Quiz 4: Research Design
Which of the following hypotheses best fits the criteria of causality?
As education increases, income tends to increase even after controlling for gender and race.
Ruth puzzles over a report that claims that women are more likely to vote for Democrats than are men. She puzzles because her best friend, Joan, always votes Republican. Ruth is guilty of using which of the following false criteria for nomothetic causality?
Complete causation and exceptional cases There are almost always exceptional cases. As discussed, nomothetic explanation may be applicable to only a minority of cases. Think about Bill Gates and Michael Dell. They did not finish college but did really well economically. However, we know that college dropouts tend to fare worse than college graduates in the labor market. Finally, proper nomothetic explanation is probabilistic in nature and does not explain every single case.
Generally, the first thing in a research proposal is the description of the subjects for study.
False An introduction should be the first thing is a research proposal, after proposal title and abstract. The description of the subjects for study .should come after the introduction.
Causal relationships can exist only if they apply in a majority of cases.
False It is a common misconception that, in order for causal relationships to be present, they must apply to the majority of cases. For instance, we say that children who are not supervised after school are more likely to become delinquent than those who are supervised are; hence, lack of supervision is a cause of delinquency. This causal relationship holds true even if a small percentage of those not supervised become delinquent. As long as they are more likely to be delinquent than those who are supervised, we say there is a causal relationship. The social science view of causation may vary from what you are accustomed to.
Dr. Jordan chronicles people's attitudes toward an upcoming property tax levy. Jordan is clearly doing an explanatory study.
False Jordan may not be trying to explain people's attitudes.
Researchers ought to ignore previous work on a topic so that their research can be original.
False Researchers ought to have a good understanding of the literature relevant to the topic. One purpose is, in fact, to ensure the originality of the study.
A necessary condition represents a condition that, if it is present, will pretty much guarantee the effect in question.
False Should be "sufficient." A sufficient condition is one that, if satisfied, assures the statement's truth. A necessary condition must be there, but it alone does not provide sufficient cause for the occurrence of the event.
With the idiographic type of explanation, we try to find a few factors that can account for many of the variations in a given phenomenon.
False That is the nomothetic type of explanation
If two variables are correlated with each other, there must be a causal relationship between them.
False There are two other criteria for establish causality. Correlation is a necessary condition.
Explanatory research is always superior to exploratory and descriptive research, since it addresses questions of why.
False They are different types of research method. They are to accomplish different objectives. One is not necessarily superior to others.
Explanatory research is carried out when a problem has been clearly defined, finding the relationship between variables and identify possible causal factors..
True
Description is the purpose of research that involves describing situations and events.
True An exploratory study is often carried out for a problem that has not been clearly studied, or even well defined. It often occurs before we know enough to make conceptual definitions or posit hypotheses about the relationship between variables. A descriptive study, on the other hand, is one in which information is collected without changing the environment (i.e., nothing is manipulated). It is to describe situations and events.
In some states, only those who are age 17 and older can obtain driver license. So being age 17 and older is a necessary condition for getting a driver's license.
True Being age 17 is a necessary condition. But it is not a sufficient condition for getting a driver's license. In other words, those who are age 17 and above have to meet other requirements before they can get a driver's license.
A major characteristic of exploratory studies is that they seldom provide satisfactory answers to research questions.
True Exploratory research normally involves collecting information and developing ideas about a relatively under-researched issue or context. So it rarely addresses specific research questions.
The article "House Prices and Subprime Mortgage Delinquencies" is an example of the nomothetic approach, because it is to establish general rules of behaviour to be applied to large populations.
True It is a nomothetic study and quantitative in nature. It seeks to establish causal relationships that are assumed to happen in many cases. The study allows some generalization.
Criminologist Jason Wade found that 19% of boys compared with 7% of girls report they had stolen something worth between $2 and $50. This indicates that there is likely_______________ between gender and self-reported theft.
an association Most likely an association based on limited information
Which of the following three criteria are necessary to establish nomothetic causality?
correlation, time order, and nonspurious. Idiographic causality is strictly used for qualitative methods. Different from nomothetic causality which is relevant to a broad population, idiographic causality is about individuals. A good example would be someone's biography or personal narrative or the history of events.
In which of the following methods, data are gathered essentially at one particularly point of time?
cross-sectional
Kathy studies the homeownership attainment of immigrants at a particular point of time. To increase the sample size, she collects data in three consecutive years and pool all the data together in her analysis. Which design should she use?
cross-sectional Please go to page 101. First, we can easily get rid of "panel" and "retrospective" designs. Since the study does not track any individual cohort or specific sub-population over time, it is not a "cohort" study. Then we have two choices left, which are "cross-sectional" and "trend." The study is not longitudinal in nature because it does not observe the same phenomenon over an extended period of time. Moreover, the purpose of pooling the data was to increase the sample size rather than to observe changes over time. Finally, the researcher tries to study immigrants at one particular point of time. Therefore it is a cross sectional study. In this case, the three year period is considered as one point of time in the study. Sometimes, the sample data collected at one time period is too small. Researchers have to pool several periods of data together to have a proper sample size. That is the purpose of pooling the data.
Which of the following data is the most difficult to use to establish causal relationships?
cross-sectional While it is easy to establish correlations and even associations, it is hard to detect the time sequence of events using the cross-sectional approach. Therefore, it is difficult to rely on the cross-sectional approach to causal relationships.
The topic of surrogate mothers interested Professor Snyder, even though he had little knowledge about the topic. Snyder read the available materials on the topic and wanted to develop an age, education, and income profile of women who serve as surrogate mothers in the United States. To develop this profile, Snyder should undertake a(n):
descriptive study
Andrew wants to study poverty and see if age is a major variable associated with poverty. Which unit of analysis should he use?
individuals Individual household is the unit of analysis in this case. The unit of analysis is the major entity that is being analyzed in a study. It is the 'what' or 'who' that is being studied. The study attempts to understand the differences between individuals of the groups.
In the article "Inclusion of Immigrant Status in Smoking Prevalence Statistics", the unit of analysis is:
individuals Researchers are examining the differences in smoking prevalence using CPS data. It is stated in the paper that "the CPS is a national survey of the US civilian population 15 years and older conducted monthly by the Census Bureau for the Bureau of Labor Statistics." Therefore the unit of observation is at the individual level. So is the unit of analysis.
In the article "Study suggests link between pesticides, autism", the unit of analysis is:
individuals The study is based on individuals. It looks at the individual woman who has been exposed to pesticides and examines how the risk of giving birth to an autistic child is different from those who were not exposed to pesticides. "Women who live near California farm fields sprayed with organochlorine pesticides may be more likely to give birth to children with autism..."
Which one of the following represents a condition that must be present for the effect to follow?
necessary cause
For a nomothetic causal relationship to exist, there must be evidence:
of an empirical correlation between the variables, one variable precedes the other in time, and a third variable did not cause the changed observed in the first two variables Three factors are correlations, time-sequence, and non-spuriousness.
Andy wants to study five fifth-grade classes over three years to determine how friendship patterns are established in the fifth grade affect friendship patterns in the eighth grade. He studies the same students over time. Which design should he use?
panel A panel study is an investigation of changes using a constant set of people and comparing each individual's opinions or behaviors at different times. In contrast, a cohort study is a form of longitudinal study (a type of observational study) that tracks the same birth cohort over time. Different from a panel study, a cohort study does not necessarily track the same individuals. In other words, the individuals examined at the two points of time may be different.
A researcher would like to examine the differences in crime rates among Salt Lake City neighborhoods. The unit of analysis would be:
social groups Neighborhoods are considered as social groups. The unit of analysis in this case can also be geography.
There are two variables. One is called the dependent variable while the other is called the independent variable. When an observed relationship between the two variables disappears when a third variable is controlled and when this third variable has a causal relationship with the dependent variable, the relationship is said to be:
spurious Think about the example in the textbook—the relationship between ice-cream consumption and drowning. Does ice-cream consumption cause drowning? Once we control for temperature (think about ice-cream consumption and drowning within a certain temperature range), the relationship disappears. In other words, there is a spurious relationship between the two variables. High temperature is the likely cause of both high ice cream consumption and drowning.
A __________ represents a condition that, if present, guarantees the effect in question.
sufficient cause
Elena learned from her political science professor that most rich people vote Republican. She also learned the one of the world richest individuals—Warren Buffet always voted for Democrats. She then concluded that her political science professor was wrong. What mistake did she most likely make?
the assumption of complete causation. Proper nomothetic explanation is probabilistic in nature and does not necessarily explain every single case. Exceptions do not disprove nomothetic explanation. In fact, causal relationships may exist even if they are only observed in a minority of cases.
If a researcher were conducting a study of women's attitudes toward happiness, the unit of analysis would be:
the individual
Vice president of sales wishes to study the changing characteristics of customers over the past ten years. She would like to know whether current customers are more or less influenced by advertisement. You would recommend her to use a:
trend study Trend analysis is a type of longitudinal study that examines change within a population over time. (comparison of U.S. Census over a period.)
When a researcher is faced with the question from whom or what will the information be gathered, that researcher is dealing with which aspect of the research design process?
units of analysis The process may not always be linear. Researchers may go back and forth during the process.
Statistical correlations are a sufficient condition to establish nomothetic causality.
Fasle While there is no causality in the absence of statistical correlations, statistical correlations alone cannot prove causality.
Which one of the following is the best example of the ecological fallacy?
Felisha studied Census tracts for her study on crime but then wrote up her conclusions in terms of individuals.
Which of the following is NOT a characteristic of a cross-sectional study?
It is easier to establish causality with a cross-sectional study than with a longitudinal study.
