Search
Browse
Create
Log in
Sign up
Log in
Sign up
Upgrade to remove ads
Only $2.99/month
political science research terms
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
PL 407 terms from Dr. Bowen's class at PCC
Terms in this set (83)
Theoretical population
the group of objects to which an explanation applies is called
Units of analysis (or cases)-
objects that are being studied that are part of the theoretical population
Sample
all the units we are analyzing constitute the sample of the theoretical population
Property
any directly or indirectly observable characteristic, attribute, or behavior of a unit
Variable
often used instead of the term property; property is the more general term and variable to refer to the set of numbers or other values you get after measuring a property
Qualitative
properties or variables that classify units by type, but not by amount
Quantitative (or relative)
where units are classified by degree or quantity
Dichotomous
a property or variable for which the units are classified into just one of two categories; qualitative properties are often naturally dichotomous or are treated as dichotomous because only two of the categories are of interest to the researcher
Hypothesis
a statement asserting that specific variation in one property results in or causes specific variation in the property we are seeking to explain
Dependent property
the property we are seeking to explain in a hypothesis
Independent property
the property that is asserted to cause variation in the dependent property
Causal association
variation in the independent property tends to cause, directly or indirectly, variation in the dependent property
Indicators of dispersion
which indicate the extent to which the values of the units are spread out or concentrated together
Percentage distribution
a table showing the percentage of units falling into each category of a measure
Frequency distribution
a table showing the number of units falling in each category of a measure
Theory
a general explanation that is constructed from a series of interrelated hypotheses
Professional literature
research findings of those working in the discipline
Bar graph
a figure using different size bars to represent the number of units in each category of a measure
Mode
a measure of central tendency usable for all levels of measurement indicating the category with the most units in it
Median
a measure of central tendency usable for ordinal and interval level measures indicating the middle category of the distribution
Literature review
a discussion of existing literature relating to a hypothesis or hypotheses designed to show how the research being done fits into that which has been done previously
Research justification- a statement of precisely what the researcher is going to do and how he or she is going to do it
Replication
retesting of a previously tested hypothesis
Sample
a subset of the theoretical population which will allow us to determine whether there is general support for the hypotheses
Level of measurement
indicates the amount of information communicated by knowing in which category an object is (nominal, ordinal, interval)
Interval level
measures in which the numbers distinguish units into categories that can be ordered and also indicate how far apart the categories are
Ordinal level
measures that separate the units into categories and order the categories according to the amount of the property that is present
Nominal level
measures that do nothing more than separate the units into different categories of the property
Reliable
degree to which measures would yield the same results when applied by different researchers to the same units under the same circumstances
Valid
degree to which a measure measures the property as defined
Indicators of central tendency
which reflect the middle, central, or most common value in a distribution
Range
measure of dispersion usable for ordinal and interval levels of measurement indicating the highest and lowest value of a measure
Phi
a correlation coefficient used for measuring association between dichotomous variables
Line graph
a figure using the height of a line to indicate the frequencies of units at different values of an interval level measure
Mean
a measure of central tendency for interval level measures, computed by adding the scores on a measure and dividing by the number of units
Variance
a measure of dispersion for interval measures computed by averaging the squared distances between each value and the mean of the values
Standard deviation
a measure of dispersion for interval level measures computed by taking the square root of the average squared distances between the man and each of the values. It is the square root of the variance
Unimodal
where units are clustered about a single value
Bimodal
about two nonadjacent values units cluster
Uniform distributions
distributions in which the cases are distributed more or less evenly across the range of categories may have no modal areas
Symmetrical
a distribution whose values are distributed equally on each side of the midpoint
Left-skewed (negative)
when the outlying cases are lower than the midpoint of the distribution
Right-skewed (positive)
when the outlying cases are higher than the midpoint
Bivariate relationship
the relationship between the independent and dependent variables before controlling for the effects of other variables
Percentage crosstables
a table comparing the percentage distributions among categories of an independent variable
Tests of Significance
tests to determine how likely it is that an association as strongly supportive as the one observed in a sample would be found when no supportive association exists in the theoretical population
Correlation coefficient
a single number the indicates the extent to which the variables are related
Marginals
the numbers at the bottom of the columns or on the right of the rows of a percentage cross table that indicate the total number in each column or row
Positive association
a relationship in which , as the value of one variable increases, the value of the other also tends to increase
Negative association
a relationship I which as the value of one variable increases, the value of the other tends to decrease
Correlation coefficients
a single number that indicates the extent to which the variables are related
Perfect association
the relationship that exists when the x and y variables are paired in such a way that the absolute or relative value of y for each unit can be predicted perfectly by knowing either the absolute or relative value of x
Zero association
the relationship that exists when the x and y variables are paired in such a way that knowing the x value of a unit is of no help in predicting its y value
Strength of association
a measure of how closely the observed relationship matches perfect association, usually indicated by the magnitude of the correlation coefficient
Direction of association
a measure of which y values tend to be paired with which x values, usually indicated by the sign of the correlation coefficient
Sampling error
the expected difference between the distributions observed in samples and the distributions that exist in theoretical populations
level of statistical significance
the maximum probability or risk of concluding that there is an association when there actually is no such association in the theoretical population
Known sampling distribution
a sampling distribution for which statisticians have already determined the likelihood of getting each value when samples with given characteristics are drawn from a population in which there is no association between the independent and dependent variables
Tails
the two ends of the line graph
One-tail test
a test of significance in which: (1) the direction of association is hypothesized in advance, and (2) only an association in that direction can be statistically significant
Two-tail test
a test of significance in which an association in either direction can be statistically significant
Chi square
a statistic with a known sampling distribution used for determining statistical significance
Degrees of freedom (df)
a number reflecting the values that are free to vary, given marginal or statistical constraints
F-test
a statistic with a known sampling distribution used for determining statistical significance
Sum of Squares Within (SSw)
the variation in Y within the X categories is measured by the sum of squares within; what you calculate when you compute the variance; it is the sum of the squared deviations about a mean
Sum of Squares Between (SSb)-
calculated from the squared deviations of the means for each X category about the mean for the whole sample; multiply the number of units in each category by the squared difference between the category mean and the mean for the entire sample
Asymptotic standard error
measure similar to a standard deviation and measures how much dispersion one would expect in correlation coefficients for samples drawn from populations in which there is no association between the independent and dependent variables
Controlling
eliminating or adjusting for the effects that other variables have on an association between two variables
Condition
when the hypothesis is supported for only some categories of a control variable
Intervening variables
a variable that intervenes in a causal sequence between a cause and its effect
Path Diagrams
diagrams of the expected causal relationships among properties
control variables
a variable, the effects of which are held constant while testing the relationship between the independent and dependent variables
Experimental research and Quasi-Experimental research
research in which scientists can determine the amount or level of the independent variable to which each unit is exposed
Control tables
a table or other comparison showing the relationship between the independent and dependent variables in which all units have the same value for a control variable
Scatter Plot
a graphic representation of a relationship between two interval variables
Pearson's r
a correlation coefficient used to measure association between interval-level variables
Linear association
because Y= a + bX is the equation for a straight line, r is said to measure the extent of Linear association between X and Y
Extreme outlier
a unit whose X or Y value is extremely far from the values of the other units (for example the population of China relative to the populations of all other nations)
Regression Line
a line visually representing the regression equation
Regression coefficient (slope
the slope in a multiple regression equation, it shows how much Y is estimated to increase for every increase of one in the value of the X variable
intercept
the estimated value of Y when the X variables are zero
Residual
the difference between the estimated and the observed Y value of a unit
R2 and adjusted r2
the squared of the Pearson r correlation coefficient. It represents the proportion of the variance in Y in the sample than can be explained or accounted for by variation in a single X variable (r2) or multiple X variables (R2)
partial r
a Pearson's r correlation coefficient measuring the extent of association between two interval variables while controlling for the effects of other interval variables
YOU MIGHT ALSO LIKE...
PSYC 204
94 terms
Methods Final Exam
83 terms
Soc 210
80 terms
Adv 344K Exam 3
50 terms
OTHER SETS BY THIS CREATOR
titles of amendments 11-27
17 terms
french past tense verbs
20 terms
French Vocabulary 19a-b; 21a-b
52 terms
The Judgments for Test 2: Dr. Troutman
20 terms
OTHER QUIZLET SETS
Soc 320 Exam 1
34 terms
Unit 1
16 terms
PSY 281 W1: SumNot / Exp. Design
21 terms
Research Methods Exam 2
12 terms