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;
96 Cards in this Set
- Front
- Back
- 3rd side (hint)
|
Categories for the organization of ideas and observation |
Categories |
|
|
|
Represents a label that we give to elements of the social world that seem to have common features and that strike us as significant |
Categories |
|
|
|
Process where we specify whay we mean in using terms (concepts) in research |
Conceptualization |
|
|
|
How you define your concepts/variables in the study |
Conceptualization |
|
|
|
Emprical counterpart of conceptualization |
Operationalization |
|
|
|
Specify what would be observed Process of specifying the operations that will indicate the value cases on a variable |
Operationalization |
|
|
|
Creation of indicators |
Operationalization |
|
|
|
Understanding of a concept from its avstract (theoretical) form to its concrete (empirical, observabel and measurable) form |
Operationalization |
|
|
|
Something that is devised or already exists and is less directly quantifiable |
Indicators |
|
|
|
Operational definition of a concept Indirect measures of a concept |
Indicators |
|
|
|
Taken to refer to things that can be counted |
Measure |
|
|
|
Variables can be: |
Discrete or continuous |
|
|
|
Each separate category represents a different status |
Discrete (variable) |
|
|
|
Where a number represents a quantity that can be described in terms of order, spread or relative amounts |
Continuous (variable) |
|
|
|
Levels of Measurment (types of variable) |
1st Nominal 2nd Ordinal 3rd Interval 4th Ratio |
By order |
|
|
Specifies the order of cases Gaps between responses have no meaning |
Ordinal |
|
|
|
There is standard intervals and distance between attributes matter no absolute zero |
Interval |
|
|
|
It refer to the values that an indicator can take BUT they say nothing about the indicator itself |
Levels of Measurement Types of Variables |
|
|
|
It is used to capture a respondent's reaction to an item in the scale |
Rating scale |
|
|
|
Dichotomous Nominal scale |
Binary scale |
|
|
|
Ordinal scale Mostly for social sciences |
Likert scale |
|
|
|
Composite or multi-item scale Mistly ordinal but can be interval |
Semantic differential scale |
|
|
|
Interval and ratio Dichotomous but arranged in increasing quantity |
Guttman scale |
|
|
|
Rating scales |
Binary scale Likert scale Semantic differential scale Guttman scale |
|
|
|
Validity |
Whether an indicator really measures a concept |
|
|
|
Consistency of the measure of a concept |
Reliability |
|
|
|
A study can be reliable but not valid if... |
... it's measuring the wrong concept |
|
|
|
A study can be valid but not reliable if... |
... the measures are not consistent |
|
|
|
Validity tests or techniques |
Face validity Concurrent validity Predictive validity Construct validity Convergent validity |
|
|
|
Face validity |
Asking experts in the field |
|
|
|
Concurrent validity |
Uses current or contemporary criterion |
|
|
|
Predictive validity |
Uses future criterion |
|
|
|
Construct validity |
Deduct hypotheses from a theory that is relevant to the concept |
|
|
|
Convergent validity |
Compares new measure to measures of the same concept developed through other methods |
|
|
|
Reliability tests or techniques |
Inter-rater reliability Test-retest reliability Split-half reliability Internal consistency reliability |
|
|
|
Inter-observer reliability |
Inter-rater reliability |
|
|
|
Inter-rater reliability |
Measure of cinsistency between two or more observers or raters |
|
|
|
Test-retest reliability |
Consistency between teo sets of the same construct administered to the same sample |
|
|
|
Split-half reliability |
Consistency between two halves of a construct measure The longer the measurement, the better |
|
|
|
Internal consistency reliability |
Consistency between different items of the same construct Use of cronbach alpha |
|
|
|
Random error |
Caused by unknown and uncontrollable external factors |
|
|
|
Systematic error |
Introduced by factors that affect all observations of a construct across an entire sample |
|
|
|
Sometimes considered as bias |
Systematic error |
|
|
|
Selecting a subset of a population |
Sampling |
|
|
|
Group you want to generalize |
Population |
|
|
|
Simple random |
Random
Highly representative
Not possible w/o complete list of population and takes time and money |
|
|
|
Stratified random |
From identifiable groups or strata Can ensure specific groyos are represented Complex more effort |
|
|
|
Cluster |
Successive cluster of subjects til small grps are chosen as units Possible to select randomly even w/o population list Clusters can be unequivalent Results less generalizable, higher variability of sample estimate |
|
|
|
Stage |
Cluster + stratified (multi-staged sampling) Possible to select random samples in one area COmplex, has limitations |
|
|
|
Random samples, measured variables Representative and test hypothesis |
Social survey |
|
|
|
Experimental and control grp Precise measurement |
Experiment |
|
|
|
Analyze previously collected data Many data Government |
Official statistics |
|
|
|
Predetermined categories used to count content of mass media products Reliable measures |
Content analysis |
|
|
|
Research method involving the use of standardized questionnaires |
Survey Research |
|
|
|
There is one or more independent variable |
Exoerimental research |
|
|
|
Analysis of documents and texts that seeks to define content in terms of categories |
Content analysis |
|
|
|
Integral part of quantitative research |
Statistics |
|
|
|
Overall domain concerned with mathematical treatment of variability and is a subset of the global domain concerned with mathematical principles |
Statistics |
|
|
|
Second subset of the general domain of statistics Use of already developed and accepted statistical methodology as help in research effort |
Statistics |
|
|
|
Used for treatment of variability in samples |
Descriptive statistics |
|
|
|
Univariate includes: |
Frequency distribution Central tendency Dispersion |
|
|
|
Test validity of generalizations from sample to population |
Inferential statistics |
|
|
|
States whether what is true of the sample is true of the population |
Hypothesis |
|
|
|
Done by comparing posttest outcomes of treatment and control group subjects |
Two-group comparison |
|
|
|
Data reduction technique that is used to statistically aggregate a large number of observed measures into a smaller set |
Factor analysis |
|
|
|
Assessment of convergent and discriminant validity |
Factor analysis |
|
|
|
Used for marketing applications |
Discriminant analysis |
|
|
|
Classificatory technique that aims to place a given observation in one of severak nominal categories |
Discriminant analysis |
|
|
|
Predict the probability if the successful outcome Medical science |
Logistic regression (logit model) |
|
|
|
General linear model (GLM) where the outcome variable is binary "regression analysis" |
Logistic regression (logit model) |
|
|
|
Mulitivariate GLM used for analysing directional relationships |
Path analysis |
|
|
|
General linear model (GLM) where the variable can vary between 0 and 1and is presumed to follow normal distribution |
Probit regression (probit model) |
|
|
|
Mostly used for contemporary sociak science research |
Path analysis |
|
|
|
Used in analyzing time series data |
Time series analysis |
|
|
|
Standardized interview |
Structured interview |
|
|
|
Self-administered questionnaire |
Has fewer open questions |
|
|
|
Examine interval/ratio variables Closer coefficient to 1, stronger relationship |
Pearson's r |
|
|
|
Pair of ordinal variables used when one variable is ordinal, while the other is interval/ratio |
Spearman's rho |
|
|
|
Used for closely related statistics |
Phi and Cramer's V |
|
|
|
___ is used for analysis between 2 dichotomous variables while ___ us similar, but can't show relationship direction |
Phi Cramer's V |
|
|
|
It is applied to contingency tables to establish how confident we can be that there is a relationship between 2 variables in the population |
Chi square |
|
|
|
Used in split-half reliability |
Spearman Brown Formula |
|
|
|
Test relationship in interval or ratio |
Pearson r (r) |
|
|
|
Test relationship in ordinal |
Spearman rho (ρ) |
|
|
|
Test relationship in nominal |
Chi-square test of independence |
|
|
|
Dermine if the sample mean drawn from the population with known parameters if a given group represents the population For interval or ratio |
One-population mean |
|
|
|
Determine if there's significant deifference between two independent group on situations (for 2 responses/dichotomous) Nominal |
Z-test of independent proportion |
|
|
|
Determine there's significant difference between pairs of observation from a single group Nominal |
Z-test of dependent proportion |
|
|
|
Detemine significant difference between two group Interval/ratio |
T-test of independent mean |
|
|
|
Determine significant difference between two sets of correlated scores Interval/ratio |
T-test of dependent mean |
|
|
|
Determine if there's significant difference between two or more grouos in terms of mean |
ANOVA I |
|
|
|
Determine significant difference between observed and expected distribution Nominal |
Chi-square test of goodness of fit (x2) |
|
|
|
Provides the blueprint for the ideas Background and topic of study |
Introduction |
|
|
|
Provides detailed picture How the study proceeded Design, participants/subjects, materials and appararus, procedure and data analysis |
Method |
|
|
|
Provides reader on wjat haooened in analysis using stats Shows whether the data suooirt the ideas presented in introduction |
Results |
|
|
|
Inferences and conclusion Contai speculation, interpretation, theory and connection to research |
Discussion |
|
