ECON 360 Econometrics || with 100% Errorless Solutions.
Definition of Econometrics correct answers Econometrics is the branch of economics that
develops and uses statistical methods for estimating economic relationships
Why is econometrics its own discipline seperate from statistics correct answers -It focuses on
problems inherent in analyzing data generated by individuals, firms, and other entities acting
strategically and interacting with each other
-necessary for assessing how large effects are and forecasting economic variables
Experimental Data correct answers data from controlled experiments
non experimental / observational / retrospective data correct answers Data collected in a passive
manner after outcomes on individuals and entities are observed
Empirical analysis correct answers -Uses data to test a theory, estimate an economic relationship,
or determine effects of policy or intervention
-uses an economic model to study phenomenon of interest
Parameters correct answers -the constants in a model that are being estimated
-also called the "betas"
Error term correct answers -u
-represents all other factors that affect y
-also captures measurement problems in one or more variables
Cross sectional data correct answers -Data collected on a unit at one point in time
-data must be statistically independent and drawn from a random sample
-ordering does not matter
Time series data correct answers -observations on a variable or several variables observed over a
stretch of time
-order is important
-data is not necessarily independent across time
-trends, frequency, and seasonality can be relevant
Independently pooled cross sectional data correct answers -different cross sectional data
collected at different points in time and pooled together
Independently paneled cross sectional data correct answers -same cross sectional data collected
at different points in time and paneled together
Notion of ceteris paribus correct answers -"all relevant factors equal"
-if successful, we can establish that change in one variable causes change in another variable
, Confounding factors correct answers hidden variables that correlate in some way with the
independent or dependent variable and have some sort of impact on the results; threat to internal
validity
Simple Linear Regression correct answers -begins with cross-sectional analysis collected from
random sample from population
-studies how y varies with changes in x, how other factors besides x affect y, the functional
relationship between x and y, and how we can create a ceteris paribus relationship between y and
x
Population regression equation correct answers y = Bo + B1x1 + B2x2 + u
Bo correct answers Intercept parameter
B1 , B2, B3... correct answers Slope parameter
- defined as a slope parameter because we assume y is linearly related to x. We hold u fixed to
know how y changes when x changes. This means changes in y are attributed to changes in the
slope parameters, effectively making them slope parameters
Average / Expected value of u in the population correct answers E(u) = 0
-the presence of the intercept parameter, Bo, allows us to assume E(u)=0. If E(u) is not 0, we just
adjust the intercept parameter.
Correlation between x and u in the population correct answers -We assume u and x are
uncorrelated in the population
-Corr(x,u) = 0
-implies that u and x are not linearly related
Zero conditional mean assumption correct answers E(uIx) = E(u) and E(u) = 0
therefore E(uIx) = 0
-shows that the population regression function is a linear function of x
How to estimate Bo and B1 correct answers -use E(uIx) = 0 (defines intercept)
and Cov (x,u) = 0 (defines non correlation between u and x)
OLS slope estimate correct answers -used to estimate B1
-how much the change in x,y is due to the change in x
-B1-hat = sample covariance (x,y) / sample variance (x)
-B1-hat = (sum (xi-x-bar) * (yi-y-bar)) / (sum (xi-x-bar)^2)
-can be computed as long as variance is not 0 (when all x have same value)
OLS Intercept estimate correct answers -used to estimate Bo
Definition of Econometrics correct answers Econometrics is the branch of economics that
develops and uses statistical methods for estimating economic relationships
Why is econometrics its own discipline seperate from statistics correct answers -It focuses on
problems inherent in analyzing data generated by individuals, firms, and other entities acting
strategically and interacting with each other
-necessary for assessing how large effects are and forecasting economic variables
Experimental Data correct answers data from controlled experiments
non experimental / observational / retrospective data correct answers Data collected in a passive
manner after outcomes on individuals and entities are observed
Empirical analysis correct answers -Uses data to test a theory, estimate an economic relationship,
or determine effects of policy or intervention
-uses an economic model to study phenomenon of interest
Parameters correct answers -the constants in a model that are being estimated
-also called the "betas"
Error term correct answers -u
-represents all other factors that affect y
-also captures measurement problems in one or more variables
Cross sectional data correct answers -Data collected on a unit at one point in time
-data must be statistically independent and drawn from a random sample
-ordering does not matter
Time series data correct answers -observations on a variable or several variables observed over a
stretch of time
-order is important
-data is not necessarily independent across time
-trends, frequency, and seasonality can be relevant
Independently pooled cross sectional data correct answers -different cross sectional data
collected at different points in time and pooled together
Independently paneled cross sectional data correct answers -same cross sectional data collected
at different points in time and paneled together
Notion of ceteris paribus correct answers -"all relevant factors equal"
-if successful, we can establish that change in one variable causes change in another variable
, Confounding factors correct answers hidden variables that correlate in some way with the
independent or dependent variable and have some sort of impact on the results; threat to internal
validity
Simple Linear Regression correct answers -begins with cross-sectional analysis collected from
random sample from population
-studies how y varies with changes in x, how other factors besides x affect y, the functional
relationship between x and y, and how we can create a ceteris paribus relationship between y and
x
Population regression equation correct answers y = Bo + B1x1 + B2x2 + u
Bo correct answers Intercept parameter
B1 , B2, B3... correct answers Slope parameter
- defined as a slope parameter because we assume y is linearly related to x. We hold u fixed to
know how y changes when x changes. This means changes in y are attributed to changes in the
slope parameters, effectively making them slope parameters
Average / Expected value of u in the population correct answers E(u) = 0
-the presence of the intercept parameter, Bo, allows us to assume E(u)=0. If E(u) is not 0, we just
adjust the intercept parameter.
Correlation between x and u in the population correct answers -We assume u and x are
uncorrelated in the population
-Corr(x,u) = 0
-implies that u and x are not linearly related
Zero conditional mean assumption correct answers E(uIx) = E(u) and E(u) = 0
therefore E(uIx) = 0
-shows that the population regression function is a linear function of x
How to estimate Bo and B1 correct answers -use E(uIx) = 0 (defines intercept)
and Cov (x,u) = 0 (defines non correlation between u and x)
OLS slope estimate correct answers -used to estimate B1
-how much the change in x,y is due to the change in x
-B1-hat = sample covariance (x,y) / sample variance (x)
-B1-hat = (sum (xi-x-bar) * (yi-y-bar)) / (sum (xi-x-bar)^2)
-can be computed as long as variance is not 0 (when all x have same value)
OLS Intercept estimate correct answers -used to estimate Bo
