Article Critique

Article Critique Instructions
The final product must be typewritten, double-spaced, and no more than five pages long.
Recommendation: be sure to answer every question. The easiest way to ensure you have not skipped a question in your answer is number each

paragraph of your essay (should you choose an essay form) according to the specific question. Some of you copied the whole question and

included an answer right below it.
Please recall that the purpose of the Article Critique assignment is to:
• Go through the process of thinking critically about the merits and faults within the assigned article.
• Give you practice in applying your knowledge about the research methods you have learned about in the course.
• Assess your competencies in research method content and critical thinking.
• Prepare you for developing your own research/study/article

• Be sure to explain the reasons for your opinions or justification for your responses.
• Whenever possible, provide examples from the article to support your conclusions.
• If you find fault in an area of the article, consider an alternative approach that would improve the methods.

FYI: Definitions of “critique” include:
• A critical review or commentary
• A detailed analysis and assessment of something
• A method of disciplined, systematic analysis of a written or oral discourse
• Involves identifying both strengths and faults

Some Remarks on Grading Standards (Please Remember: The Grading is BLINDED)
I. The key to this assignment is to apply the methodological concepts you have learned in this course (thus far) to the evaluation of a

research article. You demonstrate your ability by specifically linking the procedures discussed in the article to the concepts. Please do NOT

treat this assignment as an opinion essay. You have the burden of proof to demonstrate that you know what you are doing. In particular,
1. Never answer just “yes” or “no”; always explain your answer.
2. Never state some general methodological term or principle without linking it up specifically to something in the article (or to

something missing in the article).
3. Never give a vague or evasive answer in which you avoid sticking your neck out (hoping you won’t be marked “wrong”); if you don’t

commit yourself to a specific answer, I will assume you do not know what it is. But try to say what is needed as briefly as possible. Long-

winded, rambling answers are evidence that you do not know precisely what is important.

II. Questions of “fact” will be graded by comparing what the article says with what you said it said, along with your ability correctly to use

the relevant methodological terms. Questions requiring evaluation will be graded according to these criteria:
1. You take some position
2. You defend your position by talking about your article in ways that raise issues that we discussed in class.

III. If the article fails to give some information the review asks for, you get credit by saying that the article fails to give the

information. Note that this failure should then become part of your evaluation of the relevant section. (I will try to avoid approving articles

that are missing too much of the relevant information.)
IV. If the article is unclear or ambiguous, or if you are ambivalent in your evaluation of something, it is fine to give an answer that

expresses these problems.
V. Don’t blindly assume the author is always using the correct methodological terms for what s/he did.

Assignment Directions:
The assigned article: Markowitz, S. (2008). The effectiveness of cigarette regulations in reducing cases of Sudden Infant Death Syndrome.

Journal Of Health Economics, 27(1), 106-133.
Econ Journal Version.pdf
NBER Version.pdf
Here are the two versions of the article: the NBER version was presented at the National Bureau of Economic Research prior to publication in

the Journal of Health Economics. Your answers should be based on the “Econ Journal” version, but sometimes the NBER version may have additional

Please write a 3 — 5 page paper (not including title page if you decide to add it) that addresses the following questions:
1. What was the study design (Hint: observational, experimental, quasi-experimental)?
a. How so?
b. Is it adequate to answer the research question?
c. How does it differ from other study designs? Why other study designs are not appropriate given the research question?

2. Your textbook indicates, “In experimental or other quasi-experimental designs, you either assume or try to provide evidence that the program

or comparison groups are equivalent prior to the program so that post-program differences can be attributed to the manipulation/treatment.”
a. How could you satisfy this assumption in this study? In other words, how can you demonstrate it (which variable will be involved to confirm

this assumption)?
b. Does the author provide this information? How so?
c. What other (if any) assumptions related to study design mentioned in the article?

3. Do you have treatment and control groups in this study?
If so, what are they (i.e., what is the treatment, who or what constitute(s) control group, and who or what constitute(s) treatment group —

please pay attention to who or what based on unit of analyses that you had to identify in your Article Critique #1)?

4. Can you explain the difference between randomization and random sampling (if you think there is one) using examples from this study (or lack

thereof)? (Hint: for example, think of the unit of observations from one of the data sources to illustrate presence of random assignment).

5. Do you think this study has population validity and ecological validity? How so?

6. Trochim et al. talk about several single-group and multiple-group threats to internal validity? Although several of them are not applicable

to this study, one could at least wonder about 2 of them? Which ones do you think they are? (Hint: think of most relevant threats; keep in

mind, there are two levels of data: individual and state/aggregated).

7. Scavenger Hunt: Please conduct additional (lit.) search and identify a U.S. surveillance project of CDC and state health departments

developed to collect state-specific population-based data on maternal attitudes and experiences before, during, and shortly after pregnancy.
a. Please identify it and write 3-5 sentences to describe it as if you are writing a dissertation, a manuscript that you want to submit to a

peer-reviewed journal, or a technical report. See examples of data sources currently used in this study.
b. How is this data source different from the rest of the data sources used in the article?
c. How many modes of data collection are used by the data source, which you had identified in 7a and what are they?
d. What type of sampling (if any) is used in 7a?
e. What percentage of the U.S. population does your 7a data source cover?
f. What about the response rates thresholds?
g. Are there external validity threats given 7e and 7f? (To answer this questions you may need to continue your Scavenger Hunting: check out 7a

data source website, specifically, tab on data availability and year, including an excel spreadsheet).
h. What would be some of the challenges in conducting a longitudinal study to examine effects of smoke-free laws using 7a data source? (Hint:

check out 7a data source website, specifically, tab on data availability and year).
i. Pick one of the pdf questionnaires and provide examples of dichotomous questions and filter or contingency questions.
j. Given your response in 7d, what variables do you need to look for in the 7a dataset to let your software know you are working with a dataset

created using your response to 7a? (Hint: this type of variables is also listed on the 7a webpage describing variables in the 7a analytic

research file).
k. Did Markowitz study need to use these variables? Why or why not?

8. Explain nominal, ordinal, interval, and ratio measures using examples in the study (if you cannot find them in the study, you can borrow

examples from 7a).

9. Explain the difference between univariate, bivariate, and multivariate (or also known as multivariable) types of analyses using tables and

figures in the article. (Hint: you can refer me to a particular table or figure to say that it reflects a certain type of analysis and explain

how so).

10. Do we need to have conclusion validity or do we just need to focus on internal validity, or both? (Hint: do not forget the study design and

its main goal/research question).