Karteikarten
Quantitative Methoden
Karten in diesem Stapel (87)
- 1Quantitative researchTUT1
research methodology that seeks to quantify data and typically applies some form of statistical analysis. - 2Primary dataTUT1
originated by the researcher for the specific purpose of addressing the research problem. E.g., via a survey, an experiment, etc - 3Secondary dataTUT1
data collected in the past for some other purpose, which are available to be used. E.g., Statistisches Bundesamt, The World Bank DataBank, UN Database, etc - 4Population (census)TUT1
all people of the country, all men, etc. - 5SampleTUT1
part of the population (which has to be representative to the population) - 6Cross-sectional dataTUT1
data collected at one point in time. E.g., impact of advertising on attitude towards a brand, etc - 7Longitudinal data (times series data)TUT1
data observation over time. E.g., weekly sales of ice cream, etc - 8Panel dataTUT1
combination of cross-sectional and time series data: data involving repeated observations of the same variables over a long period of time. E.g., impact of acquisitions on labor productivity over time - 9Descriptive statisticsTUT1
(mostly univariate): to summarize or describe the data: numerically and graphically. E.g., average age in the sample, sales over time, standard deviation, etc - 10Inferential statisticsTUT1
(uni-, bi-, and multivariate): to draw inference about the data. E.g., estimation, correlation, forecasting, modeling, etc. - 11Univariate analysisTUT1
analysis where 1 single variable is being analyzed - 12Bivariate analysisTUT1
analysis where a relationship and/or correlation between 2 variables is being analyzed. - 13Multivariate analysisTUT1
analysis where the impact of 1 or more IV’s on 1 or more DV’s is being measured - 14Dependence techniqueTUT1
analysis where causal influence is assumed from 1 or more IV’s on 1 or more DV’s - 15Interdependence techniqueTUT1:
analysis where dependencies between the variables (factor) and/or observations (cluster) is being measured to find homogeneous groups (patterns of relationships). With these techniques, there is no hierarchy between the variables or observation, meaning no DV’s and IV’s - 16Dependent variableTUT1
represents the output variable which is tested to see if it is the effect - 17Independent variableTUT1
represents the input variable which is tested to see if it is the cause - 18CausalityTUT1
occurrence of X (cause) increases the probability of the occurrence of Y (effect). Cause must occur before the effect - 19NominalTUT1
Categorical variables (non-continuous, non-metric):
a variable that (identify and) classifies objects. E.g., gender, profession, etc. - 20OrdinalTUT1
Categorical variables (non-continuous, non-metric):
numbers indicate relative positions of objects. E.g., social class, hierarchical position, etc. - 21IntervalTUT1
Quantitative variables (continuous, metric):
differences between objects can be compared, but zero point is arbitrary. E.g., temperature, Likert scales, etc. - 22RatioTUT1
Quantitative variables (continuous, metric):
continuous variable with a fixed zero point. E.g., age, income, etc. - 23ConceptVL2
expresses an abstraction formed by generalization from particulars (e.g., capability, attitudes, buying behavior) - 24OperationalizationVL2
specification of operations necessary to measure a construct (e.g., items, questions) - 25VariableVL2
property that takes on different values (e.g., age) - 26Observable versus latent variableVL2
e.g. age vs. capability - 27HypothesisVL2
statement of the relationship between two variables (e.g., age is positively related to income)
//
statement that some diff or effect is expected (with or withour direction of effect --> one or two tailored) --> accepting the hypothesis will lead to changes in options and actions) - 28Analytical modelVL2
set of more than two variables and their relationships (e.g., age is positively related to education, education is positively related to income) - 29Likert scaleVL2
Scaling technique
response categories ranging from “strongly disagree” to “strongly agree” - 30Semantic differential scaleVL2
Scaling technique
rating scale with endpoints associated with bipolar labels that have semantic meaning (e.g., modern – old-fashioned) - 31Frequency DistributionVL3
Mathematical distribution, counts number of responses associated with different values of a variable, expresses counts in percentages - 32Mean / averageVL3
Measurement of location
value obtained by summing all elements in a set and by dividing by the number of elements (metric scale required) - 33Mode / measure of cental tendencyVL3
Measurement of location
value that occurs the most in a sample distribution (non-metric and metric scales) - 34Median / measure of central tendencyVL3
Measurement of location
value above which half of the subjects fall and below which half of the subjects fall - 35RangeVL3
Measurement of variability (metric scales required):
difference between largest and smallest value of a distribution - 36VarianceVL3
Measurement of variability (metric scales required):
mean squared deviation of all the values from the mean - 37Standard deviationVL3
Measurement of variability (metric scales required):
square root of variance - 38T-testVL3
Test for differences between sample means or difference of sample mean from zero or given population mean (one sample, two independent samples, paired sample) --> comparing a continuous variable between 2 groups - 39independent sample t-testVL3
A test to check whether two sampling distributions differ from each other; to see whether there is a difference between the means of 2 unrelated groups on the same DV - 40one sample t-testVL3
a test to check whether a sampling distributions differs from a given mean; to see whether a sample differs from a population with a specific mean. This population mean is not always known, but is sometimes hypothesized - 41Paired sample t-testVL3
A test to check whether two sampling distributions differ from each other; to see whether there is a difference between the means of 2 RELATED variables of the same sample - 42Chi-square TestVL3
A test to check for independence between two variables that consist of two or more categorical independent groups; for crosstab, to see whether there is a systematic association between the variables - 43Bivariate CorrelationVL3
A statistic summarizing the strength of association between two continuous / metric variables (without direction) --> to see whether there is a relationship between 2 variables - 44Partial CorrelationVL3
A measure of association between two variables after controlling / adjusting for the effects of a third or more additional variables --> to see whether there is a relationship between 2 variables still holds after controlling for other variables - 45Regression AnalysisVL4
Statistical procedure for analyzing relationships between a dependent variable and one or more independent variables - 46Linear regressionVL4
dependent variable is metric, independent variables are metric or dummies - 47Logit / Probit RegressionVL4
dependent is a dummy variable - 48Dummy RegressionVL4
One or more idependent variables are dichotomous - 49OutlierVL4
Unusual data points that have a strong influence on the fit of the regression line - 50NonlinearityTUT4
occurs when the model is non-linear content specified. This means the expected value of the DV is not in a straight-line function of each IV, holding the others IV, constant - 51MulticollinearityTUT4
occurs when 2 or more IV in a amultiple regression model are correlated and provide redundant information about DV - 52HeteroscedasticityTUT4
occurs when the variance of the error terms differ across observation. e.g. difference in dispersion of income over time in germany. Usually for cross-sectional data - 53AutocorrelationTUT4
occurs when the error terms are correlated. this means that the value of the error terms of 1 period depends systematically on the value of the error terms of another period. Only for time series. - 54Non-nominal distribution of the residualsTUT4
occurs when residuals are not normally distributed - 55Incompleteness of modelTUT4
Systematic influence of missing IVs (underfitting), too much IVs (overfitting), and/or endogeneity - 56Extreme observation (outlier)TUT4
Occurs when ovservations are distant (>3 standard deviation) from the regression line or from other observations - 57categorical independent variableVL 5
Factor (oftentimes manipulated, but can be measured) - 58TreatmentVL5
Factor category, can be combined from categories of more than one factor - 59Descriptive research: surveyVL1
structured questionnaire given to a sample of a population and designed to elicit specific information from respondents - 60Sampling TechniqueVL1
nonprobability sampling technique, probability sampling technique - 61Convenience samplingVL1
nonprobability sampling technique
Interviewer selects sampling units (paper) - 62Judgement samplingVL1
nonprobability sampling technique
sampling units purposely selected by the researcher (interested in certain population) - 63Quota samplingVL1
nonprobability sampling technique
convenience sampling with control categories / quotas of population elements - 64Snowball samplingVL1
nonprobability sampling technique
Initial group selected randomly, subsequent respondents selected through information provided by initial group - 65Probability sampling techniquesVL1
Simple random sampling
systematic (random) sampling
stratified sampling (proportionate and disproportionate)
cluster sampling
multi-stage random sample - 66Experimental ResearchVL1
Process of manipulatingone or more independent variables and measuring their effect on one or more dependent variables while controllingfor other explanatory variables - 67Independent variable xVL1
Key concepts of experiments
called factor - 68Factorial designVL1
Key concepts of experiments
manipulation of multiple factors; allows researchers to examine the effects of, and possible interactions among, several factors - 69TreatmentVL1
Key concepts of experiments
combination of factor levels - 70Dependent variable YVL1
Key concepts of experiments
Called responds or outcome - 71CovariateVL1
Key concepts of experiments
unmanipulated variable that is possibly predictive of the dependent variable (also: control variable) - 72InteractionVL1
Key concepts of experiments
occurs when the effect of one factor on a response depends on the level of another factor - 73ValidityVL1
internal, external, typically at odds with one another - 74RandomizationVL1
Key concepts of experiments
Random selection of participants and random assignment to experimental treatments (groups) - 75Types of experimental designVL1
Pre-experimental, true-experimental, quasi-experimental - 76ReliabilityVL2
The extent to which a scale produces consistent results for repeated measurements of the characteristic
–Test-retest reliability
–Alternative-forms reliability
–Internal consistency reliability (Coefficient Alpha: average of all possible split-half coefficients resulting from splitting of the scale items) - 77ValidityVL2
The extent to which differences in observed scale scores reflect truedifferences among objects on the characteristic being measured, rather than systematic or random errors
–Content validity
–Criterion validity
–Construct validity - 78ConstructTUT2
concept formulated in a way that it can be used in research (e.g., purchase intention, etc.). Concept and construct oftentimes used as synonyms! - 79Cronbach's AlphaTUT2
a measure of the internal consistency of a test or scale, expressed as a number between 0 and 1, where reliability should be accepted (rule of thumb) when higher than .7 - 80Sort CasesTUT2
sorts data ascending/descending along a selected variable: Data – Sort Cases - 81Merge filesTUT2
adds new cases or new variables provided new cases and variables fit the primary data set: Data – Merge Files – Add Cases. - 82Split filesTUT2
splits data in several groups, analyses are performed for each group separately (e.g., females and males): Data – Split File. - 83Select casesTUT2
selects subset of cases for further analysis (e.g., only females); all other cases can be filtered or deleted: Data – Select Cases - 84Weight casesTUT2
each case can be assigned a weight according to a weighting variable: Data – Weight Cases. - 85Multi-item scaleTUT2
several items combined to measure 1 concept (e.g., price fairness perception is measured of 4 items: fair, just, acceptable, and reasonable). Multi-item scales are more appropriate to measure complex concepts and have also higher reliability - 86Metric DataVL3
One variable: One-sample t-test
Two or more variables: two sample t-test, ANOVA - 87Nonmetric DataVL3
Two variables: chi-square
Informationen
- Beschreibung
- Karteikarten am Quantitative Methoden, erstellt von Lisa King am 14/01/2018.
- Erstellt von
- Lisa King
- Aufrufe
- 7
- Bewertung