitative Quantitative Mixed Methods Adapted from (Creswell 2003)
What are the Elements of Research? • Common terminology for constructing testable hypotheses • Terms and relationships between terms are useful for theoretical and applied research • All research, regardless of tradition, uses similar concepts for building testable statements and measuring results
Constructs and Variables • Constructs • Concepts, often complex • Not directly measurable • Also called ‘theoretical variables’ • Variables • Something we can measure • Concrete measured expressions to which we can assign numeric values
Socioeconomic Status Academic Achievement Academic Ability An example theoretical model
Socioeconomic Status Academic Achievement Academic Ability Theoretical Model with Variables Income Job Prestige Grades Level of Schooling attained Math skills Language skills
X Y X Y X Z Y Causation and Causal Paths • Direct causal paths • Reciprocal causation • Indirect causation
Video Games Violence Time spent playing Game X Observed ‘violent acts’ Over time Y Propositions and Hypotheses • Propositions link concepts together with specific relationships • Hypotheses link variables together with specific relationships
Hypothesis • “hypothesis statements contain two or more variables that are measurable or potentially measurable and that specify how the variables are related” (Kerlinger 1986)
Measurement • Variable: • A characteristic of the participants or a situation in a given study that has different values in that study. • Operational Definition: • Describes or defines a variable in terms of the operations used to produce it or techniques used to measure it.
Measurement • Example operationalizations: • Age • Guess, based on how old a person looks. • Ask to look at person’s drivers license. • Ask people their age. • Ask for actual number of years • Ask between categories (18-25, 26-33, 34-41, 42+)
Operationalization • For any operational definition, there are a few important things to keep in mind: • What is the unit of analysis? • Be able to justify your operational definition (i.e., don’t make arbitrary decisions) • Try to be consistent about level of analysis unless this is part of your theory and/or research question.
Measurement: Variables • Independent Variable • Also called predictor variables, or right-hand side variables (RHS) • Those that the researcher manipulates • Attributes or potential causes under investigation in a given study • Dependent Variable • Also called outcome variable, or left-hand side variables (LHS)
Time spent playing Game X Observed ‘violent acts’ Over time Y
Types of Variables • Categorical • Ordinal • Metric
Categorical Variables • Binary/dichotomous • Example: Student versus non-student • Nominal/non-ordered polytomous • Example: Ethnicity
Ordinal Variables • Ordered polytomous • Example: Likert scales • 1=Strongly Agree, 2=Agree, 4=Undecided, 5=Disagree, 6=Strongly Disagree
Metric Variables • Interval • Distance between attributes has meaning • Example: Fahrenheit temperature • Ratio • Distance between attributes has meaning, and there can be a meaningful zero. • Example: Count variables
Time spent playing Game X Gender Race or Ethnicity Observed ‘violent acts’ Over time Y Scale 1-5 of attitude About the President Uses Internet or not
Next Class: • Research Questions: What is a good ‘research problem’ and how is it justified? How do we turn these questions into testable hypotheses?