Quantitative Research Methods for Political Science, Public Policy and Public Administration (With Applications in R) - 3rd Edition
Hank Jenkins-Smith, University of Oklahoma
Joseph Ripberger, University of Oklahoma
Copyright Year: 2017
Publisher: University of Oklahoma Libraries
Conditions of Use
This book is highly comprehensive in the sense that it effectively marries a discussion of the theoretical foundations of research design and statistics with concrete examples and syntax for applying the concepts in R. Although there is neither an... read more
This book is highly comprehensive in the sense that it effectively marries a discussion of the theoretical foundations of research design and statistics with concrete examples and syntax for applying the concepts in R. Although there is neither an index nor a glossary, the table of contents is detailed and the book itself is effectively organized. Key words are presented in bold.
In my review of the textbook, I found no evidence of errors of bias. The book appears to be carefully edited with well-chosen examples pertinent to the field of study.
Given the subject matter (i.e., statistics and mathematics), it is unlikely that the material will date quickly. It is plausible but unlikely that the R syntax will no longer work in future iterations of the program. The textbook is on its third edition, suggesting that the authors are attentive to implementing improvements. Additionally, while there are screenshots to pages where students can download resources, the instructions are described in the text without the use of many links which can stop working and create frustration for readers.
This book contains very clear descriptions of key topics. Specific chapters could be assigned in courses, even if the application in R is not being used in the course, in which case some of the chapters would be less relevant.
This book is thoroughly edited and presents the material in a clear and well-organized way as one would find in any quality textbook on the subject.
The early chapters on research design and statistical theory could be assigned on their own, while the same would be true of the latter chapters for a course needing only instructions on how to use R.
The organization of the book is effective. I would like to see potential material on how to conduct a literature review and research ethics. Creation of examples using SPSS or Stata would also be welcome.
The formatting and interface is problem free.
This book is well edited and free from grammatical errors.
This book is free from insensitive or offensive material.
This book is very comprehensive, beginning with the scientific method, progressing through research design, data visualization, inference, regression, and culminating with a chapter on generalized linear models (logit). The table of contents is... read more
This book is very comprehensive, beginning with the scientific method, progressing through research design, data visualization, inference, regression, and culminating with a chapter on generalized linear models (logit). The table of contents is thorough, which is helpful to the reader, especially for a methods textbook, which often is not read cover-to-cover, but is referenced time and time again. There is also an appendix which introduces the reader to utilizing R to implement some of the statistical techniques provided in the text. I would like to see more time spent on interaction terms, as this is an important component of teaching quantitative methods to political scientists. While the book covers a breadth of topics, it provides only a surface coverage of many fundamental aspects of research methods (e.g. independent and dependent variables). In other words, the coverage is broad but not deep. Compared to other methods textbooks, there are not as many examples and there are not problems or questions that are often very helpful to students.
The content is accurate and unbiased and its presentation is straightforward.
The authors could spend more time explaining how to apply these concepts in R and what version of R they are using, so that they may be more easily replicated.
Due to the content (methods-based), it will remain relevant and not be quickly outdated like many texts in political science. The text is also on its third edition, which demonstrates that the authors are continuing to update and improve the text.
There are some missed opportunities for the authors to define terms. For instance, they discuss a working hypothesis and null hypothesis in the first paragraph (and put these terms in bold), but do not explicitly define them in the text. In other places, they define terms (such as the definition of theory on page 5). Defining terms consistently throughout the text would be helpful and would improve the text's clarity.
Overall, the language is clear and straightforward. It is written in a manner that is easily accessible to undergraduates. Additional examples, however, would provide a useful supplement to aid in understanding.
The presentation of graphs could be enhanced by using variable labels as opposed to variable names.
The book is consistent in its approach and terminology.
There are many short sections within each chapter. This makes it ideal and easy to assign sections of a chapter to students, rather than requiring that they read the whole chapter. Other than understanding the basics of research methods, readers could easily move between sections and read portions out of order.
The book is well organized, and progresses in an expected fashion. It begins with theories of social science and the scientific method, discusses fundamentals of research methods, describing and displaying data, discusses inference, then presents bivariate and multivariate OLS regression, and finally general linear models. This coincides with the order in which I would teach these topics.
The book is produced in latex, and so the format (including figures) should be familiar to many political scientists who utilize this software. One revision the authors could make for future revisions would be to include hyperlinks in the table of contents to link the reader to the sections, chapters, and figures.
The book is well-written.
The book is not culturally insensitive or offensive. The examples are straightforward and brief. In a future revision, the authors could consider discussing the measurement of demographic variables (e.g. gender and sex, race) in greater depth. This would provide the reader with a stronger grasp of the advantages and disadvantages of utilizing different measurement strategies.
The book is a good, comprehensive overview of research methods. It would be difficult to use it as the sole textbook for undergraduates, due to the lack of examples. It would be a strong choice for a supplemental text or may be more appropriate for a graduate course.
The book's overall approach is great -- framing quantitative methods in terms of social scientific research more broadly. If I was teaching a quantitative methods course, I would most likely use this book, as it covers a nice range of essentials,... read more
The book's overall approach is great -- framing quantitative methods in terms of social scientific research more broadly. If I was teaching a quantitative methods course, I would most likely use this book, as it covers a nice range of essentials, particularly regression, while the open source nature ensures that students can always return to this book for reference. The book's use of R is similarly ideal. There are a few areas where an instructor may wish to expand upon the book's content, but this can easily be done through lecture or by assigning one or two additional and complementary readings. I do wish the book did a bit more in terms of clearly defining key terms and concepts. For instance, null hypothesis is first mentioned on page 4, but is not defined until page 10, and one only learns this by reading the full chapter. While the book description says that the book is designed for upper level undergraduates and graduate students, I assume that most students do not encounter terms like null hypothesis until their first methods course, which is usually where they are also learning quantitative methods (and where this textbook would be appropriate). In short, a glossary of the terms set in bold would be a strong addition to this book.
I saw no inaccuracies worthy of note. One always has preferences for the way in which methods are explained, but I saw nothing that would cause me to view this book as inaccurate.
The book tackles fundamentals in social scientific research and quantitative methods, and these will stay relevant.
As mentioned above, a glossary would be an easy addition that would greatly strengthen the text. Students at all levels can become intimidated by a methods book with unfamiliar terminology. A glossary can help alleviate some anxiety.
I saw no inconsistencies.
The book is organized in a consistent and clear manner. The headings and subheadings are easily understood and navigated. Chapters can easily be broken down into smaller sections for class readings.
The text builds in a clear and logical fashion, appropriate to the subject matter of this type of course.
I saw no interface issues.
There are only trivial grammatical errors, of the kind similar to all textbooks.
I did not see anything culturally insensitive or offensive in the text. I have to admit, I only understood the Monty Python reference after googling it, but that's life.
I have one relatively minor suggestion. In the first two chapters, where theory and social scientific methodology is discussed, it might help to use a consistent, versatile example to illustrate many concepts of those chapters. For instance, when the text discusses the goal of generalization, and uses the example of why a president's approval rating may have dropped, why not also use this example later to discuss independent and dependent variables? The discussion of dependent and independent variables on page 6 doesn't use an example, and I think students would greatly benefit by having an example to illustrate this content.
This text does a solid job in providing an introduction to statistical analysis with a focus on regression. Additionally, it provides a light introduction to statistical computing in R. This is mostly a tool for teaching regression, with a light... read more
This text does a solid job in providing an introduction to statistical analysis with a focus on regression. Additionally, it provides a light introduction to statistical computing in R. This is mostly a tool for teaching regression, with a light introduction to maximum likelihood estimation and generalized linear models through a chapter on logistic regression. The text briefly discusses some other methods, though, for instance, the discussion on experimental research designs is quite minimal. There is no discussion of survey experiments, which are increasingly used by social scientists as research design. Perhaps the text should be more clearly framed as one to teach regression. Additionally, there could be more instruction provided on R, specifically in teaching best practices for conducting analyses in R.
I found the content in the text to be mostly accurate. The "Inference" section could use some editing in reference to p-values and how we interpret them. This is notoriously difficult, but could be improved.
While I cannot foresee the content regarding regression becoming obsolete any time soon, there are some limitations to the relevance of the text. For instance, many more recent developments in methodology are not included. That is fine, as no one book can address that many streams of quantitative research. However, the framing of the book makes it seem like it would address more than regression. Additionally, the text would be improved by providing an updated, more thorough introduction to R, including a "best practices" approach to analysis in R.
The text is written quite clearly, and would be very appropriate for its target audience. Complex econometric concepts are written in an approachable way, with illustrative and complementary examples. I can see this text being especially useful for public policy and public administration students. While the text is framed as being designed for graduate students, it also seems appropriate for teaching undergraduate statistics courses.
I found the text to be consistent in its notation, which is important in statistics texts.
I really appreciated the way in which chapters were organized. Subjects were broken down to manageable chapter lengths, and the use of headings and subheadings was very clear. I can easily picture assigning readings throughout the semester without much modification to chapters.
I appreciate the authors' decision to structure the the text as similar to the way in which scientific research is conducted, beginning with the development of theory, moving to research design, and ending with statistical analyses and model evaluation. It is important to place an emphasis on following the scientific method when conducting statistical analyses. While the Appendix on R is helpful, it may make sense to incorporate some introduction to R in the main text. When R is introduced in the main text, it somewhat assumes a baseline familiarity with R.
The PDF version was mostly free of interface issues. It would be nice to incorporate hyperlinks within the text, so that one can simply click on a page number to navigate to a section rather than being limited to scrolling to find things. There also seems to be some inconsistency in formatting of tables and figures -- while most are center-aligned, some are left-aligned.
I did not encounter problematic grammatical errors.
I did not find the text to be culturally insensitive in any way.
The book's coverage of regression is outstanding. In particular, this is the most comprehensive coverage of regression diagnostics I've seen in a research methods text. There is also an entire chapter on logit regression, whereas most texts may... read more
The book's coverage of regression is outstanding. In particular, this is the most comprehensive coverage of regression diagnostics I've seen in a research methods text. There is also an entire chapter on logit regression, whereas most texts may devote a paragraph to it at best. Most texts jump right into inference after descriptive statistics, but the authors add a chapter on probability before discussing inference, which is a nice addition. However, there are certain topics that are not covered or barely covered. There is only a cursory discussion of sampling distributions and only one paragraph on the Central Limit Theorem. The authors fly through the discussion of t tests and there is no coverage of the assumptions needed for independent sample t tests. The only coverage of ANOVA is in the discussion of model fit. I think this is an excellent text for instructors who want to emphasize regressions, but those who like to build up to regressions with t tests and ANOVA might find this text lacking.
The book is accurate and thorough, particularly regarding regression and regression diagnostics. On a few occasions, the authors talked about "accepting the null hypothesis" if the p value is greater than 0.05, which is too strong, but apart from that, I saw no problems with the analysis or interpretations.
A nice feature of this text is that it is written in open source R markdown, so instructors can adapt and add content as desired, making updates easy to implement.
The book has the right tone and level of technical information for Ph.D. students in the social sciences, but I think parts of it are too advanced for the typical MPA student. There are entire chapters on calculus (chapter 8) and matrix algebra (chapter 11), which in my opinion are unnecessary for and would likely intimidate most MPA students.
The terminology and framework are consistent and easy to follow.
This book is best covered as a whole. I think it would be difficult to use only a subset of chapters as they all build off and reference each other. For instance, there are numerous instances where terminology (e.g., null hypothesis, Likert scale) are briefly introduced with the promise to cover them in more detail in future chapters.
The book starts off with an emphasis on theory as the basis and guiding force of quality social science research and the topics are presented with this theme in mind. I applaud the authors for making theory and causality a guiding principle for the organization of the text because too many research methods texts leave the students with the impression that quantitative research involves looking at the data, discerning patterns, and then developing a theory. I think the organization of the text is ideal with the emphasis of theory and testable hypotheses as the starting point of research.
The text has no interface or navigation problems.
There are a number of minor grammatical mistakes and typos, but nothing that would cause confusion for the reader.
The text uses only one example throughout (an analysis of a survey of perceptions of climate change risk by political ideology and sex). Students outside of political science might not find the example interesting or relevant for the research problems they are likely to face. The title of the text implies that it is designed for public administration students. The text should illustrate at least some of the concepts with research problems public administrators are likely to face.
Overall, I think this is an excellent text, but I think it is too advanced and technical, and has too much of a political science focus, for MPA students.
In terms of content, this text contains nearly everything I generally cover in my introductory statistics class. This book is aimed at graduate students, but I am reviewing it for undergraduate social science majors. Overall, I think this will... read more
In terms of content, this text contains nearly everything I generally cover in my introductory statistics class. This book is aimed at graduate students, but I am reviewing it for undergraduate social science majors. Overall, I think this will be a good text. It does seem that the authors assume some level of knowledge of R before beginning the book. There is additional information available online and in the appendix, but I think more of an introduction to R placed at the beginning of the book would have been useful, given how prominently R features in the text. I share the author's frustration with teaching this course-- the cost of these textbooks is high and the relationship between statistics and actual research is sometimes spotty. I think this text does a good job of really connecting statistical techniques to social science research.
I saw no glaring inaccuracies in the text.
One great thing about statistics books is that the formula for standard deviation is unlikely to change any time soon. I see this text as having a long self life. The only thing that might change would be the R code, but the authors have noted that there is more information available about the R online.
I found the writing in this text to be very clear. One nice addition would be titles for all of the R code that corresponded with a quick reference list for the code included. Then, if a student was looking for the R code to recode a variable (page 80), for instance, they could quickly find it. Given the online format, one can search for this information in the text, but I think students who print the text might find it useful.
The book is generally consistent in terms of format.
This is one of the text's strong points. They cover a lot of information in an efficient manner, and they also include some useful asides. For instance, in section 5.3.3, when discussing statistical inference, they have a header entitled "Some Miscellaneous Notes about Hypothesis Testing." I find this sort of discussion very useful. This section included information on why .05 is a standard, Type I and Type II errors, etc. While these are clearly important, they are secondary compared to general ideas about inference. In this sense, I think the layout of the text is very reader friendly. The bolded terms are also crucial. I also appreciate the "Summary" sections at the end of chapters.
I think the organization is very good. In an undergraduate course, I'm not sure I will go in as much depth as is included in some of the later chapters (ex: having students do quartile plots for residuals), but I still find it useful. Moreover, an instructor could easily pick and choose which sections they wanted students to read given the section headers. I might just move the R appendix to the beginning of the text.
I think that the graphics (some in color) are particularly useful. Moreover, I think that the inclusion of R output throughout the text was generally useful. I would like to have seen more presentations of "cleaned" data, to show students how they should present their data output. There are several points in the text where the R code seems to be out of place. For instance, on page 76, part of the code goes outside the grey shaded box.
The grammar and writing style of the textbook was good. I saw no major problems.
The text has the occasional nerd-culture reference (ex: page 40 contained a Monty Python reference) and sports references (ex: lots of baseball references in the probability chapter). In another example, when talking about sampling strategies, the authors write about how one might observe a potential partner in a variety of circumstances to determine whether they would me a good match. While I find this example a bit odd, I think the impulse to include interesting examples is a good one.
I am planning on using this for an undergraduate class, and it seems like the authors have pitched this for graduate students. I don't anticipate too many differences, but I'm excited to see how this textbook works for undergrads.
This book definitely tackles many of the issues facing students doing quantitative analysis in social sciences. The authors try to cover the main data analysis techniques, providing readers with ample examples to better appreciate the complexity... read more
This book definitely tackles many of the issues facing students doing quantitative analysis in social sciences. The authors try to cover the main data analysis techniques, providing readers with ample examples to better appreciate the complexity and dynamism of each model. While no text can attend to all models with detail, this book tries to educate the reader holistically and achieves this breadth, in my opinion, very effectively.
The book is accurate and error-free.
The book is certainly up-to-date and includes R codes to apply the models in the R interface.
The forte of the book is explaining complex econometrics models in very simple language with ample examples.
The text is internally consistent.
The books has various subheadings and makes the division of material very clear at the outset.
The topics are presented in a logical and clear fashion.
There are no significant interface issues.
The text is free of grammatical errors.
The books is not culturally offensive in any way.
The authors can improve the teaching capacity of the material by adding a sequel to the book, discussing more complicated models used in social sciences.
Table of Contents
I Theory and Empirical Social Science
- 1 Theories and Social Science
- 2 Research Design
- 3 Exploring and Visualizing Data
- 4 Probability
- 5 Inference
- 6 Association of Variables
II Simple Regression
- 7 The Logic of Ordinary Least Squares Estimation
- 8 Linear Estimation and Minimizing Error
- 9 Bi-Variate Hypothesis Testing and Model Fit
- 10 OLS Assumptions and Simple Regression Diagnostics
III Multiple Regression
- 11 Introduction to Multiple Regression
- 12 The Logic of Multiple Regression
- 13 Multiple Regression and Model Building
- 14 Topics in Multiple Regression
- 15 The Art of Regression Diagnostic
IV Generalized Linear Model
- 16 Logit Regression
- 17 Appendix: Basic
About the Book
The focus of this book is on using quantitative research methods to test hypotheses and build theory in political science, public policy and public administration. It is designed for advanced undergraduate courses, or introductory and intermediate graduate-level courses. The first part of the book introduces the scientific method, then covers research design, measurement, descriptive statistics, probability, inference, and basic measures of association. The second part of the book covers bivariate and multiple linear regression using the ordinary least squares, the calculus and matrix algebra that are necessary for understanding bivariate and multiple linear regression, the assumptions that underlie these methods, and then provides a short introduction to generalized linear models.The book fully embraces the open access and open source philosophies. The book is freely available in the SHAREOK repository; it is written in R Markdown files that are available in a public GitHub repository; it uses and teaches R and RStudio for data analysis, visualization and data management; and it uses publically available survey data (from the Meso-Scale Integrated Socio-geographic Network) to illustrate important concepts and methods. We encourage students to download the data, replicate the examples, and explore further! We also encourage instructors to download the R Markdown files and modify the text for use in different courses.
About the Contributors
Hank Jenkins-Smith earned his PhD in political science from the University of Rochester (1985). He is a George Lynn Cross Research Professor in the Political Science Department at the University of Oklahoma, and serves as a co-Director of the National Institute for Risk and Resilience. Professor Jenkins-Smith has published books and articles on public policy processes, national security, weather, and energy and environmental policy. He has served on National Research Council Committees, as an elected member on the National Council on Radiation Protection and Measurement, and as a member of the governing Council of the American Political Science Association. His current research focuses on theories of the public policy process, with particular emphasis on the management (and mismanagement) of controversial technical issues involving high risk perceptions on the part of the public. In 2012 he and collaborators initiated a series of studies focused on social responses to the risks posed by severe weather. This work continues with a panel survey of Oklahoma households, funded by the National Science Foundation, to track perceptions of and responses to changing weather patterns. In his spare time, Professor Jenkins-Smith engages in personal experiments in risk perception and management via skiing, scuba diving and motorcycling.
Joseph Ripberger currently works at the Center for Risk and Crisis Management, University of Oklahoma. Joseph does research in Public Policy. Their current project is 'Glen Canyon Dam.'