ICAR AIEEA (PG): Master's entrance, Veterinary Science and Animal Sciences · India · NTA for ICAR
Original practice questions written to the published syllabus · not past papersThe statistics a veterinarian needs to read a paper, design a trial or analyse herd records: descriptive statistics, tests of significance, regression and experimental design.
In the exams: ICAR AIEEA-PG 14 (statistics unit); ASRB NET
ICAR AIEEA (PG), Code 14 Animal Sciences (statistics unit)
Short numerical problems on mean, median, mode, SD, CV and SE; properties of the normal, binomial and Poisson distributions; choice and df of t, chi-square and F tests; correlation and regression coefficients; df in CRD and RBD.
How our questions for ICAR AIEEA spread across the units of Biostatistics, Computer Application & Research Methodology. Difficulty: 37 easy, 40 medium, 9 hard.
| Tests of significance: the t-test | 10 | |
| Measures of central tendency | 8 | |
| Probability distributions | 8 | |
| Research methodology | 8 | |
| Measures of dispersion | 7 | |
| Sampling methods | 7 | |
| The chi-square test | 7 | |
| Analysis of variance | 7 | |
| Correlation and regression | 7 | |
| Computer and spreadsheet basics | 7 | |
| Experimental designs: CRD and RBD | 6 | |
| Sample-size calculation | 4 |
Choose an answer, then open the working. Each explanation says why the right answer is right and why the others are not.
Herd A has mean daily milk yield 10 litres with SD 2 litres; herd B has mean 25 litres with SD 4 litres. Which statement about relative variability is correct?
D. Herd A is relatively more variable, CV 20% against 16%
CV = SD/mean × 100: herd A 2/10 = 20%, herd B 4/25 = 16%. The larger SD of herd B reflects its larger mean; the unit-free CV shows herd A is relatively more variable.
Further reading: Petrie A, Watson P. Statistics for Veterinary and Animal Science, 3rd ed.
Every PCV reading from a mis-calibrated centrifuge is 3 percentage points too high. When 3 is subtracted from every reading, how do the mean and SD change?
B. Mean falls by 3; SD is unchanged
Subtracting a constant shifts the whole distribution (change of origin): the mean falls by 3, but every deviation from the mean is unchanged, so the SD and variance are unchanged. Multiplying by a constant would change the SD.
Further reading: Petrie A, Watson P. Statistics for Veterinary and Animal Science, 3rd ed.
Assuming each calf is equally likely to be male or female and births are independent, what is the probability that exactly 2 of 4 calves are female?
B. 0.375
Binomial: 4C2 × 0.5² × 0.5² = 6/16 = 0.375. 0.500 confuses 'half the calves' with a probability; 0.0625 is the probability of one specific order such as FFMM; 0.250 counts 4 orders instead of 4C2 = 6.
Further reading: Petrie A, Watson P. Statistics for Veterinary and Animal Science, 3rd ed.
In a normal distribution, approximately what percentage of observations lie within one standard deviation of the mean?
C. 68.27%
Mean ± 1 SD contains 68.27%, ± 2 SD 95.45% and ± 3 SD 99.73%. Exactly 95% lies within ± 1.96 SD.
Further reading: Petrie A, Watson P. Statistics for Veterinary and Animal Science, 3rd ed.
From a list of 80 villages, 10 villages are chosen at random and every pig in those 10 villages is examined. What is this design called, and what is its main drawback?
A. Cluster sampling; pigs within a village resemble each other, lowering precision
Selecting groups and examining all their members is cluster sampling. It needs no list of individual pigs, but animals in one village share exposures, so the effective sample size is lower than the number of pigs examined (the design effect).
Further reading: Thrusfield M, Christley R. Veterinary Epidemiology, 4th ed.
At α = 0.05, what is the critical value of z for a one-tailed test?
B. 1.645
One-tailed 5% puts all 5% in one tail: z = 1.645. 1.960 is two-tailed 5%; 2.576 two-tailed 1%; 2.326 one-tailed 1%.
Further reading: Petrie A, Watson P. Statistics for Veterinary and Animal Science, 3rd ed.
Body weights are converted from kilograms to pounds. What happens to the correlation coefficient with heart girth and to the regression coefficient of weight on girth?
B. Correlation unchanged; regression coefficient changes
r is independent of change of origin and scale, so it stays the same; the regression coefficient carries units of y per unit of x and is multiplied by the conversion factor.
Further reading: Petrie A, Watson P. Statistics for Veterinary and Animal Science, 3rd ed.
In a 2 × 2 factorial trial, a feed additive improves growth at the low protein level but not at the high protein level. This is an example of:
C. Interaction between the two factors
Interaction exists when the effect of one factor depends on the level of the other. Factorial designs are the only designs that estimate it; separate one-factor trials miss it.
Further reading: Gomez KA, Gomez AA. Statistical Procedures for Agricultural Research, 2nd ed.
What is the main purpose of randomisation in an experiment?
C. To remove bias and make the error estimate valid
Randomisation gives every animal the same chance of each treatment, so unknown factors are not systematically linked to treatment and the error estimate is valid. It does not guarantee exactly equal groups; blocking addresses known differences.
Further reading: Gomez KA, Gomez AA. Statistical Procedures for Agricultural Research, 2nd ed.
Which study design starts with diseased and non-diseased animals and looks back at their past exposures?
D. Case-control study
A case-control study selects on outcome and compares past exposure, giving an odds ratio. A cohort study selects on exposure and follows forward; a cross-sectional survey measures both at one time.
Further reading: Petrie A, Watson P. Statistics for Veterinary and Animal Science, 3rd ed.
Ten here, 86 in the app. The Laisha app has every practice question we have written to ICAR AIEEA 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.
An AI operating system for agriculture: free guides, manuals and tools written for every country.