1 单选

1a possible solution to errors-in-variables bias is to

A mitigate the problem through in struinentes variables regression

B use log-log specifications

C use the square root of that variables sincethe error becomes smaller

D choose different funtional forms

2 thefollowing equations belong to the calss of liner regression model except:

A Y_i=B₀+B₁X_i+B₂Xi²+U_i                                B LnY_i=B₀+B₁X_i+U_i

C Y_i=Ln(B₀+B₁X_i+U_i )                           D  Y_i=Ln(B₀+B₁X_i  )+U_i

3 the interpretation of the slope coefficient in the model Y_i=B₀+B₁ Ln(X_i )+U_i is :a

A 1% change in x is associated with a B₁ % change in Y

B change in x by one unit is associated with 100 B₁ % change in Y

C  1% change in x is associated with a change in Y of 0.01 B₁ 

D  change in x by one unit is associated with a  B₁  change in y

4 to test population regerssion funtion is linear rather than a polynomial of order

A look at the pattern of the coefficients:if they change from positive to negative to positive.etc.then the polynomial regression should be used

B use the test of restrictions using the f.statistic

C compare the tss fom both regressions.

D check whether the regression k for the polynomial regression is higher than that of the linear regression.

5 including an interaction term between two independent variables allows for the flowing except that : the interaction term.

A lets the effects on y of a change in x₂ depend on the value of x₁

B lets the effect on y of a change in x₁ depend on the value of  x₂

C coefficient is the effect of of a unit increase in 根号下（x₁ +x₂ )

D coefficient is the effect of a unit increase in x₁ and x₂  above and beyond the sum of the individual effects of a unit increase in the two variables alone.

6  the ADL(p,q) model is represented by the following equation.

7in the log-log model the slope coefficient indicates

A the elasticity of y with respect to x

B ΔY/ΔX* Y/X

C ΔY/ΔX

D the effect that a unit change in x has on y.

 8 simultameous causality

A means that a third variable affects both Y and X .

B leads  to correlation between the repressor and the error term

C cannot be established regression analysis only detects correlation bewteen variables

D  means you must run a second repression of X  and y.

9 sample selection bias

A results in the OLS estimator being biased at although it is still consistent

B is more important for nonlinear least squares estimation than for OLS

C is very important for finite sample results

D occurs when a selection process influences the availablity of data and that process is related to the dependent vaviable.

10 possible solutions to omitted varilble bias when the omitted variable is not observed include the following with the exception of

A use of instrumental variables regressions

B  panel data estimation

C  use of randomized controlled experiments

D  nonlinear least squares estimation

11 the granger causality test

A  uses the f-statistic to test the hypothesis that certain repressors have no prelictive content for the dependent variable beyond that contained in the other repressors.

B is a special case of the aggwmented dickey-fuller test.

C  estiblishes the direction of cousality ( as used in common purlante) between x and y in addition to correlation

D  is a rather complicated test for statistical independence.

12 the root mean squared forecast error ( RMSFE) is defined as

A 根号下E[|Y_t-?_t/t-1|]                  B 根号下(Y_t-?_t/t-1)2

C根号下E[(Y_t-?_t/t-1)²]                  D  根号下E[(Y_t-?_t/t-1)]

13 in order to make reliable forecast with time series data. all of the following conditions are needed with time exception of

a the presence of omited variable bias

b the regression having high explanatorypower.

c coefficients having beeen estimated precisely

d the regression being stable

14 the first difference of the logurithm of Y_t equals

a the difference between the lead and the log of Y

b the grouth rate of Y  exactly

c approximately the prouth rate of Y  when grouth rate is small

d the first difference of Y 

15 stationarity means that the

a error terms are not correlated

b forecasts remain within 1.96 standard deriation outside the sample period

c time series has a unit root.

d probability distribution of the time series varible does not change over time

16 negative autocorrelation in the change of a varible implies that  

a the data are negatively trended

b the variable contains only negative values

c  the series is not stable

d an increase in the period is on average associated with a decrease in the next

17 the AR(p) model

a is defined as Y_t=B_o+B_pY_t-p+U_t

b can be written as  Y_t=B_o+B_pY_t-p+U_t-p

c represents Y_t  as a linear funtion of p of its lugged values

d can be represented as follows