Muutke küpsiste eelistusi

E-raamat: Research Methods in Practice: Strategies for Description and Causation

  • Formaat: 648 pages
  • Ilmumisaeg: 24-Mar-2014
  • Kirjastus: SAGE Publications Inc
  • Keel: eng
  • ISBN-13: 9781483323589
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 82,75 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
  • Formaat: 648 pages
  • Ilmumisaeg: 24-Mar-2014
  • Kirjastus: SAGE Publications Inc
  • Keel: eng
  • ISBN-13: 9781483323589
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

This textbook is specially designed for use with students with diverse backgrounds in research and who vary in how they will use research later in their careers. The text is organized around two kinds of research: strategies for description and strategies to reveal causation. Unlike many texts, this text covers causation at length. Part 1 presents foundations, with material on theories, models, research questions, and qualitative research. Part 2 covers strategies for description, with chapters on measurement, sampling, secondary data, surveys and other primary data. Part 3 deals with statistical tools and their interpretation, and Part 4 details strategies for causation, with chapters on observational studies, regression, and randomized experiments. Part 5 considers the politics, production, and ethics of research, and offers tips on how to find, review, and present research. The reader-friendly color layout provides color photos, summary charts, and process diagrams, along with margin notes, discussion and review questions, and critical thinking boxes. This second edition contains more explicit guidance for those planning or doing their own research project or thesis. The companion web site is now expanded with study tools for students, plus lecture slides, test bank, sample syllabi, and instructor’s manual for teachers. Annotation ©2014 Ringgold, Inc., Portland, OR (protoview.com)

Providing a state-of-the-art introduction to research and analytical methods, this book covers methods and concepts of contemporary research allowing readers to grasp the logic, and limits, of modern research.

Arvustused

Research Methods in Practice offers a combination of academic weight, coupled clarity and an easy to follow style that will allow students and practitioners to take their research skills to a level otherwise considered unrealistic.  If students are looking to purchase one text that will provide sound coverage of research methods coupled with examples that provide clarity of application this is it.











The text is very well organized.  Often reading research methods texts can lead to more confusion than the student originally had.  This text, by contrast is presented in a clear, logical, tool box approach.  -- Matthew Cooper Remler and Van Ryzin have filled a void that has too long complicated the job of teaching statistical methods and research design to graduate students of applied social science and public policy.



 



I believe this is the best text available for teaching students the fundamentals of research design and statistics, and introducing them to the difficulties inherent in evaluation research and causal inference. -- Dave E. Marcotte What do you get when you cross writings from an electrical engineering-health economist (Dahlia Remler) with a psychologist-geographer (Gregg Van Ryzin)? An eclectic array of fundamental ideas on research portrayed and measured across multidisciplinary domains, i.e., Research Methods in Practice. Just about every topic you might consider for developing theory and building research questions, to formulating knowledge and identifying relevant methods is discussed. Accordingly, experimental approaches, data analyses, and research methods are exposed to the reader in a clear, concise fashion.  



 



Research Methods in Practice is the go-to book for that quick start in learning how to do research. -- Gary Langford The strengths of this text include the many contemporary references to current events, the language and graphics. The strength is also the simplicity (which is effective) of research, that we do it daily and that it should not be seen as a laborious task (although it may be), but rather as a necessary part of whatever we plan to do in life as scholars, researchers, civil servants, doctors, lawyers, social workers, etc. The ease of applicability of research and the research process as a deliberate, strategic, systematic way to gather credible and useable data/information is one of the most effective aspects of the textbook. -- Khadijah O. Miller This is a well-organized book that deals with a good number of issues. It develops the discussion into an appropriate depth for the students on undergraduate and post graduate programmes without confusion.



 



[ This book] gives the student the opportunity to see things in a different way from the standard texts. -- Sue Lillyman

Preface xxix
Acknowledgments xxxiii
About the Authors xxxv
PART I FOUNDATIONS
1(92)
Learning Objectives
2(1)
1 Research in the Real World
3(22)
Do Methods Matter?
3(2)
Good Evidence Comes From Well-Made Research
3(1)
May the Best Methods Win
4(1)
Research-Savvy People Rule
4(1)
Research, Policy, and Practice
5(1)
Performance Measurement
5(1)
Evaluation Research
5(1)
Evidence-Based Policy and Programs
6(1)
Evidence Can Mislead
6(1)
Misleading Measurements
6(1)
Misleading Samples
6(1)
Misleading Correlations
7(1)
What Is Research?
7(4)
Secondary and Primary Research
7(1)
It Comes in Various Shapes and Sizes
8(1)
It's Never Perfect
8(1)
It's Uncertain and Contingent
8(1)
It Aims to Generalize
9(1)
Bits and Pieces of a Puzzle
9(1)
It Involves Competition and Criticism
10(1)
It Can Be Quantitative, Qualitative, or a Mix of Both
10(1)
It Can Be Applied or Basic
10(1)
Descriptive and Causal Research
11(1)
Description: What Is the World Like?
11(1)
Causation: How Would the World Be Different If Something Changed?
12(1)
Description of a Correlation Is Not Proof of Causation
12(1)
Epistemology: Ways of Knowing
12(3)
The Scientific Method
13(1)
Is There One Truth in Social Science?
13(1)
Induction and Deduction
14(1)
Proof Requires Fresh Data
14(1)
Approaching Research From Different Angles
15(2)
Consuming Research
15(1)
Commissioning Research
16(1)
Conducting Research
16(1)
Ethics of Research
17(4)
Poisoned by New York's Best Restaurants
17(1)
History of Human Subjects Abuses in Research
18(1)
Principles of Ethical Research Emerge
18(1)
What Constitutes Informed Consent?
19(1)
Ethical Issues Depend on Research Form and Context
20(1)
Conclusion: The Road Ahead
21(1)
Chapter Resources
21(3)
Key Terms
21(1)
Exercises
21(2)
Student Study Site
23(1)
Learning Objectives
24(1)
2 Theory, Models, and Research Questions
25(34)
Fighting Crime in New York City
25(1)
What Is a Theory?
26(2)
Theories Identify Key Variables
26(1)
Theories Tell Causal Stories
26(1)
Theories Explain Variation
27(1)
Theories Generate Testable Hypotheses
28(1)
Theories Focus on Modifiable Variables
28(1)
Where Do Theories Come From?
28(2)
Grand Social Theories
28(1)
Academic Disciplines
29(1)
Induction and Deduction
29(1)
Exploratory and Qualitative Research
29(1)
Theories, Norms, and Values
30(1)
What Is a Model?
30(6)
Variables and Relationships
30(1)
Independent and Dependent Variables
31(1)
Box 2.1 Independent And Dependent Variables
32(1)
Causal Mechanisms
32(1)
Box 2.2 Equations As Models: Right-Hand Side And Left-Hand Side Variables
33(1)
Direction of a Relationship
33(1)
Naming Variables
34(1)
Models With Multiple Causes
35(1)
Causal and Noncausal Relationships
35(1)
Unit of Analysis
36(2)
Same Theory, Different Unit of Analysis
36(2)
Logic Models
38(7)
Box 2.3 What Is A Logic Model?
38(1)
Do Smaller Classes Help Kids Learn?
39(1)
Intervening Variables
40(1)
What About Other Causes?
41(1)
Usefulness of a Logic Model
41(1)
Box 2.4 China Launches Nationwide Aids Prevention Program
42(1)
Tips for Creating a Logic Model
43(2)
Inputs, Activities, Outputs, and Outcomes
45(2)
Additional Issues in Theory Building
47(2)
Interpretivist Theory
47(1)
Does Theory Shape Observation?
47(1)
Theories of the Independent Variable
47(1)
Moderators
48(1)
Hierarchical (Multilevel) Models and Contextual Variables
48(1)
Theoretical Research
49(1)
How to Find and Focus Research Questions
49(3)
Applied Research Questions
49(1)
Questions You Ideally Want to Answer, and Those You Really Can
50(1)
Know If Your Question Is Descriptive or Causal
51(1)
Make Your Question Positive, Not Normative
51(1)
Generating Questions and Ideas
51(1)
Conclusion: Theories Are Practical
52(2)
Box 2.5 Critical Questions To Ask About Theory, Models, And Research Questions
53(1)
Box 2.6 Tips On Doing Your Own Research: Theory, Models, And Research Questions
53(1)
Chapter Resources
54(4)
Key Terms
54(1)
Exercises
54(2)
Student Study Site
56(2)
Learning Objectives
58(1)
3 Qualitative Research
59(34)
Fighting Malaria in Kenya
59(2)
Theory, Causes, and Qualitative Research
60(1)
What Is Qualitative Research?
61(4)
Contrasting Qualitative With Quantitative Research
61(2)
Schools of Thought in Qualitative Research
63(1)
Advantages of Qualitative Research
64(1)
Existing Qualitative Data
65(2)
Archival and Other Written Documents
66(1)
Visual Media, Popular Culture, and the Internet
66(1)
Qualitative Interviews
67(3)
Unstructured Interviews
67(1)
Semistructured Interviews
67(2)
Asking Truly Open-Ended Questions
69(1)
The Power of Probes
69(1)
Some Practical Considerations When Doing Interviews
70(1)
Focus Groups
70(3)
What Do People Think of Congestion Pricing?
71(1)
Moderating a Focus Group
72(1)
Why a Focus Group? Why Not Individual Interviews?
73(1)
Telephone and Online Focus Groups
73(1)
Qualitative Observation
73(1)
Participant Observation and Ethnography
74(2)
Why Do the Homeless Refuse Help?
74(1)
Levels on a Participation-Observation Continuum
75(1)
Secret Shopping and Audit Studies
75(1)
Case Study Research
76(1)
Maryland's Gun Violence Act
76(1)
Selecting a Case to Study
77(1)
Comparing Cases
77(1)
Qualitative Data Analysis
77(5)
Integration of Analysis and Data Gathering
78(1)
Tools of Qualitative Analysis
78(1)
Coding and Content Analysis
79(2)
Qualitative Data Analysis Software
81(1)
The Qualitative-Quantitative Debate
82(5)
A Brief History of the Debate
82(1)
Blurring the Lines: How Qualitative and Quantitative Approaches Overlap
83(1)
A Qualitative-Quantitative Research Cycle
83(3)
Mixed-Methods Research and Triangulation
86(1)
Box 3.1 Transition Services For Incarcerated Youth: A Mixed Methods Evaluation Study
86(1)
Ethics in Qualitative Research
87(1)
Presenting Qualitative Data
87(1)
Can You Obtain Informed Consent?
87(1)
Should You Help People With Their Problems?
87(1)
Should You Empower People?
88(1)
Conclusion: Matching Methods to Questions
88(2)
Box 3.2 Critical Questions To Ask About A Qualitative Study
89(1)
Box 3.3 Tips On Doing Your Own Qualitative Research
89(1)
Chapter Resources
90(3)
Key Terms
90(1)
Exercises
90(2)
Student Study Site
92(1)
PART II STRATEGIES FOR DESCRIPTION
93(148)
Learning Objectives
94(1)
4 Measurement
95(46)
The U.S. Poverty Measure
95(1)
What Is Measurement?
95(2)
Measurement in Qualitative Research
96(1)
Performance Measurement
96(1)
Measurement: The Basic Model and a Road Map
96(1)
Conceptualization
97(3)
Defining Can Be Difficult
97(1)
Where Do Conceptualizations Come From?
98(1)
Box 4.1 Is Poverty The Same Thing The World Over?
98(1)
Manifest and Latent Constructs
99(1)
Dimensions
99(1)
Operationalization
100(6)
Birth of the U.S. Poverty Measure
100(1)
Instruments
101(1)
Box 4.2 Operational Definition Of Poverty In The United States
101(1)
Protocols and Personnel
102(1)
Proxies and Indicators
102(1)
Composite Measures: Scales and Indexes
103(2)
Box 4.3 What Is A Likert Scale?
105(1)
Validity
106(4)
Box 4.4 Using Items That Vary In Difficulty: Item Response Theory
107(1)
Is the U.S. Poverty Measure Valid?
107(1)
Face Validity
108(1)
Content Validity
108(1)
Valid for What Purpose?
109(1)
Criterion-Related Validity
110(4)
Self-Reported Drug Use: Is It Valid?
110(1)
Does the Measure Predict Behavior?
110(1)
Does the Measure Relate to Other Variables as Expected?
111(1)
Limitations of Validity Studies
112(1)
Box 4.5 The Various (Measurement) Validities
113(1)
Box 4.6 Example Of A Validity Study
114(1)
Measurement Error
114(4)
Bias
115(1)
Random Error---Noise
115(1)
Box 4.7 Bias, Bias Everywhere
116(1)
Bias and Noise in the U.S. Poverty Measure
116(1)
Box 4.8 Classical Test Theory
117(1)
Reliability
118(6)
Why Reliability Matters
118(3)
Many Ways to Tell If a Measure Is Reliable
121(1)
Validity and Reliability Contrasted and Compared
122(2)
Validity and Reliability in Qualitative Research
124(1)
Levels of Measurement
124(7)
Quantitative Measures
125(1)
Box 4.9 Unit/Level Of Measurement/Analysis?
126(1)
Categorical Measures
126(2)
Turning Categorical Variables Into Quantitative Ones
128(2)
Units of Analysis and Levels of Measurement
130(1)
Measurement in the Real World: Trade-offs and Choices
131(4)
What Will It Cost?
131(1)
Is It Ethical?
131(1)
How Will It Affect the Quality and Rate of Responding?
131(1)
Validity-Reliability Trade-off
132(1)
High Stakes? Gaming and Other Behavioral Responses
133(1)
Use Multiple Measures for Multiple Dimensions---or Aggregate to One Measure?
133(1)
Conclusion: Measurement Matters
134(1)
Box 4.10 Critical Questions To Ask About Measurement
134(1)
Box 4.11 Tips On Doing Your Own Research: Measurement
135(1)
Chapter Resources
135(5)
Key Terms
135(1)
Exercises
136(3)
Student Study Site
139(1)
Learning Objectives
140(1)
5 Sampling
141(40)
Gauging the Fallout From Hurricane Katrina
141(1)
Generalizability
141(4)
Population of Interest, Sampling, and Generalizability
142(1)
Are Experiments More Generalizable?
143(1)
Replicating Research and Meta-Analysis
143(1)
Are Relationships More Generalizable? Health and Happiness in Moldova
144(1)
Generalizability of Qualitative Studies
145(1)
Basic Sampling Concepts
145(4)
Population, Sample, and Inference
145(2)
Census Versus Sample
147(1)
How to Select a Sample: Sampling Frames and Steps
148(1)
Problems and Biases in Sampling
149(5)
Coverage Problems
149(1)
Nonresponse Problems
150(1)
When Does Nonresponse Cause Bias?
150(2)
When Do Coverage Problems Cause Bias?
152(1)
Box 5.1 Steps In Assessing Coverage And Nonresponse Bias
153(1)
Box 5.2 Sampling Bias
154(1)
Ethics of Nonresponse
154(1)
Nonprobability Sampling
154(5)
Voluntary Sampling
155(1)
Box 5.3 Steps In Assessing Volunteer Bias
155(1)
Convenience Sampling
156(1)
Snowball Sampling
156(1)
Quota Sampling
156(1)
Sampling Online: Open Web Polls and Internet Access Panels
156(2)
Purposive Sampling and Qualitative Research
158(1)
Random (Probability) Sampling
159(2)
The Contribution of Random Sampling
159(1)
Random Sampling Versus Randomized Experiments
160(1)
Simple Random Sampling
160(1)
Sampling Variability
161(1)
Sampling Distributions, Standard Errors, and Confidence Intervals
161(7)
Confidence Intervals (Margins of Error)
162(1)
Box 5.4 Relationship Between Various Precision Measures
163(2)
Sample Size and the Precision of Government Statistics
165(1)
Determining How Large a Sample You Need
165(2)
What Is the True Sample Size?
167(1)
Sampling in Practice
168(6)
Systematic Sampling
168(1)
Stratified Sampling
168(1)
Disproportionate Sampling (Oversampling)
169(1)
Poststratification Weighting
170(1)
Sampling With Probabilities Proportional to Size
171(1)
Multistage and Cluster Sampling
171(1)
Design Effects: Complex Survey Sampling Corrections
172(1)
Random Digit Dialing Sampling
173(1)
Sampling and Generalizability: A Summary
174(2)
Box 5.5 Critical Questions To Ask About Sampling In Studies
174(1)
Box 5.6 Tips On Doing Your Own Research: Sampling
175(1)
Chapter Resources
176(4)
Key Terms
176(1)
Exercises
176(3)
Student Study Site
179(1)
Learning Objectives
180(1)
6 Secondary Data
181(30)
Tracking the Flu
181(1)
Big Data and the Virtual World
182(1)
Quantitative Data---and Their Forms
182(6)
Quantitative Data Versus Quantitative Variables
182(1)
Forms of Quantitative Data
183(1)
Micro, Aggregate, and Multilevel Data
184(1)
Box 6.1 Unit Of Observation Versus Unit Of Analysis
184(1)
Time Dimension of Data
184(2)
Metadata
186(2)
Where Do Quantitative Data Come From?
188(1)
Administrative Records
188(3)
Adapting Administrative Data for Research
188(2)
Vital Statistics, Crime Reports, and Unemployment Claims
190(1)
Data for Purchase
190(1)
Ethics of Administrative Record Data
191(1)
Published Data Tables
191(3)
Where to Find Published Tables
194(1)
Published Time-Series and Panel Data
194(1)
Public Use Microdata
194(9)
Secondary Analysis of Public Use Data: A New Model of Research?
194(1)
Know the Major Surveys in Your Field
195(7)
Accessing and Analyzing Public Use Data
202(1)
Data Archives
202(1)
Ethics of Public Use Microdata
203(1)
Secondary Qualitative Data
203(1)
Linking Data
204(1)
Some Limitations of Secondary Data
204(2)
Does Data Availability Distort Research?
205(1)
When to Collect Original Data?
205(1)
Conclusion
206(1)
Box 6.2 Critical Questions To Ask About Secondary Data
206(1)
Box 6.3 Tips On Doing Your Own Research: Secondary Data
206(1)
Chapter Resources
207(3)
Key Terms
207(1)
Exercises
207(2)
Student Study Site
209(1)
Learning Objectives
210(1)
7 Surveys and Other Primary Data
211(30)
Taking the Nation's Economic Pulse
211(1)
When Should You Do a Survey?
211(2)
Do You Know Enough About the Topic?
212(1)
Does the Information Exist Already in Another Source?
212(1)
Can People Tell You What You Want to Know?
212(1)
Will People Provide Truthful Answers?
213(1)
Steps in the Survey Research Process
213(2)
Identify the Population and Sampling Strategy
213(1)
Develop a Questionnaire
213(1)
Pretest Questionnaire and Survey Procedures
214(1)
Recruit and Train Interviewers
214(1)
Collect Data
214(1)
Enter and Prepare Data for Analysis
215(1)
Analyze Data and Present Findings
215(1)
Modes of Survey Data Collection
215(9)
Intercept Interview Surveys
215(1)
Household Interview Surveys
216(1)
Telephone Interview Surveys
217(1)
Mail Self-Administered Surveys
218(2)
Group Self-Administered Surveys
220(1)
Web or Internet Surveys
220(1)
Box 7.1 Web Survey Software
221(1)
Establishment (Business or Organization) Surveys
222(1)
Panel or Longitudinal Surveys
222(1)
Choosing or Mixing Modes
223(1)
Crafting a Questionnaire
224(7)
Start With Survey Purpose or Constructs
224(1)
If You Could Ask Only One or Two Questions. . .
224(1)
Prepare Mock Tables and Charts of Survey Results
224(1)
Look for Prior Surveys on Your Topic
224(1)
Hook Respondents With Your First Few Questions
225(1)
Box 7.2 Comparing Opening Questions
225(1)
Closed-Ended Versus Open-Ended Questions
226(1)
Box 7.3 Questionnaire Composed Of Open-Ended Questions
227(1)
Some Advice on Question Wording
227(3)
Physical and Graphical Design
230(1)
Put Yourself in Your Respondent's Shoes
230(1)
Ethics of Survey Research
231(1)
Informed Consent
231(1)
Pushing for a High Response Rate
231(1)
Overburdening Respondents
231(1)
Protecting Privacy and Confidentiality
231(1)
Surveying Minors and Other Vulnerable Populations
232(1)
Making Survey Data Available for Public Use
232(1)
Other Ways to Collect Primary Data
232(4)
Trained Observation
233(2)
Scientific Instruments
235(1)
Computer Code and Data Extraction Algorithms
236(1)
Conclusion
236(2)
Box 7.4 Critical Questions To Ask About Surveys And Other Primary Data
236(1)
Box 7.5 Tips On Doing Your Own Survey
237(1)
Chapter Resources
238(3)
Key Terms
238(1)
Exercises
238(1)
Student Study Site
239(2)
PART III STATISTICAL TOOLS AND THEIR INTERPRETATION
241(106)
Learning Objectives
242(1)
8 Making Sense of the Numbers
243(38)
"Last Weekend I Walked Eight"
243(1)
Units, Rates, and Ratios
243(5)
What Units?
243(1)
Rates or Why Counts Often Mislead
244(1)
Box 8.1 Relevant Comparisons
245(1)
Percent Change and Percentage Point Change
245(1)
The Strangeness of Percent Change on the Return Trip
246(1)
Rates of Change and Rates of Change of Rates
246(1)
Odds
247(1)
Prevalence and Incidence
247(1)
Statistics Starting Point: Variables in a Data Set
248(1)
Distributions
249(3)
Distribution of a Categorical Variable
249(2)
Distribution of a Quantitative Variable
251(1)
Measures of Center: Mean and Median
252(1)
Box 8.2 Mean: The Formula
252(1)
When to Use Median? When to Use Mean?
253(1)
Measures of Spread and Variation
253(4)
Standard Deviation
254(1)
Box 8.3 Standard Deviation: The Formula
254(1)
Pay Attention to the Standard Deviation, Not Just the Mean
255(1)
Standardized (z) Scores
255(1)
Quantiles: Another Way to Measure Spread
256(1)
Coefficient of Variation: A Way to Compare Spread
256(1)
Relationships Between Categorical Variables
257(3)
Cross-Tabulation
257(2)
Relative Risks and Odds Ratios: Another Way to Show Relationships in Categorical Data
259(1)
Adjusted and Standardized Rates: When to Use Them
260(1)
Relationships Between Quantitative Variables: Scatterplots and Correlation
260(4)
Scatterplots
260(2)
Correlation
262(1)
Box 8.4 Correlation: The Formula
262(1)
Relationships Between a Categorical and a Quantitative Variable
263(1)
Box 8.5 Which One Is The Dependent Variable? Which One Is The Independent Variable?
264(1)
Simple Regression: Best-Fit Straight Line
264(5)
Box 8.6 Simple Regression: The Equations
265(1)
Interpreting the Regression Coefficient (Slope)
266(1)
Box 8.7 Steps For Interpreting A Regression Coefficient
266(1)
Can a Regression Coefficient Be Interpreted as a Causal Effect?
267(1)
Changes Versus Levels
267(1)
R-Squared and Residuals: How Well Does the Line Fit the Data?
268(1)
Practical Significance
269(2)
Practical Significance Is a Matter of Judgment
269(1)
Effect Size
270(1)
Statistical Software
271(1)
Spreadsheets
271(1)
Statistical Packages: SAS, SPSS, Stata, and R
271(1)
Specialized Modeling and Matrix Language Programs
271(1)
Conclusion: Tools for Description and Causation
271(2)
Box 8.8 Tips On Doing Your Own Research: Descriptive Statistics
272(1)
Chapter Resources
273(7)
Key Terms
273(1)
Exercises
273(6)
Student Study Site
279(1)
Learning Objectives
280(1)
9 Making Sense of Inferential Statistics
281(32)
But Is It Significant?
281(1)
Statistical Inference: What's It Good For?
281(1)
The Sampling Distribution: Foundation of Statistical Inference
282(3)
What a Sampling Distribution Looks Like
282(2)
The Standard Error (of a Proportion)
284(1)
The Standard Error (of a Mean)
285(1)
Confidence Intervals
285(6)
Univariate Statistics and Relationships Both Have Confidence Intervals
286(1)
Confidence Intervals Reflect Only Some Sources of Error
287(1)
Calculating a Confidence Interval (Margin of Error) for a Proportion
287(1)
Calculating a Confidence Interval (Margin of Error) for a Mean
288(2)
How Big Does the Sample Size Need to Be? Getting the Precision You Want
290(1)
Significance Tests
291(7)
Falsification and the Logic of Significance Testing
292(1)
Running a Significance Test
292(1)
p Values
293(1)
Significance Tests for Simple Regression
294(2)
Chi-Square Test of Cross-Tabs
296(1)
Other Test Statistics
297(1)
Statistical Significance, Practical Significance, and Power
298(5)
Combinations of Statistical and Practical Significance
298(2)
Box 9.1 Sources Of Statistical Significance And Of Statistical Insignificance
300(1)
Failing to Recognize a Difference: Type II Errors
301(1)
Power
301(1)
Multiple Comparison Corrections
302(1)
Sample Size Calculations for Significance Tests
302(1)
Adjusting Inference for Clustering and Other Complex Sampling
303(1)
Issues and Extensions of Statistical Inference
303(2)
Inference With a Nonprobability Sample: What Does It Mean?
303(1)
Bootstrapping: Inference for Statistics With No Standard Error Formulas
304(1)
Bayesian Inference
305(1)
Conclusion
305(1)
Box 9.2 Tips On Doing Your Own Research: Inferential Statistics
306(1)
Chapter Resources
306(6)
Key Terms
306(1)
Exercises
307(3)
Student Study Site
310(2)
Learning Objectives
312(1)
10 Making Sense of Multivariate Statistics
313(34)
Multiple Regression: The Basics
313(7)
Box 10.1 How To Run A Multiple Regression Using Software
314(1)
Multiple Regression for Prediction
315(1)
Box 10.2 Steps For Predicting With Regression
316(1)
The Danger (and Necessity) of Out-of-Sample Extrapolation
316(1)
R-Squared and Adjusted R-Squared
316(1)
All Else Held Constant: A Bit More Mathematics
317(1)
Multicollinearity
318(1)
Standardized Coefficients: The Relative Importance of Independent Variables
319(1)
Inference for Regression
320(3)
Standard Error of the Coefficient
320(1)
Confidence Intervals in Regression
321(1)
Confidence Interval of a Predicted Value
321(1)
Significance Testing in Regression
321(1)
Influences on Inference in Multiple Regression
322(1)
Categorical Independent Variables
323(4)
Dummy Variables in Regression
323(1)
Categorical Variables With More Than Two Possible Values
324(1)
Box 10.3 Representing A Categorical Variable With More Than Two Categories: Diabetes Example
324(1)
Interpreting the Coefficient of a Dummy Variable
325(1)
Box 10.4 Interpreting The Coefficient Of A Dummy Variable
326(1)
Analysis of Variance (ANOVA)
327(1)
Interactions in Regression
327(2)
How to Use and Interpret Interaction Variables
327(2)
Interactions With Quantitative Variables
329(1)
Always Include Both Main Effects
329(1)
Functional Form and Transformations in Regression
329(2)
How to Fit a Curved Relationship
330(1)
How to Interpret Coefficients When a Variable Is Logged
330(1)
The Value of Robustness and Transparency
331(1)
Categorical Variables as Dependent Variables in Regression
331(2)
Linear Probability Model
332(1)
Logistic and Probit Regression
332(1)
What If the Dependent Variable Has More Than Two Categories?
333(1)
Beware of Unrealistic Underlying Assumptions
333(1)
Which Statistical Methods Can I Use?
333(2)
Other Multivariate Methods
335(7)
Path Analysis
335(1)
Factor Analysis
336(1)
Structural Equation Modeling
337(1)
Multilevel Models
338(1)
Time Series and Forecasting
339(1)
Panel Data Methods
340(1)
Spatial Analysis
340(1)
Limited Dependent Variables
341(1)
Survival Analysis
341(1)
More Multivariate Methods Not Covered
341(1)
Conclusion
342(1)
Box 10.5 Tips On Doing Your Own Research: Multivariate Statistics
342(1)
Chapter Resources
343(4)
Key Terms
343(1)
Exercises
343(2)
Student Study Site
345(2)
PART IV STRATEGIES FOR CAUSATION
347(154)
Learning Objectives
348(1)
11 Causation
349(28)
Family Dinners and Teenage Substance Abuse
349(2)
Correlation Is Not Causation
349(1)
Box 11.1 Children Who Have Frequent Family Dinners Less Likely To Use Marijuana, Tobacco, And Drink Alcohol
350(1)
Possible Explanations of a Correlation
351(4)
Causation and Reverse Causation
351(1)
Common Causes
351(1)
Bias From a Common Cause
352(2)
Bias From Reverse Causation: Simultaneity Bias
354(1)
Some More Correlations That Imply Causation
354(1)
Causal Mechanisms
355(3)
Indirect and Direct Causal Effects
356(1)
Chance Correlations and Statistical Significance
357(1)
Arrows, Arrows Everywhere
357(1)
Why Worry About the Correct Causal Model?
358(1)
Evidence of Causation: Some Initial Clues
358(3)
The Cause Happens Before the Effect
358(1)
The Correlation Appears in Many Different Contexts
359(1)
Box 11.2 Prominent Epidemiologists Discuss Clues Of Causation
359(1)
A Plausible Mechanism and Qualitative Evidence
359(1)
There Are No Plausible Alternative Explanations
360(1)
Common Causes Are Accounted For in the Analysis
361(1)
Detective Work and Shoe Leather
361(1)
Self-Selection and Endogeneity
361(1)
Self-Selection
362(1)
Endogeneity
362(1)
The Counterfactual Definition of Causation
362(2)
Box 11.3 Causation And Causality---Two Words For The Same Thing
363(1)
Box 11.4 Counterfactuals And Potential Outcomes
363(1)
If We Only Had a Time Machine
364(1)
Experimentation and Exogeneity: Making Things Happen
364(7)
Can Exercise Cure Depression?
365(1)
Why Experimentation Beats Passive Observation
365(1)
Exogeneity: Intervening in the World
366(1)
Box 11.5 Exogenous Or Endogenous? It Depends On The Dependent Variable
367(1)
Box 11.6 The Meaning Of Exogeneity And Endogeneity In Structural Equation Modeling
368(1)
Control: Holding Things Constant
368(1)
Experimentation: The Basic Steps
369(1)
Limited Generalizability of Experiments
370(1)
Ethical Limitations of Experiments
370(1)
Experimentation, Policy, and Practice
370(1)
Conclusion: End of Innocence
371(1)
Box 11.7 Critical Questions To Ask About Causation
371(1)
Box 11.8 Tips On Doing Your Own Research: Causation
372(1)
Chapter Resources
372(4)
Key Terms
372(1)
Exercises
372(2)
Student Study Site
374(2)
Learning Objectives
376(1)
12 Observational Studies
377(26)
Private Versus Public Schools
377(1)
What Is an Observational Study?
377(2)
The Gold Standard for Description---but Not for Causal Estimation
378(1)
Limitations of an Observational Study
378(1)
Control Variables
379(1)
How Control Variables Help Disentangle a Causal Effect
379(1)
How to Choose Control Variables
379(1)
How Did Control Variables Change the Estimate of a Causal Effect?
380(1)
Matching and Case-Control Studies
380(3)
Matching
380(2)
Case-Control Studies
382(1)
Statistical Control: An Empirical Example
383(8)
Step 1 Speculate on Common Causes
384(1)
Step 2 Look for Differences
385(1)
Step 3 Stratify by Control Variables
385(2)
Omitted Variable Bias
387(1)
Box 12.1 Omitted Variables---And The Bias They Cause---By Any Other Name
387(2)
A Different Choice of Control Variable
389(1)
Multiple Control Variables
389(1)
What If the Dependent Variable Is Categorical? Layered Cross-tabs
390(1)
How to Choose Control Variables
391(6)
What's Driving the Independent Variable?
393(1)
Do Not Use Intervening Variables as Controls
393(1)
Complex Common Causes and Unexplained Correlations
394(1)
Causes That Can Be Ignored
395(1)
Choosing Good Control Variables Depends on Your Question
395(1)
Unmeasured Variables and Omitted Variable Bias
396(1)
Box 12.2 Jargon: Unmeasured Variables And Unobservables
396(1)
Proxies
396(1)
Conclusion: Observational Studies in Perspective
397(1)
Box 12.3 Critical Questions To Ask About Observational Studies With Control Variables
397(1)
Box 12.4 Tips On Doing Your Own Research: Observational Studies With Control Variables
398(1)
Chapter Resources
398(4)
Key Terms
398(1)
Exercises
399(1)
Student Study Site
400(2)
Learning Objectives
402(1)
13 Using Regression to Estimate Causal Effects
403(24)
Cigarette Taxes and Smoking
403(1)
From Stratification to Multiple Regression
403(6)
Using More Than One (or Two) Control Variables
404(1)
Control Variables That Are Quantitative
404(1)
From Description to Causation: The Education-Earnings Link Reconsidered
404(2)
Multiple Regression: Brief Overview and Interpretation
406(1)
How Multiple Regression Is Like Stratification: A Graphical Illustration
406(2)
Specification: How the Choice of Control Variables Influences Regression Results
408(1)
What About Unmeasured Variables?
409(1)
The Effect of Breast-Feeding on Intelligence: Is There a Causal Connection?
409(6)
Step 1 Speculate on Common Causes
410(1)
Step 2 Examine the Relationship Between the Independent Variable of Interest and Potential Common Causes
410(1)
Step 3 Implement Control Variables Through Multiple Regression
410(3)
How to Interpret Multiple Regression Coefficients: Effects of Controls
413(1)
How to Interpret Multiple Regression Coefficients: Effect of Interest
413(1)
Adding and Removing Controls: What Can Be Learned?
414(1)
Technical Complexities
415(1)
Further Topics in Regression for Estimating Causal Effects
415(3)
Possible Effects of Adding Control Variables
416(1)
Interactions, Functional Forms, and Categorical Dependent Variables
416(1)
The Decision to Focus on One Causal Effect---and the Confusion It Can Cause
416(1)
Box 13.1 When To Call Something A Control Variable
417(1)
When Is Low R-Squared a Problem?
417(1)
Software Doesn't Know the Difference, but You Should
417(1)
Box 13.2 The Health Of Taxi Drivers: Prediction Versus Causation
418(1)
Multivariate Matching: Using Propensity Scores
418(2)
Propensity Score Matching
419(1)
Conclusion: A Widely Used Strategy, With Drawbacks
420(1)
Box 13.3 Critical Questions To Ask About Studies That Use Regression To Estimate Causal Effects
420(1)
Box 13.4 Tips On Doing Your Own Research: Multiple Regression To Estimate Causal Effects
420(1)
Chapter Resources
421(5)
Key Terms
421(1)
Exercises
421(3)
Student Study Site
424(2)
Learning Objectives
426(1)
14 Randomized Experiments
427(40)
Time Limits on Welfare
427(1)
Florida's Family Transition Program: A Randomized Experiment
427(1)
Random Assignment: Creating Statistical Equivalence
428(5)
Random Assignment in Practice
429(1)
Box 14.1 Manpower Demonstration Research Corporation (Mdrc)
429(2)
Statistical Equivalence: A Look at the Data
431(1)
Why Random Assignment Is Better Than Matching or Control Variables
432(1)
Findings: What Happened in Pensacola
432(1)
Evidence-Based Public Policies?
433(1)
Box 14.2 The Coalition For Evidence-Based Policy
433(1)
The Logic of Randomized Experiments: Exogeneity Revisited
433(3)
Statistical Significance of an Experimental Result
435(1)
The Settings of Randomized Experiments
436(3)
Lab Experiments
436(1)
Field Experiments
436(1)
Box 14.3 Practical Difficulties In A Field Experiment About Online Education
437(1)
Box 14.4 Abduf Latif Jameel Poverty Action Lab At Mit
438(1)
Survey Experiments
438(1)
Generalizability of Randomized Experiments
439(6)
Random Assignment Versus Random Sampling
439(1)
The Limited Settings: What Would Happen If Time or Place Were Different?
440(2)
Box 14.5 The Rand Health Insurance Experiment
442(1)
Volunteers and Generalizability
442(1)
The Ideal Study: Random Sampling, Then Random Assignment
443(1)
Box 14.6 Time-Sharing Experiments For The Social Sciences (Tess)
444(1)
Generalizability of the Treatment
444(1)
Generalizability in the Long Run: Will the Effect Always Be the Same?
445(1)
Variations on the Design of Experiments
445(4)
Cluster Randomization
445(2)
Arms in an Experiment
447(1)
Levels of a Treatment: Probing a Dose-Response Relationship
447(1)
Factors in an Experiment: Probing an Interaction
448(1)
Within-Subjects (Crossover) Experiments
448(1)
Artifacts in Experiments
449(3)
The Hawthorne Effect and the Value of Unobtrusive or Nonreactive Measures
449(1)
Placebo Effect and Blinding
450(1)
Box 14.7 The Perry Preschool Study
451(1)
Contamination
451(1)
Demoralization and Rivalry
451(1)
Noncompliance
452(1)
Attrition
452(1)
Analysis of Randomized Experiments
452(3)
Balancing and the Occasional Need for Control Variables
453(1)
Sample Size and Minimal Detectable Effects
453(1)
Heterogeneous Treatment Effects
453(1)
Intent to Treat Analysis
454(1)
Treatment of the Treated in Moving to Opportunity
454(1)
Ethics of Randomized Experiments
455(3)
Box 14.8 The Moving To Opportunity Demonstration
456(1)
Something for Everyone: The Principle of Beneficence
456(1)
Informed Consent When the Stakes Are High
457(1)
Is Randomization Itself Unethical?
457(1)
Qualitative Methods and Randomized Experiments
458(1)
Conclusion: A Gold Standard, With Limitations
458(3)
Box 14.9 Critical Questions To Ask About A Randomized Experiment
459(1)
Box 14.10 Tips On Doing Your Own Research: Randomized Experiments
460(1)
Chapter Resources
461(5)
Key Terms
461(1)
Exercises
461(3)
Student Study Site
464(2)
Learning Objectives
466(1)
15 Natural and Quasi Experiments
467(34)
A Casino Benefits the Mental Health of Cherokee Children
467(1)
What Are Natural and Quasi Experiments?
467(9)
Natural Experiments: Finding Exogeneity in the World
468(2)
Quasi Experiments: Evaluating Interventions Without Random Assignment
470(2)
Why Distinguish Natural Experiments From Quasi Experiments?
472(1)
Box 15.1 Origins Of The Terms Natural Experiment And Quasi Experiment
473(1)
Box 15.2 A Decision Tree For Categorizing Studies
473(2)
Box 15.3 Oregon'S Health Insurance Lottery
475(1)
Internal Validity of Natural and Quasi Experiments
476(1)
Exogeneity and Comparability
476(1)
How Did People Get the Treatment?
476(1)
Nothing's Perfect
476(1)
Generalizability of Natural and Quasi Experiments
477(1)
Generalizability of the Treatment Effect
477(1)
Types of Natural and Quasi Experimental Studies
478(6)
Before-After Studies
478(1)
Be Careful Interpreting Significance Tests for Quasi and Natural Experiments
479(1)
Interrupted Time Series
479(2)
Cross-Sectional Comparisons
481(2)
Prospective and Retrospective Studies
483(1)
Box 15.4 Cross-Sectional Analysis Of Longitudinal Data
484(1)
Difference-in-Differences Strategy
484(4)
Do Parental Notification Laws Reduce Teenage Abortions and Births?
485(1)
What Does a Difference-in-Differences Study Assume?
486(1)
Difference-in-Differences in a Regression Framework
487(1)
Panel Data for Difference-in-Differences
488(2)
What Do Panel Difference-in-Differences Studies Assume?
489(1)
Weaknesses of Panel Difference-in-Differences Studies
489(1)
Instrumental Variables and Regression Discontinuity
490(2)
Instrumental Variables
490(1)
Box 15.5 How To Determine If An Instrument Is Valid
491(1)
Regression Discontinuity
492(1)
Ethics of Quasi and Natural Experiments
492(2)
Conclusion
494(2)
Searching for and Creating Exogeneity
494(1)
Estimating Causal Effects in Perspective: A Wrap-up to Part IV
494(1)
Box 15.6 Critical Questions To Ask About Natural And Quasi Experiments
495(1)
Box 15.7 Tips On Doing Your Own Research: Natural And Quasi Experiments
495(1)
Chapter Resources
496(5)
Key Terms
496(1)
Exercises
496(4)
Student Study Site
500(1)
PART V CONTEXT AND COMMUNICATION
501(54)
Learning Objectives
502(1)
16 The Politics, Production, and Ethics of Research
503(26)
Risking Your Baby's Health
503(1)
From Research to Policy
504(7)
Rational Model of Policy
504(1)
Box 16.1 The Effects Of Breast-Feeding: Many Studies
505(1)
How Many Studies?
506(1)
Dealing With Uncertainty, Costs, and Benefits
507(1)
Pathways of Influence
507(1)
Politics and Other Barriers
508(2)
A Failure to Move From Research to Policy: The U.S. Poverty Definition
510(1)
How Can Research Have More Influence?
511(1)
The Production of Research
511(6)
Who Funds Research?
512(1)
How Time and Cost Shape Research
513(1)
Where Is Research Conducted?
513(2)
Research Cultures and Disciplines
515(1)
Which Research Questions Should Be Studied?
515(2)
Making Research Ethical
517(8)
The Ethical Review Process
517(2)
Box 16.2 Template For Informed Consent Form
519(2)
When You Don't Need an Informed Consent Form
521(1)
Research Ethics Procedures: It Depends Which Country You're In
521(1)
How to Keep Data Anonymous or Confidential
522(1)
Ethical Authorship and Collaboration
522(1)
Additional Issues in Research Ethics
523(2)
Conclusion
525(1)
Chapter Resources
525(3)
Key Terms
525(1)
Exercises
526(1)
Student Study Site
527(1)
Learning Objectives
528(1)
17 How to Find, Review, and Present Research
529(26)
Where to Find Research
529(5)
Journals
529(2)
Open-Access and e-Journals
531(1)
Books
532(1)
Attending Conferences and Seminars
532(1)
Reports
533(1)
Working Papers
533(1)
The News Media and Blogs
533(1)
How to Search for Studies
534(3)
Google Scholar
534(1)
Box 17.1 What Is Google Scholar?
534(1)
Electronic Resources: Indexes, Full-Text Databases, and Aggregators
535(1)
Wikipedia
536(1)
Box 17.2 What Is Wikipedia?
536(1)
Browsing and Following Citation Trails
537(1)
Bibliographic Citation Software
537(1)
How to Write a Literature Review
537(3)
What a Literature Review Should Not Do
537(1)
What a Literature Review Should Do
538(1)
Literature Review as a Context for Your Own Study
539(1)
How to Communicate Your Own Research
540(10)
The Importance of Rewriting
540(1)
Know Your Audience
540(1)
Organization of a Research Report
541(2)
Writing About Numbers
543(2)
Tables and Figures
545(1)
Tips for Creating Good Tables
545(2)
Tips for Creating Good Figures
547(1)
How to Write About Qualitative Research
548(1)
Presenting: How It Is and Is Not Like Writing
549(1)
How to Publish Your Research
550(1)
Conclusion
551(1)
Chapter Resources
552(3)
Key Terms
552(1)
Exercises
552(1)
Student Study Site
553(2)
Glossary 555(18)
References 573(14)
Author Index 587(8)
Subject Index 595
Dahlia K. Remler is Professor at the School of Public Affairs, Baruch College, and the Department of Economics, Graduate Center, both of the City University of New York. She is also a Research Associate at the National Bureau of Economic Research.

Dahlia has been in an unusual mix of disciplinary and interdisciplinary settings. She received a BS in electrical engineering from the University of California at Berkeley, a DPhil in physical chemistry from Oxford Universitywhile a Marshall Scholarand a PhD in economics from Harvard University. During the Clinton administrations health care reform efforts, Dahlia held a fellowship at the Brookings Institution to finish her dissertation on health care cost containment. She then held a postdoctoral research fellowship at Harvard Medical School, followed by assistant professorships at Tulanes and Columbias Schools of Public Health, prior to joining the faculty at Baruch. She enjoys comparing and contrasting how different disciplines see the same issues.

Dahlia has published widely in a variety of areas in health care policy, including health care cost containment, information technology in health care, cigarette tax regressivity, simulation methods for health insurance take-up, and health insurance and health care markets. She has also recently started working on higher education and media issues. Her work has appeared in the Journal of Policy Analysis and Management, Health Affairs, the Quarterly Journal of Economics, the American Journal of Public Health, Medical Care Research and Review, and many other journals. She blogs on health care policy, higher education and other topics at DahliaRemler.com.

Dahlia lives with her husband, Howard, in New York City, where they enjoy the citys theaters, restaurants, and parksand Dahlia enjoys being a complete amateur dancer in some of the citys superb dance studios.

Gregg G. Van Ryzin is Professor at the School of Public Affairs and Administration, Rutgers UniversityNewark. He received his BA in geography from Columbia University and his PhD in psychology from the City University of New York. During his doctoral training, he worked as a planner for a nonprofit housing and community development organization in New York City, and he completed his dissertation on low income housing for the elderly in Detroit. He next worked in Washington, D.C., for ICF Inc. and later Westat, Inc. on surveys and program evaluations for the U.S. Department of Housing and Urban Development and other federal agencies. In 1995, he joined the faculty of the School of Public Affairs, Baruch College, where he directed their Survey Research Unit for 8 years. In that role, he helped develop and direct the New York City Community Health Survey, a large-scale behavioral health survey for the citys health department, and also played a key role in shaping and conducting the citys survey of satisfaction with government services. He has spent time in Madrid, collaborating with researchers there on the analysis of surveys about public attitudes toward Spanish government policy. Gregg has published many scholarly articles on housing and welfare programs, survey and evaluation methods, and public opinion about government services and institutions. His work has appeared in the International Review of Administrative Sciences, the Journal of Policy Analysis and Management, the Journal of Public Administration Research and Theory, the Journal of Urban Affairs, Nonprofit and Voluntary Sector Quarterly, Public Administration Review, Public Management Review, Public Performance and Management Review, Urban Affairs Review, and other journals.

Gregg lives in New York City with his wife, Ada (a history professor at NYU), and their daughters Alina and Lucia. They enjoy life in their Greenwich Village neighborhood, escaping on occasion to Spain, Miami, Maine, Cuba, and other interesting places in the world.