Terms.pdfnino

Embed Size (px)

Citation preview

  • 8/14/2019 Terms.pdfnino

    1/2

    Chapter 6

    Adjusted R -Squared

    A goodness-of-fit measure in multiple regression analysis that penalizes additional explanatoryvariables by using a degrees of freedom adjustment in estimating the error variance.

    BetaCoefficients

    See standardized coefficients.

    Bootstrap A resampling method that draws random samples, with replacement, from the original dataset.

    BootstrapStandardError

    A standard error obtained as the sample standard deviation of an estimate across all bootstrapsamples.

    InteractionEffect

    In multiple regression, the partial effect of one explanatory variable depends on the value of adifferent explanatory variable.

    NonnestedModels

    Two (or more) models where no model can be written as a special case of the other byimposing restrictions on the parameters.

    OverControlling

    In a multiple regression model, including explanatory variables that should not be held fixedwhen studying the ceteris paribus effect of one or more other explanatory variables; this canoccur when variables that are themselves outcomes of an intervention or a policy are includedamong the regressors.

    Population R -Squared

    In the population, the fraction of the variation in the dependent variable that is explained by theexplanatory variables.

    Prediction The estimate of an outcome obtained by plugging specific values of the explanatory variablesinto an estimated model, usually a multiple regression model.

    PredictionError The difference between the actual outcome and a prediction of that outcome.

    PredictionInterval

    A confidence interval for an unknown outcome on a dependent variable in a multipleregression model.

    QuadraticFunctions

    Functions that contain squares of one or more explanatory variables; they capture diminishingor increasing effects on the dependent variable.

    ResamplingMethod

    A technique for approximating standard errors (and distributions of test statistics) whereby aseries of samples are obtained from the original data set and estimates are computed for eachsubsample.

    ResidualAnalysis

    A type of analysis that studies the sign and size of residuals for particular observations after amultiple regression model has been estimated.

    SmearingEstimate

    A retransformation method particularly useful for predicting the level of a response variablewhen a linear model has been estimated for the natural log of the response variable.

    StandardizedCoefficients

    Regression coefficients that measure the standard deviation change in the dependent variablegiven a one standard deviation increase in an independent variable.

    Variance ofthe PredictionError

    The variance in the error that arises when predicting a future value of the dependent variablebased on an estimated multiple regression equation.

    Chapter 7

    Base Group The group represented by the overall intercept in a multiple regression model that includesdummy explanatory variables.

    BenchmarkGroup

    See base group.

    BinaryVariable

    See dummy variable.

    ChowStatistic

    An F statistic for testing the equality of regression parameters across different groups (say,men and women) or time periods (say, before and after a policy change).

  • 8/14/2019 Terms.pdfnino

    2/2

    Control Group In program evaluation, the group that does not participate in the program.

    Difference inSlopes A description of a model where some slope parameters may differ by group or time period.

    DummyVariable A variable that takes on the value zero or one.

    DummyVariable Trap

    The mistake of including too many dummy variables among the independent variables; itoccurs when an overall intercept is in the model and a dummy variable is included for eachgroup.

    ExperimentalGroup

    See treatment group.

    InteractionTerm An independent variable in a regression model that is the product of two explanatory variables.

    Intercept Shift The intercept in a regression model differs by group or time period.

    LinearProbabilityModel (LPM)

    A binary response model where the response probability

    OrdinalVariable A variable where the ordering of the values conveys information but the magnitude of thevalues does not.

    PercentCorrectlyPredicted

    In a binary response model, the percentage of times the prediction of zero or one coincideswith the actual outcome.

    PolicyAnalysis

    An empirical analysis that uses econometric methods to evaluate the effects of a certainpolicy.

    ProgramEvaluation

    An analysis of a particular private or public program using econometric methods to obtain thecausal effect of the program.

    ResponseProbability

    In a binary response model, the probability that the dependent variable takes on the value one,conditional on explanatory variables.

    Self-Selection Deciding on an action based on the likely benefits, or costs, of taking that action.

    TreatmentGroup In program evaluation, the group that participates in the program.

    Uncentered R -Squared

    The R -squared computed without subtracting the sample average of the dependent variablewhen obtaining the total sum of squares (SST).