BLISS POINT STUDIES
RBI GRADE B (DEPR)
Test Series
Test – 13 (Phase –II)
Candidate has to attempt FIVE Questions in all.
Question No. 1 and 5 are compulsory and out of the
remaining, THREE are to be attempted choosing at least
ONE from each section.
SECTION - A
1. Answer the following questions in about 100 words each :
(a) Show that an AR(1) process is simply an MA(∞) process (that is, moving
average scheme of order infinity). 5
(b) Explain briefly : Gini coefficient 5
(c) What are the different types of machine learning algorithms? 5
(d) In a regression model does a high value of R 2 indicate a definite evidence of high
collinearity ? Explain. 5
2 (a) Explain multicollinearity problem in a regression model. What are its consequences? State
different indicators of multicollinearity and explain. 15
2
Find the value of r when the intercept term is absent in the two variable
linear regression model. 5
3 (a) Fit a second degree polynomial to the following data: 10
Year: 1882 1883 1884 1885 1886 1887 1888 1889 1890
Price Index: 84 82 76 72 69 68 70 72 73
(b)
Consider AR(2) given by X t X t 1 0 5 X t 2 wt , where wt is white noise 0, 2 .
(i) Is the process weak (covariance) stationary? Give reasons for your answer.
(ii) Calculate corr X1 , X 2 and corr X 5 , X 7 . 10
4 (a) If the ratio between Laspeyres’ and Paasche’s index numbers is 28/27,
find the missing figure (x) in the following table : 10
(b) Define a stationary time series.
For the stationary AR(2) process
5 1
Xt X t 1 X t 2 et
6 6
where e t ~ N 0, e2 denotes the noise.
Find the autocorrelation function of lags 1 and 2. 10
SECTION - B
Answer the following questions in about 100 words each :
5 (a) What do you understand by the seasonal variations in a time series ? Give
example. 5
(b) Show that the relationship X t 0 7 X t 1 0 3X t 2 t 0 7 t 1 (where
t denotes white noise ) defines ARIMA (1, 1, 1) model. 5
(c) How can artificial intelligence be used to improve healthcare? 5
(d) Show that TSS ESS RSS . 5
6 (a) Discuss the concept of heteroscedasticity. Explain this by graphical
representation. Show that OLS estimators are unbiased even under the
condition of heteroscedasticity. Obtain its variance. 15
(b) Explain the relevance of including an intercept term in a Classical linear
regression model. 5
7 The following model has been estimated to study the relationship between
demand for automobiles and per capita income in six states of India over a
period of 15 years
AUTOit 1 2 PCYit uit
where AUTO = demand for automobiles and PCY = per capita income.
(a) Explain how the Fixed Effect Within-Group (WG) method can be
applied to the above model. Show that in the process of estimation,
the fixed effect gets eliminated while the cross-section specific
intercept can still be obtained. 10
(b) Rewrite the model using the Fixed Effect LSDV method and explain
how the method allows for heterogeneity among the state. 10
8 (a) Consider Cobb-Douglas production function:
Q b0 Lb1 k b2
Test the hypothesis at 5% level of significance
H 0 : b1 b2 1
against H1 : b1 b2 1 10
(b) Discuss Durbin-Watson test for Autocorrelation. The data of the
following table are the OLS residuals of a consumption function :
Ĉt 3 02 0 93 Yt
Calculate Durbin-Watson d-statistic. Write your conclusion. 10
