Principles of Data Management and Presentation - Softcover

Hoffmann, John P.

Softcover

ISBN 10: 0520289943 ISBN 13: 9780520289949

Publisher: University of California Press, 2017

Synopsis

The world is saturated with data. We are regularly presented with data in words, tables, and graphics. Students from many academic fields are now expected to be educated about data in one form or another. Yet the typical sequence of courses—introductory statistics and research methods—does not provide sufficient information about how to focus in on a research question, how to access data and work with datasets, or how to present data to various audiences.
  
Principles of Data Management and Presentation addresses this gap. Assuming only that students have some familiarity with basic statistics and research methods, it provides a comprehensive set of principles for understanding and using data as part of a research project, including:
• how to narrow a research topic to a specific research question
• how to access and organize data that are useful for answering a research question
• how to use software such as Stata, SPSS, and SAS to manage data
• how to present data so that they convey a clear and effective message
 
A companion website includes material to enhance the learning experience—specifically statistical software code and the datasets used in the examples, in text format as well as Stata, SPSS, and SAS formats. Visit www.ucpress.edu/go/datamanagement, Downloads tab. 

About this title

About the Author

John P. Hoffmann is Professor of Sociology at Brigham Young University. Before arriving at BYU, he was a senior research scientist at the National Opinion Research Center (NORC), a nonprofit firm affiliated with the University of Chicago. He received a master's in Law and Justice from American University and a doctorate in Criminal Justice from SUNY-Albany. He also received a master's in Public Health with emphases in Epidemiology and Behavioral Sciences at Emory University. His research addresses drug use, juvenile delinquency, and the sociology of religion.

Excerpt. © Reprinted by permission. All rights reserved.

Principles of Data Management and Presentation

By John P. Hoffmann

UNIVERSITY OF CALIFORNIA PRESS

Copyright © 2017 The Regents of the University of California
All rights reserved.

ISBN: 978-0-520-28994-9

Contents

Preface, 
Acknowledgments, 
1 Why Research?, 
2 Developing Research Questions, 
3 Data, 
4 Principles of Data Management, 
5 Finding and Using Secondary Data, 
6 Primary and Administrative Data, 
7 Working with Missing Data, 
8 Principles of Data Presentation, 
9 Designing Tables for Data Presentations, 
10 Designing Graphics for Data Presentations, 
Appendix: Introduction to Statistical Software, 
References, 
Index, 

CHAPTER 1

Why Research?

It seems that every day brings another report of some research finding. A quick Internet search of news articles that appeared on an otherwise ordinary day in June revealed, among other stories, that California just approved a publicly funded gun research center, the Netherlands began a campaign to identify and reduce research misconduct, a geological study discovered that some parts of the San Andreas Fault are sinking and others are rising, a nutrition study suggested that broccoli is healthier than previously thought because its phenolic compounds have notable antioxidant properties, and a survey revealed that about 31% of people admit to snooping on a friend or loved one by looking at their cell phones. As suggested by just a single day's news coverage, research is a huge enterprise, employing millions of people worldwide and resulting in thousands of reports, articles, and books every year. The American Association for the Advancement of Science (2016) estimates that the US government spends about $70 billion per year on various forms of research.

But many people have questioned the value of some of this funded research. We regularly see debates about the value of research on global warming, firearms, health-care systems, and many other topics. In addition, conservative politicians such as US Senator Tom Coburn of Oklahoma publish annual reports of federal government waste, taking particular glee in pointing out what are considered dubious scientific studies. For example, the 2014 Wastebook highlights studies of gambling monkeys, mountain lions on treadmills, and synchronized swimming by brine shrimp. Yet, there is clearly much to be gained from good research. Without it, there is little doubt that death, illness, and injury rates would be much higher. Food production would be substantially lower. The field of forensic science would be much more primitive, thus impeding efforts to solve crimes and catch criminals. Producing enough power to light homes, operate cars, and run businesses would be much more difficult. The list goes on and on.

Social science often gets a particularly bad rap because some do not consider it a true "science." But it has also contributed not only to making the world a better place, but also to increasing our understanding of the way people, social groups, communities, and institutions function and interact. Let's examine a few examples of social science research to see what it has taught us. As you read the following illustrations, think of what broader implications each has for understanding the social world and perhaps even improving people's lives.

In the mid-1960s, the social psychologist Stanley Milgram wanted to determine how close or far apart people were socially. He devised a project in which he mailed a letter to random people who lived in several Midwestern US cities. The letter asked them if they personally knew an individual — again selected randomly — who lived in Boston, Massachusetts. If they did, they were to send the letter to this person. If not, they were to send the letter to a friend or relative who was more likely to know the person in Boston. He then examined how many times, on average, the letters that reached the person had been sent. This led to the famous phrase about "six degrees of separation," which was based on the average number of times the letter was forwarded (Milgram 1967). Even though the project and its findings have been criticized in the ensuing years (Watts 2004), it has motivated hundreds of subsequent studies on social networks and led to the proliferation of social network analysis as a valuable research tool for the social sciences. In what other ways might social networks be important for understanding the way people interact and how this affects their lives?

In the early 1990s, political scientist Bruce Keith and his colleagues wished to understand better what it means to be a political independent. Whereas many people in the United States identify as a Democrat or a Republican, a plurality claim they are independent and don't identify with either political party. Understanding what this signifies has important implications for voting behavior and the public's support of political figures and their policies. Keith et al. (1992) determined that a large number of independents are actually fairly consistent in voting for Democratic or Republican candidates. Thus, regardless of how they label themselves, only a relatively small percentage of voters are truly "independent." What might this finding suggest for other questions about how people identify with groups and engage in civic life?

Finally, most residents of a town or city can distinguish the "good" neighborhoods from the "bad" neighborhoods. Good neighborhoods tend to be safe, whereas bad neighborhoods tend to be dangerous, places where the risk of falling victim to crime is high. Often, we perceive of bad neighborhoods as those with vacant lots, graffiti, and boarded-up buildings. Sociologists Robert Sampson and Stephen Raudenbush (2004) sought to understand whether these signs of "disorder" were valid markers of dangerous areas. By carefully studying dozens of Chicago neighborhoods, they found that it was less the explicit "dangerousness" of a neighborhood — as measured by criminal activity or physical decay — that predicted whether people judged a neighborhood as qualitatively bad or good, but instead whether there was more poverty and minorities who lived in a neighborhood. In other words, neighborhoods can get labeled as bad or good based on the types of people who live in them, regardless of how objectively safe they are. What consequences does this finding have for understanding social and ethnic relationships, the health and development of communities, and how the criminal justice system operates?

I hope it is clear that each of these studies, while important in its own right, illustrates the value of social science research. We know that scientific research has led to many improvements in the world, from longer lives due to medical advances to rapid transit from one part of the globe to another. Although perhaps not considered as beneficial, research in the social and behavioral sciences has also led to a better understanding of society, with the potential to improve lives, relationships, and communities. For example, social network studies, many of which are motivated by Stanley Milgram's research, have led to more effective health education and intervention programs (e.g., Kim et al. 2015), thus serving to improve health among underserved groups of people. Sampson and Raudenbush's study might lead to more just policing strategies and help prevent police shootings in minority neighborhoods (a problem that has plagued several US communities over the past few years).

WHY RESEARCH?

Although most of us will never conduct research that is as influential as these notable examples, we may nevertheless find satisfaction in the design and execution of a good research project. Perhaps some of you will also be involved in research that will improve the human condition. This book discusses some of the principles and tools that are at the foundation of social scientific research. Before embarking on this discussion, though, it may be helpful to think a bit more about why we conduct research. Here are four broad reasons (Booth et al. 2008).

• Research helps us develop a deeper understanding of questions and answers. This assumes we wish to know the answer to some important questions that research can provide, such as those that involve patterns of behavior, factors that influence social problems, or why some forms of government or social policies seem to work better than others. It is also a good way — some argue a critical way — to identify facts: those bits of information for which there is evidence to indicate they genuinely exist. This is often contrasted with opinions: beliefs about some issue that depend largely on the holder's point of view. We'll return to the issue of evidence later. Research can be especially important when it comes to studies of health, safety, and economic well-being — research can improve and save lives.

• Research helps explain the world around us. Research can help us understand and explain how things operate and why events occur. I may not want to be able to explain something because I wish to change it, but rather simply because I'm curious about why it operates the way it does. Although this reason is often considered the domain of "pure research" in fields such as physics, many social scientists are also interested in explaining why people or social groups behave or believe the way they do. This is not because they want to change behaviors or beliefs, but rather because they are curious about them. This can be especially satisfying when other people or groups seem different or peculiar from the researcher's perspective. It can help us unmask our own preconceptions about others.

• Some people find pleasure in solving puzzles. In the social sciences, researchers often gain satisfaction by answering questions that others have not thought of or have not been able to answer in the past. For example, what, if any, influence do neighborhood factors have above and beyond the influence of families or schools on the way young people behave? If a young person moves from an impoverished neighborhood to a wealthy neighborhood, should we expect her chances of attending college to improve? Or does her likelihood of going to college depend mainly on her family's station and influence? This might be considered a puzzle that has not been solved yet.

• Research provides a learning environment. By conducting research, we may learn new and more advanced skills. This furnishes training to conduct more sophisticated forms of research. One way to think about this is that early involvement in research is a type of apprenticeship that might lead to a vocation at which you can excel (or at least support yourself!).

These four reasons need not be independent of one another, though. Someone's pleasure in solving research puzzles may certainly be related to her interest in answering a question or to comprehending how the world and its inhabitants operate.

WHAT IS RESEARCH?

But what do we mean by the term research? Most dictionary definitions of this word use terms such a systematic exploration, discovery, or investigation. For example, the Oxford English Dictionary (2016) defines the noun form of research as "the systematic investigation into and study of materials and sources in order to establish facts and reach new conclusions." In a guide to research practices in the social sciences, DePoy and Gitlin (2016, 3) offer the following definition:

Research is ... multiple, systematic strategies to generate knowledge about human behavior, human experience, and human environments in which the thinking and action processes of the researcher are clearly specified so that they are logical, understandable, confirmable, and useful.

In this context, research is a systematic set of transparent procedures designed to produce knowledge. Systematic refers to a fixed plan that can be repeated. Transparent means that the procedures used are clear and understandable. Thus, research is a process of fixed and clear steps that is aimed at revealing something that is unknown, poorly understand, or even to assess a statement of fact ("Watching violent films makes teenagers more aggressive"). Moreover, some suggest that it is fundamentally about identifying a problem and finding a solution (Booth et al. 2008). Research includes many kinds of information or data gathering exercises. In general, we wish to collect information — in a systematic and documentable way — to solve a problem, answer a question, or perhaps even generate more questions.

Research Involves Telling a Story

A useful way of thinking about research is to relate it to telling a story. Simply put, research involves the following: Something happened, it's important, and I want to tell you about it. Good stories include themes — key things the story tries to tell or teach the reader — and plots — information and events that are organized in a logical and recognizable order. Good stories are narratives: they connect events, sometimes in clever and unexpected ways. One of the tasks of research is to describe and explain how events are connected. Yet there is often an aspect of research that sets it apart from a story about Uncle Joe and how he lost a family heirloom when he went surfing. Although the heirloom may be valuable to some family members, researchers usually wish to tell stories that are important in a more general sense. As related earlier, Professors Sampson and Raudenbush told a story about how people identify and label Chicago neighborhoods based on the types of people living in them. A theme of this story is that what we perceive with our eyes and interpret with our minds do not necessarily reflect reality. Our general perception of the physical environment is influenced largely by who we see in that environment. In general, research tells stories — like many good stories — about things that apply broadly.

Research Is about Making Comparisons

Research also involves comparisons. When researchers wish to answer a question, such as whether a drug abuse prevention program is effective, they are concerned with comparing those who were exposed to the prevention program to those who were not. Even when they observe only one group, it is important to think about what would have happened to members of that group — or a similar group — if they had had a different experience. Similarly, how does the group under investigation compare to other groups who may behave similarly or who live under similar conditions but behave differently? For example, suppose an ethnographer is studying a group of methamphetamine users in rural Missouri. It is usually helpful — even if only implicitly — to consider how those in this setting compare to those in other settings, such as in inner-city St. Louis or rural South Dakota. How might their use of methamphetamine serve a similar or different purpose than use among other users? Does their motivation to use or eventually abstain differ from the experiences of others? What implications does the broader social or cultural milieu have for their use vis-à-vis others' use?

A term that is frequently used when thinking about research as a comparison is counterfactual. This refers to attempting to infer what would have happened if some other experience than that observed had occurred. For instance, when an experiment is conducted and only one group — the experimental group — is given the stimulus (such as when only one group of people watches a violent encounter), the counterfactual asks what would have happened to those in the comparison group if they had been given the same stimulus. An assumption is that they would have reacted in a similar way — thus demonstrating the same outcome. This assumption is made more realistic by randomization, a process designed to make the groups comparable in most conceivable ways. If they are comparable, then the only difference between them is the stimulus that they experienced. However, we may never observe the true counterfactual (Mumford and Anjum 2013). Yet, imagining it by thinking explicitly about comparisons among research participants is a useful mental exercise that helps answer questions.

Research Is a Type of Argumentation

Another useful way to think about research is that it is a type of argumentation (Booth et al. 2008). Argumentation refers to the process of developing and assessing arguments. However, the type of argument referred to here is not an angry or hostile verbal exchange between two opponents. Rather, we are interested in two relevant types of arguments. The first type, rhetorical, provides information — or a set of supporting statements — to persuade someone that some claim is accurate ("ocean waters appear blue because of the way water absorbs light waves"). A claim is simply an assertion that something is true. Rhetorical arguments are used in many spheres, from a teacher who tells her students which ethnic groups vote most often in local elections to the radio personality who claims that a politician is wrong on some issue and provides reasons, such as by discussing the politician's voting record and public statements. The second type, dialogical, examines different, perhaps opposing, claims and tries to reach agreement on which one is most accurate (Driver et al. 2000). Research is appropriate for evaluating dialogical arguments since it is important to consider alternative explanations for phenomena. Explanatory research is especially well suited for examining scientific arguments: the process of using scientific methods to demonstrate that some process or claim is the most reasonable or valid, usually when compared to some alternative process or claim (Khine 2012).

Discussions of argumentation typically identify and distinguish three components: claims, warrants, and data. The following two sentences provide an illustration of an argument:

Michael Jordan was a better basketball player than Kobe Bryant (claim). He won more NBA championships and most valuable player awards (data) because he was more talented physically, a better team player, and had a stronger drive to succeed (warrants).

(Continues...)

Excerpted from Principles of Data Management and Presentation by John P. Hoffmann. Copyright © 2017 The Regents of the University of California. Excerpted by permission of UNIVERSITY OF CALIFORNIA PRESS.
All rights reserved. No part of this excerpt may be reproduced or reprinted without permission in writing from the publisher.
Excerpts are provided by Dial-A-Book Inc. solely for the personal use of visitors to this web site.

Edition details

• Publisher: University of California Press
• Publication date: 2017
• Language: English
• ISBN 10: 0520289943
• ISBN 13: 9780520289949
• Binding: Paperback
• Edition number: 1
• Number of pages: 282