Chapter 4 Questions

Explain why a tautological statement is problematic for an empirical analysis and provide an example.

Hypotheses stated in tautological form are also untestable in the sense that they are not really a test of the hypothesis. A tautology is a statement linking two concepts that mean essentially the same thing: for example, "The less support there is for a country's political institutions, the more tenuous the stability of that country's political system." This hypothesis would be difficult to disconfirm because the two concepts—support for political institutions and stability of a political system—are so similar. To provide a fair test one would have to measure independently—in different ways—the support for the political institutions and the stability of the political system.

A ____________ is a guess (but of an educated nature) that represents the proposed explanation for some phenomenon and that indicates how an independent variable is thought to affect, influence, or alter a dependent variable.

Hypothesis

Please explain how the unit of analysis plays a part in ecological inference and ecological fallacy.

Sometimes researchers conduct what is called a cross-level analysis. In this type of analysis, researchers use data collected for one unit of analysis to make inferences about another unit of analysis. A frequent goal of cross-level analysis is making ecological inference, the use of aggregate data to study the behavior of individuals. Yet, if a relationship is found between group indicators or characteristics, it does not necessarily mean that a relationship exists between the characteristics for individuals in the group. Using information that shows a relationship for groups to infer that the same relationship exists for individuals when in fact there is no such relationship at the individual level is called an ecological fallacy.

What is the difference between an independent and dependent variable? How are they related? In your answer please give an example.

A phenomenon that we think will help us explain the political characteristics or behavior is called an independent variable. Independent variables are the measurements of the phenomena that are thought to influence, affect, or cause some other phenomenon. A dependent variable is thought to be caused, to depend upon, or to be a function of an independent variable. Thus, if a researcher has hypothesized that acquiring more formal education will lead to increased income later on (in other words, that income may be explained by education), then years of formal education would be the independent variable and income would be the dependent variable. Example will vary.

What is the difference between a hypothesis and a theory? In your answer please define each and explain the role each would play in a research project.

A theory is a body of statements that systematize knowledge of, and explain, phenomena. Stated differently, theories help "organize, systematize, and coordinate existing knowledge" in a unified explanatory framework. Two crucial aspects of empirical theory are that (1) it leads to specific, testable predictions and (2) the more observations there are to support these predictions, the more the theory is confirmed. A hypothesis is an explicit statement that indicates how a researcher thinks the phenomena of interest are related. A hypothesis is a guess (but of an educated nature) that represents the proposed explanation for some phenomenon and that indicates how an independent variable is thought to affect, influence, or alter a dependent variable. Since hypotheses are proposed relationships, they may turn out to be incorrect. A good hypothesis has six characteristics: (1) it is an empirical statement, (2) it is stated as a generality, (3) it is plausible, (4) it is specific (includes direction), (5) it is stated in a manner that corresponds to the way in which the researcher intends to test it, and (6) it is testable. Ideally, you could generate multiple hypotheses from a theory and test each of them. Finding support for more hypotheses leads to support for the theory, which cannot itself be tested directly.

What is the difference between an antecedent variable and an intervening variable?

A variable that occurs prior to all other variables and that may affect other independent variables is called an antecedent variable. A variable that occurs closer in time to the dependent variable and is itself affected by other independent variables is called an intervening variable. The roles of antecedent and intervening variables in the explanation of the dependent variable differ significantly. Antecedent variables push our explanatory scheme further back in time and, we hope, will lead to a more complete understanding of a particular phenomenon.

__________ concepts should be defined very carefully because they can mean different things to different people.

Abstract

Please provide a hypothesis then identify the independent variable, the dependent variable, the direction of the relationship and the unit of analysis.

Answers vary. The student's answer should include a hypothesis like those in the chapter that include all of the above elements.

A variable that occurs prior to all other variables and that may affect other independent variables is called a(n) ______________ variable.

Antecedent

A(n) _______________ specifies the phenomena of interest; indicates which variables are independent, alternative, antecedent, intervening, and dependent; and shows which variables are thought to affect which other ones.

Arrow diagram

What is the difference between a variable and a constant and why is the difference important for testing hypotheses?

As the word variable connotes, we expect the value of the concepts we identify as variables to vary or change. A concept that does not change in value is called a constant and will not make a suitable phenomenon to investigate as part of the research process. In order to test hypotheses, there must be variation in the independent and dependent variables to measure the reaction to change in the independent variable.

Identify the unit of analysis in this hypothesis: Civil wars that are halted by negotiated peace agreements are less likely to re-erupt than are those that cease due to the military superiority of one of the parties to the conflict.

Civil wars

Why are clear definitions of concepts important in developing specific hypotheses?

Clear definitions are first and foremost important so that the knowledge we acquire from testing our hypotheses is transmissible and empirical. Because a particular discipline has some minimal level of shared consensus concerning its significant concepts, researchers can usually communicate more readily with other researchers in the same discipline than with researchers in other disciplines. Many interesting concepts that political scientists deal with are abstract and lack a completely precise, shared meaning. This hinders communication concerning research and creates uncertainty regarding the measurement of a phenomenon. Consequently, a researcher must explain what is meant by the concept so that a measurement strategy may be developed and so that those reading and evaluating the research can decide if the meaning accords with their own understanding of the term.

The words that we choose to describe political behaviors or attributes are called _________.

Concepts

In a(n) ______________ researchers use data collected for one unit of analysis to make inferences about another unit of analysis.

Cross-level analysis

A(n) __________ variable is thought to be caused, to depend upon, or to be a function of a(n) _________ variable.

Dependent, independent

Using information that shows a relationship for groups to infer that the same relationship exists for individuals when in fact there is no such relationship at the individual level is called a(n) ____________.

Ecological fallacy

The use of aggregate data to study the behavior of individuals is called ________________.

Ecological inference

A phenomenon that we think will help us explain the political characteristics or behavior that interests us is called a(n) __________________.

Independent variable

A variable that occurs closer in time to the dependent variable and is itself affected by other independent variables is called a(n) _________ variable.

Intervening

A _______________ relationship is one where the values of one variable increases as the values of another variable decreases.

Negative

A ______________ relationship is one where the values of one variable increases (or decreases) as the values of another variable increases (or decreases).

Positive

In the space below, please write three hypotheses; one should represent a positive relationship, one should represent a negative relationship, and one should represent a relationship with no direction. Label each hypothesis as positive, negative, or no direction.

The hypotheses should be written to match the following formats: positive: an increase (decrease) in X causes an increase (decrease) in Y. negative: an increase (decrease) in X causes an decrease (increase) in Y. no direction: X is (is not) related to Y.

The particular type of actor whose political behavior is named in a hypothesis is the __________ for the research project

Unit of analysis

Hypotheses should be a __________ rather than a ____________ statement.

Empirical, nonempirical