LAISHA
Open Laisha

ASRB NET Survey Design, Questionnaires, Field Operations & Non-Sampling Errors: 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
74written to this exam in this subject
11syllabus units

What this subject covers

Turning a sampling design into data: pilot surveys, questionnaire and schedule design, enumerator training and supervision, CAPI and digital data capture, total survey error, non-sampling error models and post-enumeration checks, as used in large-scale agricultural and household surveys.

In the exams: AICE-JRF Ag Stat Unit 5 'non-sampling errors', 'design and organization of pilot and large scale surveys' (heavy); UPSC ISS Statistics III (present); national statistical offices (applied)

What ASRB NET asks from it

ASRB NET / ARS Agricultural Statistics

Planning and execution of agricultural surveys, non-sampling errors and their control (reported pattern).

Where the 74 questions fall

How our questions for ASRB NET spread across the units of Survey Design, Questionnaires, Field Operations & Non-Sampling Errors. Difficulty: 11 easy, 43 medium, 20 hard.

Response errors and interviewer effects; interpenetrating sub-samples9
CAPI, mobile data collection and paradata8
Confidentiality, disclosure control and release of microdata8
Questionnaire and schedule design; recall periods7
Post-enumeration surveys and coverage evaluation7
Planning a survey: objectives, population, frame and budget6
Pilot and pre-tests6
Field organisation: training, supervision and scrutiny6
Total survey error framework6
Data processing, editing, coding and tabulation6
Non-sampling errors: sources and classification5

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.

1 · Planning a survey: objectives, population, frame and budget · medium

An SRS calculation gives n0 = 400. With design effect 1.5 and expected response rate 80%, what sample should be drawn (n = n0 x deff / response rate)?

  1. 600
  2. 500
  3. 480
  4. 750
Answer and working

D. 750

n = 400 x 1.5 / 0.8 = 750.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

2 · Planning a survey: objectives, population, frame and budget · medium

What does an area frame guarantee that a list frame may not?

  1. Lower cost of construction per unit
  2. Up-to-date names of every farmer
  3. Complete coverage of land
  4. No need for field measurement at all
Answer and working

C. Complete coverage of land

Area segments cover all land by construction, but building them is expensive.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

3 · Questionnaire and schedule design; recall periods · medium

How does bounded recall reduce telescoping?

  1. A previous interview marks the period's start
  2. Interviewers are rotated between villages
  3. Respondents keep diaries for a full year
  4. Questions are asked only about last week
Answer and working

A. A previous interview marks the period's start

Neter and Waksberg showed bounding reduces telescoping.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

4 · Field organisation: training, supervision and scrutiny · medium

Why is a survey's sample often split into sub-rounds?

  1. To raise the interviewer design effect
  2. To avoid training the investigators
  3. To spread seasonal variation evenly
  4. To reduce the number of tables
Answer and working

C. To spread seasonal variation evenly

Each sub-round covers a part of the year with a random part of the sample.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

5 · CAPI, mobile data collection and paradata · medium

Which risk is greater with CAPI than with paper?

  1. Illegible handwriting on schedules
  2. Separate data-entry errors at headquarters
  3. One programming error affects all interviews
  4. Skip patterns followed wrongly by hand
Answer and working

C. One programming error affects all interviews

Instruments must be tested and version-controlled.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

6 · Response errors and interviewer effects; interpenetrating sub-samples · hard

What can interpenetrating sub-samples NOT detect?

  1. A bias common to all investigators
  2. Total variance of the estimate
  3. Variable errors of the investigators
  4. Differences between investigator teams
Answer and working

A. A bias common to all investigators

A shared bias shifts every sub-sample equally.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

7 · Total survey error framework · medium

An estimator has bias 2 and variance 4. What is its MSE?

  1. 6
  2. 4
  3. 16
  4. 8
Answer and working

D. 8

MSE = variance + bias^2 = 4 + 4 = 8.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

8 · Total survey error framework · medium

TSE recommends designing a survey to minimise:

  1. Response rate per interviewer
  2. The number of questions only
  3. Total error at fixed cost
  4. Sampling error at any cost
Answer and working

C. Total error at fixed cost

Trade-offs among error sources under a budget.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

9 · Confidentiality, disclosure control and release of microdata · medium

Under the (n, k) dominance rule, a cell is sensitive if:

  1. It has more than n contributors in all
  2. Its n largest units exceed k% of the total
  3. Its total exceeds k units of the variable
  4. It lies in the nth row of the table
Answer and working

B. Its n largest units exceed k% of the total

A few dominant contributors could be estimated.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

10 · Confidentiality, disclosure control and release of microdata · hard

Which pair captures the core trade-off in disclosure control?

  1. Coding speed and entry speed
  2. Sampling error and coverage error
  3. Response rate and interview length
  4. Disclosure risk and information loss
Answer and working

D. Disclosure risk and information loss

Each protection reduces analytical value.

Further reading: Groves et al., Survey Methodology; Murthy, Sampling Theory and Methods; Sukhatme et al., Sampling Theory of Surveys with Applications

Ten here, 74 in the app. The Laisha app has every practice question we have written to ASRB NET in this subject, marked as you go, with timed papers, a jump-to-unanswered list and a certificate when you pass at 70 per cent.

Free for ten days, then one subscription of US$10 a month. We would rather say so here than have you find it later.

Practise the full set in Laisha →

Read the subject

Survey Design, Questionnaires, Field Operations & Non-Sampling ErrorsThe full study manual, free ASRB NETFormat, sections and how it has changed

More ASRB NET practice

Small Area Estimation & Model-Based Survey InferenceBioinformatics & Computational BiologySampling Theory II: Unequal Probability, Cluster, Multistage & Repeated SamplingFactorial Experiments, Confounding, Split- & Strip-Plot DesignsResponse Surface, Mixture & Optimal DesignsStatistical Genetics: Population & Quantitative GeneticsBiometrical Techniques in Plant & Animal BreedingSpecialised Agricultural Experiments: Cropping Systems, Animal & On-Farm TrialsStatistical Genomics: QTL Mapping, GWAS & Genomic SelectionIncomplete Block Designs & Design ConstructionGroups of Experiments, Multi-Location Trials & Genotype x Environment AnalysisLinear Mixed Models, Variance Components & Spatial Analysis of Field TrialsAdvanced Design of Experiments (PhD)Bioassay, Survival & Epidemiological StatisticsCrop Area & Yield Estimation: Crop-Cutting ExperimentsLinear Models & Regression AnalysisCategorical Data Analysis & Generalized Linear ModelsPrinciples of Experimental Design & Basic DesignsOptimization Techniques for StatisticiansMultivariate AnalysisCrop Forecasting, Weather-Based Models & Non-linear Growth ModelsSampling Theory I: Simple, Stratified, Systematic, Ratio & Regression EstimationNonparametric & Rank-Based MethodsAgricultural Statistics System, Census & Official Statistics

Survey Design, Questionnaires, Field Operations & Non-Sampling Errors for other exams

ICAR AICE-JRF/SRF · IndiaIndian Statistical Service Examination · India

Ask Laisha about this

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