LAISHA
Open Laisha

ASRB NET Time Series Analysis: practice questions

ASRB NET - Agricultural Statistics (and Computer Application / Bioinformatics) · India · Agricultural Scientists Recruitment Board (ICAR)

Original practice questions written to the published syllabus · not past papers
10worked here, free
43written to this exam in this subject
6syllabus units

About ASRB NET

ASRB NET - Agricultural Statistics (and Computer Application / Bioinformatics) is a professional certification run by Agricultural Scientists Recruitment Board (ICAR), for candidates in India. NET: one objective paper of about 150 questions, 2 hours, negative marking, online, Master's level (pattern as reported for other disciplines).

Official site: asrb.org.in.

We have not been able to confirm these details against the exam body's own specification, so fees, dates and pass marks are left out on purpose. Check the current format, eligibility, fees and dates on the official site.

Time Series Analysis in ASRB NET

Components of time series, measurement of trend and seasonal indices, moving averages, stationarity, ACF and PACF, identification of AR, MA and ARMA models, and simple forecasting.

Modelling observations ordered in time, from classical decomposition to Box-Jenkins and beyond: stationarity, ARIMA and seasonal ARIMA, volatility models for prices, vector autoregressions, state-space models and the Kalman filter, and forecast evaluation. Agribusiness econometrics introduces ARIMA and unit roots; this subject is the full treatment.

Our 43 ASRB NET questions in this subject: 19 easy, 24 medium, 0 hard, across 6 units.

10 practice questions, worked

Choose an answer, then open the working. Each explanation says why the right answer is right and why the others are not.

These 10 were written to ASRB NET and are not shown on any other exam's page.

Question 1 · easy

A dairy plant procures 2,640 thousand litres of milk in July. The multiplicative seasonal index for July is 120. What is the seasonally adjusted procurement for July?

  1. 3,168 thousand litres
  2. 2,640 thousand litres
  3. 2,200 thousand litres
  4. 2,520 thousand litres
Answer and working

C. 2,200 thousand litres

Seasonally adjusted value = original / index x 100 = 2,640 / 120 x 100 = 2,200. Multiplying by 1.2 gives 3,168, the opposite adjustment; subtracting 120 treats a multiplicative index as an additive amount.

Question 2 · medium

An exponential trend fitted to annual rice production gives log10(Y) = 2.31 + 0.0212 t, with t in years. What is the compound annual growth rate of production?

  1. 5.0 per cent
  2. 2.14 per cent
  3. 2.1 per cent
  4. 21.2 per cent
Answer and working

A. 5.0 per cent

With base-10 logs, Y grows by a factor of 10^0.0212 = 1.0500 each year, a growth rate of 5.0%. Reading 0.0212 directly as 2.1%, or using e^0.0212 (natural-log formula), ignores that the logs are base 10.

Question 3 · medium

In simple exponential smoothing with alpha = 0.4, what weight does the current smoothed level give to the observation two periods before the latest one, Y(t-2)?

  1. 0.064
  2. 0.240
  3. 0.144
  4. 0.360
Answer and working

C. 0.144

The weight on Y(t-j) is alpha(1 - alpha)^j = 0.4 x 0.6^2 = 0.144. 0.240 is the weight on Y(t-1); 0.064 uses 0.4^3; 0.360 is (1 - alpha)^2 without the alpha.

Question 4 · medium

A cooperative forecasts monthly fertiliser sales, which have a rising trend and a seasonal peak before each sowing season that grows in size as sales grow. Which smoothing method fits this pattern?

  1. Holt's linear method without a seasonal equation
  2. Simple exponential smoothing with a large alpha
  3. Multiplicative Holt-Winters
  4. Additive Holt-Winters with a fixed seasonal amount
Answer and working

C. Multiplicative Holt-Winters

Trend plus seasonality calls for Holt-Winters; a seasonal swing that grows with the level calls for the multiplicative form. Additive Holt-Winters assumes a constant seasonal amount; SES and Holt's method have no seasonal term.

Question 5 · medium

Why do forecasters often prefer a damped-trend version of Holt's method for horizons of several years?

  1. It always gives narrower prediction intervals than Holt's method
  2. Its long-range forecasts level off instead of rising for ever
  3. It removes the need for a level equation in the model
  4. It makes the method equivalent to simple moving averages
Answer and working

B. Its long-range forecasts level off instead of rising for ever

The damping factor phi below 1 shrinks the slope each step, so forecasts approach a constant. Straight-line extrapolation of a trend for many periods is usually too optimistic. Damping does not remove the level equation or guarantee narrower intervals.

Question 6 · easy

For a stationary AR(1) process with phi = 0.7, what is the autocorrelation at lag 3?

  1. 0.343
  2. 0.700
  3. 2.100
  4. 0.490
Answer and working

A. 0.343

rho(k) = phi^k, so rho(3) = 0.7^3 = 0.343. 0.700 is rho(1), 0.490 is rho(2), and 2.1 = 3 x 0.7 is not a correlation.

Question 7 · medium

The ACF of a stationary series shows a damped sine-wave pattern and the PACF has two significant spikes at lags 1 and 2 only. Which model is suggested?

  1. A random walk with drift
  2. An MA(2) process with real roots
  3. An ARMA(1,1) with a negative MA coefficient
  4. An AR(2) with complex roots
Answer and working

D. An AR(2) with complex roots

A PACF cutting off after lag 2 points to AR(2); a damped sine-wave ACF indicates complex roots, a pseudo-cycle. An MA(2) would have an ACF cutting off after lag 2; a random walk would show a slowly decaying ACF.

Question 8 · medium

An ARIMA model with 3 estimated parameters fitted to 100 observations has a maximised log-likelihood of -120. What is its BIC (Schwarz criterion), using natural logarithms?

  1. 253.8
  2. -106.2
  3. 267.6
  4. 246.0
Answer and working

A. 253.8

BIC = -2 log L + k ln n = 240 + 3 x 4.605 = 253.8. 246.0 is the AIC (penalty 2k); doubling the BIC penalty gives 267.6; -106.2 forgets the -2 multiplier.

Question 9 · medium

After first differencing, a series shows a lag-1 autocorrelation of about -0.5, and a fitted MA(1) coefficient is close to -1. What do these signs indicate?

  1. An explosive autoregressive component
  2. Over-differencing
  3. Conditional heteroscedasticity in the residuals
  4. A strong seasonal unit root at lag 12
Answer and working

B. Over-differencing

Differencing a series that was already stationary introduces a non-invertible MA root near -1 and a lag-1 autocorrelation near -0.5. The fix is to use one less difference. Seasonal or ARCH problems would show at seasonal lags or in squared residuals.

Question 10 · medium

After regular and seasonal differencing, the ACF of a monthly series has one significant spike at lag 12 and the PACF shows decaying spikes at lags 12, 24 and 36. Which seasonal term is indicated?

  1. A seasonal AR(3), P = 3
  2. A seasonal AR(1), P = 1
  3. A seasonal MA(1), Q = 1
  4. A further seasonal difference, D = 2
Answer and working

C. A seasonal MA(1), Q = 1

At seasonal lags the same rules apply as at ordinary lags: an ACF cutting off after one seasonal lag with a decaying seasonal PACF identifies a seasonal MA(1). A seasonal AR(1) would show the reverse pattern.

A study plan for Time Series Analysis in ASRB NET

This plan follows where our questions actually fall, so the time goes where the marks are likely to be. It is our reading of the syllabus, not the exam body's weighting.

  1. First, the heavy units (37% of the 43 questions): AR, MA and ARMA processes (8, 19%); Components of time series and classical decomposition (8, 19%).

    Read the manual chapters for these first and do every worked question you can find on them.

  2. Then the middle band: Smoothing: moving averages and exponential smoothing (Holt-Winters) (8, 19%); Stationarity, autocorrelation and partial autocorrelation functions (8, 19%).

    Aim for one sitting per unit, then mixed questions across them.

  3. Then the lighter units: Box-Jenkins ARIMA: identification, estimation and diagnostic checking (7, 16%); Seasonal ARIMA and ARIMAX with weather covariates (4, 9%).

    Learn the definitions, classifications and standard numbers; these units are more often recalled than worked.

  4. Bank the easy marks: Seasonal ARIMA and ARIMAX with weather covariates (3 easy of 4); Components of time series and classical decomposition (4 easy of 8).

    Do these early in revision so they are fast on the day.

  5. Finish timed. Sit the subject as a timed set without notes, mark it, and send each wrong answer back to its unit above.

Last updated · How Laisha writes and checks its pages · Report a mistake

Ask Laisha about this

Opens Laisha's chat with your question ready to send. Sign in or start free.

Unlock every question — ASRB NET Time Series Analysis

US$10 a month · one price worldwide · cancel any time

  • Every practice question in this subject, with full working
  • Timed exam papers and progress by unit
  • Ask Laisha to explain any answer — up to 1,000 questions a month
Free or Smarter
FreeSmarter
Grow guides, pest pages, articlesRead allRead all
Ask Laisha5 a dayUp to 1,000 a month
Exam practiceThe sample on each pageEvery question, timed papers
Crop calendar and pest alerts—For your own fields
Calculators and tools—All
Uploads and reports—100 a month, real files
10 days free for every new account, no card.