• Shuffle
    Toggle On
    Toggle Off
  • Alphabetize
    Toggle On
    Toggle Off
  • Front First
    Toggle On
    Toggle Off
  • Both Sides
    Toggle On
    Toggle Off
  • Read
    Toggle On
    Toggle Off
Reading...
Front

Card Range To Study

through

image

Play button

image

Play button

image

Progress

1/41

Click to flip

Use LEFT and RIGHT arrow keys to navigate between flashcards;

Use UP and DOWN arrow keys to flip the card;

H to show hint;

A reads text to speech;

41 Cards in this Set

  • Front
  • Back
Average
=sum of all values/data points divided by the number of values/data points
=a number that typifies a set of numbers of which it is a fx
=In "How to Lie with Statistics," Huff mainly criticizes the ambiguity of the term “average”. He argues that an unqualified “average” is virtually meaningless. In addition, such an average would be easily manipulated and thus changing a statistical result.
Mode
=Most frequently observed outcome (rarely reported with numeric data)
=most frequently occurring value in a data set or a probability distribution
Median
=Value dividing distribution into two equal parts
=50th percentile
=middle value of the given numbers of distribution in their ascending order
In looking either at survey or samples of aggregated data what basic conditions must be met before one can make valid general claims about the behavior of the overall group one is trying to look at or examine?
=data must be representative subset of the group- it must reflect a random sample from the studied group
=must be large enough sample of the group
=data must be representative of phenomena
In pictoral or graphic display of data, is it possible to give radically different presentations that would imply radically different conditions using the same set of data?
-Distort scales and origins of graphs: drawing pictures and graphs is very impressive and often proves successful in conveying the desired meaning. The graphs can be easily truncated or expanded to show only the parts which he wants to spot. For example, profits can be shown to be growing rapidly within a specific period.
-in picture graphs or bar charts, height vs area can be distorted. The numbers still say two to one, but the visual impression… says the ratio is four to one.
-Reported data may be irrelevant as in advertising- semiattachment figure.
-statistical manipulation- misuse or the misrepresentation of a map, average (mean; arithmetic average) instead of median, decimal as a spurious air of precision; a poor approximation, and percentiles using dual charts etc
Does the sequence of events have any impact on the causality of events?
Not necessarily. Just because they follow each other in time does not mean a causal link.

Evidence for a claim about causes is usually a correlation between two events or kinds of events.
When we think that A causes B, we usually believe not only that A and B are correlated but also that it “makes sense” for A to cause B. Good arguments do not just appeal to the correlation of A and B, they also explain why it makes sense for A to cause B.
Most events have many possible causes. Just finding a possible cause is not enough, you must go to show that it is the most likely cause.
Huff doubts the cause and effect theory. This theory is represented in the formula saying, “If B follows A, then A has caused B.” According to him, this fallacy gives wrong outcomes and it seems a good deal more probable that neither of these things has produced the other, but both are a product of some third factor. Many correlations may not be fully accurate. In addition, even if a relationship is true, it is not possible to know which the cause is and what the effect is. Thus a vague correlation will produce uncalled-for conclusions.
Some correlations are just coincidental.
Some correlations are not relations between cause and effect but represent two effects of some other cause.
Correlation also does not establish the direction of causality. If A is correlated with B, A may cause B- but B also may cause A.
Causes may be complex
Retroactive causality.
What is the difference between hypothesis and law?
A law is an observed regular relationship between two phenomena. laws can be deterministic or probabilistic. nearly all social sciences are probabilistic. laws can be causal or noncausal.
A hypothesis is a conjectured relationship between two phenomenas. Can be causal or noncausal.
What is the difference between independent variable and a dependent variable?
An independent variable is a variable framing the causal phenomenon of a causal theory or hypothesis.
A dependent variable is a variable framing the causal phenomenon of a causal theory/hypothesis. value relies on the outcome of another operation.
What are two types of observational analysis that are available to the study of politics? Also what is the third form of analysis of phenomena that is available to the 'hard sciences' that is not available to the social science and study of politics?
Two types of observational analysis:
1. Large-n analysis or statistical analysis- large number of cases
2. case-study analysis -small number of cases in detail
=Experimentation is seldom feasible in political science.
What is falsification?
According to Poppers, refutability or testability. - Karl Popper found a fundamental asymmetry between confirming a theory/verification (irrelevant) and disconfirming it/falsification (key to science)- once hypothesis proven wrong, theory proven wrong
A theory incapable of being proven wrong is not a theory. -
Design theories so that they can be shown to be wrong as easily and quickly as possible
-Do not actually try to be wrong- An incorrect theory is better than a statement that is neither wrong nor right.
Sketch out the four standard types of tests mentioned by van Evera.
• Hoop tests. Predictions of high certitude and no uniqueness provide decisive negative tests: a flunked test kills a theory or explanation, but a passed test gives it little support.
• Smoking-gun tests. Predictions of high uniqueness and no certitude provide decisive positive tests: passage strongly corroborates the explanation, but a flunk infirms it very little. For example, a smoking gun seen in a suspect’s hand moments after a shooting is quite conclusive proof of guilt, but a suspect not seen with a smoking gun is not proven innocent.
• Doubly-decisive tests. Predictions of high uniqueness and high certitude provide tests that are decisive both ways: passage strongly corroborates an explanation, a flunk kills it. If a bank security camera records the faces of bank robbers, its film is decisive both ways— it proves suspects guilty or innocent. Such a test combines a “hoop test” and “smoking-gun” test in a single study. Such tests convey the most inforation but are rare.
Straw-in-the-wind tests. Most predictions have low uniqueness and low certitude, and hence provide tests that are indecisive both ways: passed and flunked tests are both “straws in the wind.”
What is the null hypothesis and why is it important?
A null hypothesis is the opposite of a hypothesis.
establishes no causal relationship.
if you prove it false, the hypothesis is plausible/possible.
tests value of social theories: do these theories have any explanatory power?
Of scientific research in the social sciences, what is the goal? How is the procedural research done? What are the conclusions? What is the method?
The goal is inference- make descriptive/explanatory inferences on the basis of empirical info about the world. facts (qualitative or quant) systematically and infer beyond the immediate data to something broader that is not directly observed.
2. the procedures are public- explicit, codified, public methods to generate and analyze data whose reliability can be assessed.
The conclusions are uncertain- imperfect process. goal to use quan/qual data to learn about the world that produced them.
The goal is to apply the scientific method and rigors of science to social science by including quantitative and qualitative designs.
the content is the method- scientific research adheres to a set of rules of inference on which its validity depends.
What are the 6 ways the King, Koehane, and Verba list that one can "make a contribution to scholarship" when one is making a proposed research?
1. Choose a hypothesis seen as important by scholars in the literature but for which no one has completed a systematic study. If we find evidence in favor of or opposed to the favored hypothesis, we will be making a contribution.

2. Choose an accepted hypothesis in the literature that we suspect is false(or one we believe has not been adequately confirmed) and investigate whether it is indeed false or whether some other theory is correct.

3. Attempt to resolve or provide further evidence of one side of a controversy in the literature—perhaps demonstrate that the controversy was unfounded from the start.

4. Design research to illuminate or evaluate unquestioned assumptions in the literature.

5. Argue that an important topic has been overlooked in the literature and then proceed to contribute a systematic study to the area.

6. Show that theories or evidence designed for some purpose in one literature could be applied in another literature to solve an existing but apparently unrelated problem.
What do King, Keohane, and Verba say are the two basic assumptions when estimating causal effects?
Unit homogeneity
conditional independence
What do King, Koehane, and Verba say are the 5 rules for constructing causal theories?
1. Construct falsifiable theories
2. build theories that are internally consistent
3. select dependent variables carefully
4. maximize concreteness
5. state theories in as encompassing ways as feasible
What three guidelines does King, Keohane, and Verba give about the selection of dependent variables?
1. Dependent variables should be dependent.
2. Do not select observations based on the dependent variable so that the dependent variable is constant.
3. Choose a dependent variable that represents the variation we wish to explain
What does King, Keohane, and Verba mean by "descriptive inference"?
using observations from the world to learn about other unobserved facts
the process of understanding an unobserved phenomenon on the basis of a set of observation= using observations from the world to learn about other unobserved facts.
What is meant by multicollinearity?
Refers to any situation where we can perfectly predict one explanatory variable from one or more of the remaining explanatory variables
-describes a condition that may appear when analysts simultaneously consider more than one explanation for a social outcome. It occurs when two or more of the explanatory variables in a sample overlap. Because of the overlap, methods of analysis cannot fully distinguish the explanatory factors from each other or isolate their independent influence.
What are 4 things to avoid?
1. Measurement Error – bias our results as well as make them less efficient
2. Bias in our causal inferences that can result when we have omitted explanatory variables that we should have included in the analysis
3. Including irrelevant variables that reduce the efficiency of our analysis
4. Endogeneity: Problem that results when our ‘dependent’ variable affects our ‘explanatory’ variables (values of our explanatory variables take on are sometimes a consequence, rather than a cause, of our dependent variable)
Two types of measurement errors mentioned
1. Systematic measurement error
2. Nonsystematic measurement error
What does King, Keohane, and Verba mean by the term endogeneity?
The values our explanatory variables take on are sometimes a consequence, rather than a cause, of our dependent variable.
Common and serious problem for many areas of qualitative and quantitative research
Uncertainty of direction of causality
What are the three ways one can test test studies?
1. Controlled comparison
2. congruence procedure
3. process tracing
What are the two forms or ways of comparison?
Differences or similiarities
What is the difference between Type I Congruence and Type 2 Congruence Procedure?
Congruience procedure type 1: comparison to typical values: across cases to test theory: observe values on the IV and DV within a particular case and observe the world to ascertain the values on the IV and DV that are typical in most other cases. Then deduce relative values for the IV and DV in the study case and measure the congruence/incongruence between expectation and observation= similar to controlled comparison
Type2= multiple within-case comparisons- number of paired observations of values on the IV/DV across a range of circumstances within a case. then assess whether these value covary in accordance wtih the prediction of the test hypoth. if they covary, the test is passed.
What are Delphi methods? What are they useful for? And why can't they be used for means of testing?
Investigator mines views of case participants or others who experienced the case for hypotheses. often observe important unrecorded data that is lost to later investigators. use their memories/judgments to infer hypotheses that could not be made from direct observation alone. not so credible. unique situations, cannot be repeated.
What is the greatest value that Snidal argues is gotten from the use of formal methods?
Provides a precise language to describe the key elements of a problem, a powerful deductive machinery that extends the logical power of our theories, and an important means to expand our understanding and interpretation of the world. use properly (never in isolation from less formal theory/empirical analysis), can greatly enrich our analysis of int'l politics
=precision, logical consistency, generaltiy, and especially deductive inference.
Basic general hypothesis of Richardson's Arms Race Model
Arms race can be understood as an interaction between two states conditioned by 3 motivations (grievances, fear, and fatigue). states increase armaments because of grievances against and fear of other states but these increases are inhibited by the fatigue of maintaining greater armament levels.
wanted to predict the circumstances that create an arms race: when will two states rapidly increase arm. against each other?
deduction: arms races will result among fearful states and among states that have grievances but will be less likely among states tat are senstitive to the fatigue induced by the cost of arms.
According to Conybear, what are the 4 building blocks of microeconomics that can be applied as a model in IR?
utility, consumption, production (supply and demand), and input (Factors of production)
According to Kilgore and Wolinsky-Nahmias, what are the 5 elements that must be specified in a non-cooperative game of complete information?
1. actors
2. structure- how actors interact
3. outcomes-when actors interact within the structure
4. preferences- pref of actors over such outcomes
5. decision critera- critera that underlie decision
Van Evera gives 11 case selection criteria. what are they?
1. data richness
2. extreme values on the independent variable, dependent variable, or condition variable
3. large winthin case variance in values on the indep, dep, or condition variables
4.divergence of predictions made of the case by competing theories
5.the resemblance of case background conditions to the conditions of current policy problems
6.prototypicality of case background conditions
7.appropriateness for controlled comparison with other cases
8.outlier character
9. intrinsic importance
10.appropriateness for replication of previous tests
11.appropriateness for performing a previously omitted type of test
What does the term 'n' mean?
the number of observations or measurements that you have
sample size
In regression, what does R2 refer to?
=Degree of correlation
-how well one term can predict another
if 1.0= perfectly predict value of another
if 0.0- doesn't help predict at all
used in linear regression- tell how well resulting line match the original data points
=how strongly and under what conditions an indep variable and a dependent variable are associated (causal inferences)
y=a+bx slope of line b + o r -
What are the four conditions required for validity for the data of variables to be used in a regression equation?
the data are adequately distributed over the investigated range;
the number of data points is high; the relation between the data is linear
no bias
Sketch out the classical 'Prisoner dilemma' game.
Central model in study of IR
taken as the representation of the hobbesian anarchy that characterizes Int'l setting and of the prsumed impossiblity of cooperating without an overarching sovereign government.
demonstrates why two people might not cooperate even if its in both their interests
two suspects arrested by the police. insuffienct evidence for a conviction and having separated the prisoners, visit each of them to offer the same deal. if one testifies for the prosecution against the other and the other remains silent, the defector goes free and the silent accomplice receives the full term. if both remain silent, both are sentenced to only one month in jail. if each betrays the other, each receives a thre month sentence. must decide whether to betray or remain silen without knowing what the other will chose.
What is the difference between cooperative versus non-cooperative game?
cooperative games are those in which players can make binding and enforceable agreements, whereas noncooperative games may or may not allow for communication among the players but do assume that any agreement reached must be in equilibrium—that is, it is rational for a player not to violate it if other players do not, because the player would be worse off if it did.
In any hypothesis what is the relationship between variables and phenomena?
-A hypothesis is an explicit statement about the relationship between phenomena that formalizes researcher's infomed guesses. the researcher introduces different variables into an experiement to test its effect on the outcome (phenomena)
# After choosing a research question, it is necessary to propose an explanation for the phenomena by specifying how two or more variables are related.

* A variable is a concept with variation, whereas a constant is a concept without variation.
* An independent variable is thought to influence, affect, or cause variation in another variable.
* A dependent variable is thought to depend upon or be caused by variation in an independent variable.
* In general, more than one independent variable is needed to adequately explain political phenomena.
* A variable that occurs prior to all other variables is referred to as an antecedent variable, whereas a variable that occurs closer in time to the dependent variable is called an intervening variable.
What is an antecedent condition?
A phenomena whose presence activates or magnifies the action of a causal law or hypothesis. without it causation operates more weakly. can be restated as a causal law/hypothesis
Name the types of variables?
Independent Variable
Dependent variable
intervening variable
condition variable
study variable
Name the type of phenomena
Causal Phenomena (doing causing)
Caused Phenomena (being caused)
Intervening Phenomena (Phenomena that forms the explanation's explanation. caused by causal phenomena and cause the outcome phenomena)
antecedent phenomena (presence activates or magnifies the causal action of the causal/explanatory phenomena
What do Baumoeller and Sartors say are the common pitfalls in all statistical models (and all models)?
Misunderstanding or ignorance of the underlying purpose of the statistical method.
statistical models are models of human behavior and as a result the assumptions that underlie them are substantially nontrivial
1. error of specification
2. theory weak and difficult to test because too imprecise or too shallow
3. imposing a statistical model on the theory instead of crafting a model to test the theory
4. inattention to the causal process/processes that generated the data