Search results
Apr 22, 2020 · Abstract. This purpose of this guide is to help university students, staff and researchers understand the basic principles of analysing the typical kinds of quantitative data they may collect...
- Quantitative Data Analysis Approaches
A Primer on Partial Least Squares Structural Equation...
- Login
Abstract. This purpose of this guide is to help university...
- Help Center
ResearchGate Help Center provides answers to common...
- Quantitative Data Analysis Approaches
Jun 8, 2019 · The objective of this handbook is that readers become capable to conduct research following a quantitative methodology. This is a manual to understand and practice all the phases of the...
- What is research?
- Quantitative research
- Research process
- Research process (actually)
- Data Collection
- Models
- Hypotheses
- Statistical model
- STATA resources
- Excel to Stata
- STATA gold rules
- Exploring your data
Controlled collection and analysis of information in order to understand a phenomenon Originates with a question, a problem, a puzzling fact Requires both theory and data. Previous theory helps us form an understanding of the data we see (no blank slate). Data lets us tests our hypotheses.
Quantitative methods allow us to learn about the world by quantifying some variation(s) in it. Example: how do suicide rates vary across demographic categories (Durkheim)? In order to learn about the world, we use inference: General definition: “Using facts you know to learn about facts you don't know” (Gary King) Example: Using a sample to learn a...
(confirmatory or deductive model) Reviewing literature and identifying a question Sometimes question helps you identify relevant literature, sometimes literature helps you identify unsolved puzzle What makes the question interesting? Real world implications and theoretical contribution Form hypotheses Think about data you need to test them Think ab...
Back and forth between theory and data Each is going to highlight relevant features of the other That’s how a contribution takes shape But: you can’t use the same data to generate and test hypotheses. It would be tautological Importance of cross-validation Exploratory and confirmatory analysis
Think hard about the population you want to study Think hard about selection Interviewing method: face to face, phone Sampling: random? Purposive? Time of day Place Who agrees to respond?
A model is a strategic simplification Never true or false Only useful or not (does it capture the features you are interested in?) Examples: Obesity rate=f(absolute wealth, inequality) Food security=f(total hh income, distribution of control over income) Fertility=f(individual factors, structural constraints*cultural norms) Models Let’s think about...
Inequality and health H0: life expectancy only affected by level of GDP Ha: autonomous effect of economic inequality on life expectancy To test this, I need data on countries which have similar levels of GDP but different levels of inequality (eg, Sweden versus US)
Depends on the process you want to study: Continuous outcome (rate, income...): linear or log-linear regression Binary outcome (marriage, incarceration): logistic regression Count data (civil wars): Poisson regression (advanced) Timing of events: Survival analysis (advanced)
UCLA website (v. popular): http://www.ats.ucla.edu/stat/stata/ Princeton web page (the one I learnt from, good to start): http://data.princeton.edu/stata/ List of various books: http://www.stata.com/links/resources-for-learning-stata/ My personal bible: Cameron & Trivedi Microeconometrics using Stata, Stata Press. RTC team in CGIS building (awesome...
If your data are currently in Excel, you need to convert and import them: http://www.stata.com/support/faqs/data -management/converting-excel-files/ Also: “help insheet” in Stata
Always use a do-file Always comment on everything you do within the do-file You don’t want to be lost months from now Also in some cases you might want to show me or your adviser your do-file (Almost) never save the data at the end of a session That will replace your original data set Better to “save as”
Always useful: help command What do my variables mean? Command describe [name/list of var] Command codebook [name/list of var] Basic statistics Summarize [list of variables], detail Tabulate [one or two variables], options
Assess how study design and quantitative data (format, approach) shape quantitative analysis: research questions and hypotheses, choice of analysis methods, formulation and interpretation of results. Describe best practices of quantitative data visualization (charts and tables) and critique examples. We are going to do this later instead.
1. Unit of Analysis (also referred to as cases): The most elementary part of what is being studied or observed. Some examples include individuals, households, court cases, countries, states, rms, industries, etc. 2. Variables: Concepts, characteristics, or properties that can vary, or change, from one unit of analysis to another. Please note that
What is quantitative research? Research methods in education (and the other social sciences) are often divided into two main types: quantitative and qualitative methods. This book will discuss one of these two main strands: ‘quantitative methods’, and what distinguishes quantitative from qualitative methods.
People also ask
What is a quantitative approach in research?
When should a researcher use a qual-itative method?
What is a combination of quantitative and qualitative research methods?
What is quantitative data analysis?
This chapter looks at many quantitative techniques used in the process of data analysis. These techniques depend on the statistical types of variables (nominal, ordinal, interval-ratio), because the types of variables determine what kind of statistical analysis is possible.