Mains PYQs
UPSC Mains Statistics paper 1 2023 questions
- Out of 1000 persons born, only 900 reach the age of 15 years, and out of every 1000 who reach the age of 15 years, 950 reach the age of 50 years. Out of every 1000 who reach the age of 50 years, 40 die in one year. Accordingly, what is the probability that a person would attain the age of 51 years ?
- Let X be a continuous random variable with probability density function :
$$f(x) = \begin{cases} \dfrac{x}{2}, & 0 \le x < 1 \\ \dfrac{1}{2}, & 1 \le x < 2 \\ \dfrac{3-x}{2}, & 2 \le x < 3 \\ 0, & \text{elsewhere} \end{cases}$$
Obtain the cumulative distribution function of X and hence find the value of $P\left(X > \dfrac{3}{2}\right)$.
- Let $\{X_n, n \ge 1\}$ be a sequence of mutually independent random variables such that
$P(X_n = n^{\alpha}) = P(X_n = -n^{\alpha}) = 0.5$, for any $\alpha > 0$.
Derive the condition on $\alpha$ under which the sequence $\{X_n, n \ge 1\}$ obeys WLLNs.
- Apply Run Test to test the randomness of the following sequence of H and T at 5% level of significance :
HHHHHHTHHHHHTHTHHHH
TTHHHHTHHHTTHHHHHH
THHTTHHTHHH
Given : $Z_{(0.025)} = 1.96$
$Z_{(0.05)} = 1.645$
- Differentiate between prior and posterior distributions. In case of squared error loss function, find out the Bayes estimator for unknown parameter.
- Let X, Y, Z be three mutually independent standard exponential variates and $W_1 = X + Y + Z$, $W_2 = \dfrac{X+Y}{X+Y+Z}$, $W_3 = \dfrac{X}{X+Y}$.
Then
(i) determine the joint distribution of $W_1$, $W_2$ and $W_3$. [10]
(ii) find out the marginal probability density functions of $W_1$, $W_2$ and $W_3$. [6]
(iii) examine the mutual independence of $W_1$, $W_2$ and $W_3$, and give your comment. [4]
- Give an example to prove or disapprove the following :
$$P(\limsup A_n) = 0 \Rightarrow \sum_{k=1}^{\infty} P(A_k) < \infty,$$
for any sequence $\{A_n, n \ge 1\}$ of events defined on a probability space $(\Omega, \mathcal{A}, P)$.
- Let $\{Y_n, n \ge 1\}$ be a sequence of random variables and Y be a degenerate random variable. Examine whether '$Y_n$ converges in distribution to Y' implies '$Y_n$ converges in probability to Y'.
- (i) If X is a random variable with finite variance, show that
$$\lim_{n \to \infty} n^2 P\{|X| > n\} = 0.$$ [10]
(ii) In a certain recruitment test, there are multiple choice questions. There are four possible options to each question, out of which one is correct. The probability of knowing correct option for an intelligent student is 90%, while it is 20% for a weaker student. An intelligent student ticks the correct option. What is the probability that he was guessing ? [10]
- Determine whether the sequence of mutually independent random variables $\{X_n, n \ge 1\}$, in which
$$\left.\begin{aligned} P(X_n = \pm n^{\lambda}) &= \dfrac{1}{2n^{2\lambda}} \\ P(X_n = 0) &= 1 - \dfrac{1}{n^{2\lambda}} \end{aligned}\right\} \left(\lambda < \dfrac{1}{2}\right)$$
obeys Central Limit Theorem (CLT) or not.
- Define Sequential Probability Ratio Test (SPRT) along with its operating characteristic function and average sample number. Determine SPRT for testing $H_0 : \theta = 4$ against $H_1 : \theta = 5$ in $N(\theta, 1)$ with $\alpha = 0.5$ and $\beta = 0.2$.
- What is the role of properties of completeness and sufficiency in Statistical Inference ? Explain. In U (0, $\theta$), find out Uniformly Minimum Variance Unbiased Estimator (UMVUE) of $\theta$.
- A survey of 400 families with four children each have the following distribution :
| Number of boys | 0 | 1 | 2 | 3 | 4 |
| --- | --- | --- | --- | --- | --- |
| Number of families | 16 | 89 | 145 | 118 | 32 |
Is this result consistent with the hypothesis that male and female births are equally probable at 5% level of significance ?
It is given that $\chi^2_{(.05)}$ for 4 degrees of freedom = 9.488 and
$\chi^2_{(.05)}$ for 5 degrees of freedom = 11.070.
- Define Likelihood Ratio Test. In $N(\theta, \sigma^2)$, where $\sigma^2$ is unknown, find out LR test for testing $H_0 : \theta = \theta_0$ against $H_1 : \theta \in (\Omega - \theta_0)$, where $\Omega$ is the parametric space for $\theta$. $\alpha$ is the size of the test.
- (i) If $\mathbf{X} = (X_1\ X_2\ X_3)'$ is distributed as $N_3(\boldsymbol{\mu}, \Sigma)$, find the distribution of $[(X_1 - X_2)\ (X_2 - X_3)]'$. [5]
(ii) Suppose that $\mathbf{X} = (X_1\ X_2\ X_3)' \sim N_3(\mathbf{0}, \Sigma)$, where $\Sigma = \begin{pmatrix} 1 & \rho & 0 \\ \rho & 1 & \rho \\ 0 & \rho & 1 \end{pmatrix}$.
Is there a value of $\rho$ for which $(X_1 + X_2 + X_3)$ and $(X_1 - X_2 - X_3)$ are independent ? [5]
- Show that $\mathbf{X} = (X_1, X_2, ..., X_p)'$ has p-variate normal distribution if and only if every linear combination $(l_1 X_1 + l_2 X_2 + ... + l_p X_p)$ of $\mathbf{X}$ follows a univariate normal distribution.
- Let $x_1, x_2, ..., x_n$ be n given observations, and suppose that
$Y_i = \beta_0 + \beta_1 x_i + e_i;\ i = 1, 2, ..., n$,
where $\beta_0, \beta_1$ are unknown parameters and $e_i$ are mutually independent normal random variables with $E(e_i) = 0$ and $V(e_i) = \sigma^2$, $i = 1, 2, ..., n$. Also, $\sigma^2$ is assumed to be unknown.
Test the null hypothesis $H_0 : \beta_0 = \beta_1 = 0$.
- Complete the following analysis of variance table of a design and examine whether there is a significant difference between the treatments at 5% level of significance :
| Source of Variation | Degrees of Freedom | Sum of Squares | Mean Sum of Squares | Variance Ratio |
| --- | --- | --- | --- | --- |
| Blocks | - | 21 | 4.2 | - |
| Treatments | - | - | 5.0 | - |
| Error | 15 | 12 | - | |
| Total | - | - | | |
Given that
$F_{.05}(3, 15) = 8.70$
$F_{.05}(5, 15) = 4.62$
- Define regression estimator used for the estimation of population mean. Obtain its bias and Mean Square Error (MSE) to the first order of approximation.
- Let $\mathbf{X} = (X_1\ X_2\ X_3)'$ be distributed as $N_3(\boldsymbol{\mu}, \Sigma)$, where $\boldsymbol{\mu} = (2\ \ {-1}\ \ 3)'$ and $\Sigma = \begin{pmatrix} 4 & 1 & 0 \\ 1 & 2 & 1 \\ 0 & 1 & 3 \end{pmatrix}$.
Find
(i) the conditional distribution of $(X_1\ X_2)'$ given $X_3 = 2$. [8]
(ii) partial correlation coefficient $\rho_{12.3}$ and multiple correlation coefficient $R_{1.23}$. [7]
- (i) Describe the complete analysis of two-way classified data with multiple (but equal) observations per cell, clearly stating the assumptions used. Also state two examples where such type of analysis is used. [15]
(ii) Let three mutually independent variables $Y_1$, $Y_2$ and $Y_3$ having common variance $\sigma^2$ and
$E(Y_1) = \beta_1 + \beta_2$, $E(Y_2) = \beta_1 + \beta_3$, $E(Y_3) = \beta_1 + \beta_2$ be given.
Show that the linear parametric function $p_1\beta_1 + p_2\beta_2 + p_3\beta_3$ is estimable if and only if $p_1 = p_2 + p_3$, clearly stating the assumptions used, if any. [5]
- (i) State briefly three reasons why an analyst may wish to perform a principal component analysis. [6]
(ii) Define canonical correlations and give two examples of their application. Describe the procedure of working out canonical correlations and canonical variates. [9]
- Discuss the difference between sampling for variables and sampling for attributes with examples. For a qualitative characteristic, find an unbiased estimator of population proportion along with its variance when sample is drawn by simple random sampling without replacement. Also obtain an unbiased estimator of this variance.
- The table given below gives the population and sample sizes, stratum means and variance of a stratified random sample of size 50. Symbols used have their usual meanings.
| Stratum Number | $N_i$ | $n_i$ | $\bar{y}_i$ | $s_i^2$ |
| --- | --- | --- | --- | --- |
| 1 | 30 | 5 | 35 | 36 |
| 2 | 50 | 10 | 40 | 49 |
| 3 | 60 | 15 | 40 | 81 |
| 4 | 60 | 20 | 55 | 144 |
Verify that the existing allocation is optimum for given 4 strata. Also calculate the estimate of population variance under this allocation.
- Differentiate between Simple Random Sampling and Probability Proportional to Size Sampling. How will you draw a PPS sample of size n from a population of size N (n < N) by (i) Cumulative Total Method and (ii) Lahri's Method ? Explain.
- Differentiate between randomised block design and balanced incomplete block design. In usual notations, for a balanced incomplete block design, prove that (i) bk = vr (ii) $\lambda(v - 1) = r(k - 1)$ and (iii) $b \ge v$.
- Explain the concept of confounding in design of experiment. In an experiment with three factors A, B and C, each at two levels, three replicates are divided in two blocks, each of four units. How will you confound ABC in the first, AC in the second and BC in the third replication ?
- Differentiate among fixed, random and mixed effect models with examples. How are the three basic principles of design fulfilled in randomised block design ? Explain.