Mains PYQs
UPSC Mains Statistics paper 1 2020 questions
- An insurer offers a health plan to the employees of a large company. As part of this plan, individually any employee may choose exactly two or none of the supplementary coverages A, B and C. The proportions of the company employees that choose coverage A, B and C are $\frac{1}{6}$, $\frac{1}{2}$ and $\frac{7}{12}$ respectively. Determine the probability that a randomly chosen employee will choose no supplementary coverage.
- Let X and Y be iid random variables with $P(X = k) = 2^{-k}$, $k = 1, 2, 3, \ldots$. Find $P(X > Y)$.
- For a geometric distribution $p(x) = 2^{-x}$; $x = 1, 2, 3, \ldots$, show that Chebyshev's inequality gives $P(|X - 2| \le 2) > \frac{1}{2}$, while the actual probability is $\frac{15}{16}$.
- For a group of policies, losses follow the distribution function
$$F(x) = 1 - \frac{\theta}{x}, \quad \theta < x < \infty.$$
A sample of 20 losses resulted in the following :
| Interval | Number of losses |
|---|---|
| $x \le 10$ | 9 |
| $10 < x \le 25$ | 6 |
| $x > 25$ | 5 |
(i) Obtain maximum likelihood estimator (MLE) of $\theta$. [4]
(ii) Find Cramer-Rao Lower Bound (CRLB) using MLE of $\theta$. [4]
(iii) Using CRLB and asymptotic distribution of MLE, obtain 95% confidence interval for $\theta$. [2]
- Let $X_1$ and $X_2$ be two iid random variables with normal $N(\theta, 1)$ distribution. Further, consider Bernoulli random variable V with $P(V = 1) = \frac{1}{4}$ and which is independent of $X_1$ and $X_2$. Define $X_3$ as
$$X_3 = \begin{cases} X_1, & \text{if } V = 0 \\ X_2, & \text{if } V = 1 \end{cases}$$
For testing the hypothesis $H_0 : \theta = 0$ versus $H_1 : \theta = 1$, consider the test
Reject $H_0$ if $\frac{X_1 + X_2 + X_3}{3} > C$
Find C such that the test size becomes 0.05. Also compute power of the test.
[Given that : $P(Z > 1.64) = 0.05$, $P(|Z| > 1.96) = 0.05$, $P(Z > 0.30) = 0.03821$]
- The lifetime in hours of each bulb manufactured by a particular company follows an independent exponential distribution with mean $\theta$. To test the hypothesis $H_0 : \theta = 2000$ versus $H_1 : \theta = 1000$, an experimenter sets up an experiment with 50 bulbs with 5 bulbs in each of 10 different locations to examine their lifetimes.
To get quick preliminary results, the experimenter decides to stop the experiment as soon as one bulb fails at each location. Let $Y_i$ denote the lifetime of the first bulb to fail at location i, $i = 1, 2, \ldots, 10$. Obtain the most powerful test of size 0.05 to test $H_0$ versus $H_1$ based on the available lifetimes. If the available data is
510, 9752, 5650, 12385, 230, 4225, 860, 300, 3000 and 1500,
give your conclusion.
[Given that : $P(\chi^2_{(20)} < 10.851) = 0.05$]
- The random variable X takes values on the interval $[0, 2]$. Given that $P(X = 1) = 0.25$, $F(x \mid x < 1) = x^2$, $F(x \mid x > 1) = x - 1$, $E(X) = 1$.
Find $P(X \le 1)$.
- Let $\theta > 0$ be the unknown parameter and $X_1, X_2, \ldots, X_n$ be a random sample from the distribution with the probability distribution function (pdf)
$$f(x, \theta) = \begin{cases} \frac{2x}{\theta^2}, & 0 \le x \le \theta \\ 0, & \text{otherwise} \end{cases}$$
Find maximum likelihood estimator (MLE) of $\theta$ and its mean squared error (MSE).
- Let $X_1, X_2, \ldots, X_n$ be a random sample from uniform distribution $U(\theta - \frac{1}{2}, \theta + \frac{1}{2})$. Show that $Y = (X_{(1)}, X_{(n)})$ is sufficient statistic for $\theta$ but not complete, where
$X_{(1)} = \min.(X_1, X_2, \ldots, X_n)$
$X_{(n)} = \max.(X_1, X_2, \ldots, X_n)$
- Let $X \sim$ uniform $U(0, 2\theta)$, $\theta > 0$ distribution.
Define $Y = \max(X, 2\theta - X)$. Find $E(Y)$.
- State inversion theorem on characteristic function. Hence, find the density function corresponding to the characteristic function
$$\phi(t) = \begin{cases} 1 - |t|, & |t| \le 1 \\ 0, & |t| > 1. \end{cases}$$
- To test sequentially the hypothesis $H_0$ for which the distribution is given by
$$P(X = -1) = P(X = 1) = P(X = 2) = \frac{1}{3}$$
against the alternative $H_1$ that is given by
$$P(X = -1) = P(X = 1) = \frac{1}{4}, \quad P(X = 2) = \frac{1}{2}$$
it is decided to continue sampling as long as
$$-\left(\frac{n+1}{2}\right) < S_n < \left(\frac{n+2}{2}\right)$$
where $S_n = \sum_{i=1}^{n} X_i$, and $X_i$'s are successive observations.
Compute the probability under $H_0$ and $H_1$ that the procedure will terminate with the $2^{nd}$ observation or earlier.
- (i) Obtain characteristic function of uniform distribution $U(0, 1)$. [5]
(ii) Let $\{X_n\}$ be a sequence of independent random variables such that
$$P\left(X_k = \frac{k}{n}\right) = \frac{1}{n}, \quad k = 1, 2, \ldots, n$$
Show that $X_n$ converges in law to a uniform distribution. State the result you have used. [10]
- A random sample of 14 male students from a rural Junior High School and an independent random sample of 16 male students from an urban Junior High School were given a test to measure their level of mental health. The obtained data are given in the following table :
Mental Health Scores of Junior High Schools' male students :
Rural : 28, 49, 42, 30, 33, 36, 49, 31, 41, 46, 41, 21, 20, 28
Urban : 37, 22, 24, 24, 27, 44, 34, 26, 20, 26, 25, 45, 32, 40, 45, 25
Apply Median Test to test the hypothesis at 5% level of significance that their median mental health level scores are equal or not.
[Given that $\chi^2_{(1, 0.05)} = 3.841$]
- A student fits the following linear regression model to a given data :
$$y_i = \alpha + \beta x_i + u_i, \quad i = 1, 2, \ldots, n$$
$u_i$'s are iid normal values ($N(0, \sigma^2)$), where $\sigma^2$ is unknown.
The following information is available :
$n = 7$, $\sum (x_i - \bar{x})^2 = 280000$, $\sum (x_i - \bar{x})(y_i - \bar{y}) = 16500$
95% confidence interval for $\beta$ is : $(0.030, 0.088)$.
Calculate what proportion of the total variability of the responses is explained by the model. Given that $t_{0.025, 5} = 2.57$.
- Let $X \sim N_2(\mu, \Sigma)$ with probability distribution function (pdf),
$$f(x) = C e^{-Q/2},$$
where $Q = 3x^2 + 2y^2 - 2xy - 32x + 4y + 92$.
Obtain $\mu$ and $\Sigma$.
- A population consists of 6 units with values 6, 3, 1, 4, 2 and 5. Write down all possible samples of size 2 without replacement and verify that
$$V(\bar{y}) = \frac{N - n}{N.n} S^2.$$
- Define Gauss-Markov linear model. State and prove necessary and sufficient condition for the linear function $l'\beta$ of the parameters to be linearly estimable.
- Describe BIBD and show that $b \ge v$, where symbols have usual meanings.
- What is systematic sampling ? In usual notation, prove that
$$V(\bar{y}_{sys}) = \frac{nk - 1}{nk} \cdot \frac{S^2}{n} \{1 + (n - 1)\rho\},$$
where $\rho$ is the intra-class correlation coefficient between the units of the same systematic samples. Hence, determine the minimum value of $\rho$ for $V(\bar{y}_{sys})$ to be non-negative.
- Let $Y_1, Y_2, Y_3$ be uncorrelated variables with common variance $\sigma^2$ such that
$E(Y_1) = \beta_1 + \beta_2$
$E(Y_2) = 2\beta_1$
$E(Y_3) = \beta_1 - \beta_2$
Compute residual mean square.
- Let $n = 4$, $p = 2$, $X = \begin{pmatrix} X_1 \\ X_2 \end{pmatrix}$, where
$X_1$ : weight (in kg), $X_2$ : height (in cm) of infant.
Sample data matrix
$$X = \begin{bmatrix} 3.0 & 4.0 & 3.0 & 3.0 \\ 40 & 40 & 30 & 35 \end{bmatrix}$$
Test at 5% level of significance the null hypothesis $H_0 : \mu = \mu_0 = \begin{pmatrix} 3.0 \\ 35.0 \end{pmatrix}$.
[Given that : $F_{((2,2), 0.05)} = 19.00$]
- Define Hotelling's-$T^2$. Show that $T^2$ statistic is a function of likelihood ratio criteria.
- Let R be the ratio of population totals of 'y' and 'x' and $\hat{R}$ is the estimate of R. Obtain $V(\hat{R})$. Also find the estimate $\hat{V}(\hat{R})$.
- What do you mean by Partial Confounding ? Describe a $2^3$-factorial design arranged in 2 blocks with 4 replications, where ABC, BC, AC and AB are confounded. Also prepare ANOVA table for such design.
- Discuss Simple Lattice Design. Let $\beta_{1.}, \ldots, \beta_{p.}$ denote row block effects and $\beta_{.1}, \ldots, \beta_{.p}$ denote column block effects and $\zeta_{ij}$ denote the effect of $(i, j)^{th}$ treatment, where number of treatments $t = p^2$. How do you test the hypothesis
$$H_0 : \zeta_{11} = \zeta_{12} = \ldots = \zeta_{pp} = \tau$$
using ANOVA table ?
- Show that in pps sampling, with replacement, an unbiased estimator of the population mean $\bar{Y}$ is
$$\bar{y}_{pps} = \frac{1}{n}\sum_{i=1}^{n} \frac{y_i}{Np_i} = \frac{1}{n}\sum_{i=1}^{n} Z_i = \bar{Z}, \text{ with variance}$$
$$V(\bar{y}_{pps}) = \frac{1}{n}\sum_{i=1}^{N} p_i \left(\frac{y_i}{Np_i} - \bar{Y}\right)^2$$
where $p_i = \frac{X_i}{X}$ be the probability that the $i^{th}$ unit is selected in a sample, such that $\sum p_i = 1$, $Z_i = \frac{y_i}{Np_i}$.
- Two types of tests viz : written and oral were conducted for seeking admission to MBA course. The result of the test given by the students are as follows :
$$x = \begin{pmatrix} x_1 \\ x_2 \end{pmatrix} = \begin{pmatrix} \text{marks obtained in written test} \\ \text{marks obtained in oral test} \end{pmatrix}$$
Let
$\pi_1$ : students eligible for admission to MBA course
$\pi_2$ : students not eligible for admission to MBA course
$$\mu_1 = \begin{pmatrix} 30.6 \\ 14.4 \end{pmatrix}, \quad \Sigma_1 = \begin{pmatrix} 5.60 & -0.62 \\ -0.62 & 2.08 \end{pmatrix}$$
$$\mu_2 = \begin{pmatrix} 24.8 \\ 11.2 \end{pmatrix}, \quad \Sigma_2 = \begin{pmatrix} 5.60 & -0.62 \\ -0.62 & 2.08 \end{pmatrix}$$
If one student gets 29.0 marks in written test and 12.0 in oral test, classify the student as eligible or not based on Fisher's linear discriminant function. Also find the probability of misclassification.
[Given that $P(0 < Z < 1.8277) = 0.4664$]