Mains PYQs
UPSC Mains Statistics paper 1 2019 questions
- Suppose a coin is tossed three times. If X denotes the number of heads on first toss and Y is the total number of heads, then write down the probability distribution of $Z = X + Y$.
- Prove that
$X_n \xrightarrow{P} 0$ if and only if $X_n \xrightarrow{d} 0$.
- Suppose $X_1$ and $X_2$ are independent and identically distributed (i.i.d) observations from the pdf given by
$f(x, \alpha) = \alpha x^{\alpha-1} e^{-x^{\alpha}}$, $x > 0$, $\alpha > 0$.
Show that $\dfrac{\log X_1}{\log X_2}$ is an ancillary statistic.
- The manufacturer of a spot remover claims that his product removes 90% of all spots. If, in a random sample, 17 of 20 spots were removed with the manufacturer's product, test the null hypothesis $H_0: \theta = 0.90$ against the alternative hypothesis $H_1: \theta < 0.90$ at the 0.05 significance level and comment.
- Let $X_1, X_2, X_3$ be three independent random variables with common pdf
$$f(x) = \begin{cases} 2e^{-2x}, & x \geq 0 \\ 0, & \text{otherwise.} \end{cases}$$
Let $Y = \min(X_1, X_2, X_3)$. Find mgf of Y. Using mgf, find $E(Y)$ and $E(Y^2)$.
- $X_1, \ldots, X_n$ is a random sample from probability density function
$f(x \mid \theta) = \theta x^{-2}$, $0 < \theta \leq x < \infty$.
(i) What is a sufficient statistic for $\theta$?
(ii) Find the Maximum Likelihood Estimate (MLE) of $\theta$.
(iii) Find the Method of Moments (MoM) estimate of $\theta$.
- Show that every Bernoulli sequence of random variables obeys the central limit law.
- Let X have the pdf
$$f(x, \theta) = \begin{cases} \dfrac{1}{\theta} e^{-x/\theta}, & 0 < x < \infty \\ 0, & \text{otherwise.} \end{cases}$$
To test $H_0: \theta = 2$ against $H_1: \theta = 4$, let $X_1$ and $X_2$ be a random sample of size 2. A test is defined by taking critical region as
$C = \{(X_1, X_2); 9.5 \leq X_1 + X_2 < \infty\}$.
Determine size and power of the test.
- Let X be one observation from the pdf
$f(x \mid \theta) = \left(\dfrac{\theta}{2}\right)^{|x|} (1-\theta)^{1-|x|}$, $x = -1, 0, 1$, $0 \leq \theta \leq 1$.
(i) Is X a complete sufficient statistic? Check also if $|X|$ is a complete sufficient statistic.
(ii) Does $f(x \mid \theta)$ belong to exponential class?
(iii) Find the MLE of $\theta$.
- Let the joint probability density function of X and Y be
$f(x, y) = C \cdot \exp\{-(x^2 - 4y^2 - xy)\}$,
where C is a constant.
Find:
(i) $E(X)$ and $V(X)$
(ii) $E(Y)$ and $V(Y)$
(iii) Correlation between X and Y
Also identify the distributions of X and Y.
- (i) An accounts manager in a company classifies 75% of customers as 'good credit' and the rest as 'risky credit' depending on their 'credit rating'. Customers in the 'risky' category allow their accounts to go overdue 50% of the time on average, whereas those in the 'good' category allow their accounts to become overdue only 10% of the time. What percentage of overdue accounts are held by customers in the 'risky credit' category? [8]
(ii) Suppose that two chess players played games and it was seen that the probability that Player I would win is 0.30, the probability that Player II would win is 0.45, and the probability that the game would end in a draw is 0.25. If these two chess players played 10 games, find the probability that Player I wins 6 games, Player II wins 2 games, and the remaining 2 games would be drawn. [7]
- Suppose $X_1, \ldots, X_n$ are i.i.d beta $(\mu, 1)$ and $Y_1, \ldots, Y_m$ are i.i.d beta $(\theta, 1)$. X's are independent of Y's.
(i) Find a Likelihood Ratio Test (LRT) of $H_0: \theta = \mu$ vs. $H_1: \theta \neq \mu$.
(ii) Show that the test in part (i) can be based on the statistic
$$T = \dfrac{\sum_{i=1}^{n} \log X_i}{\sum_{i=1}^{n} \log X_i + \sum_{j=1}^{m} \log Y_j}.$$
(iii) Find the distribution of T, when $H_0$ is true and then show how to get a test of size $\alpha$.
- A random variable X has the following probability function:
| Value of X = x | -2 | -1 | 0 | 1 | 2 | 3 |
|---|---|---|---|---|---|---|
| f(x) | 0.15 | k | 0.25 | 2k | 0.35 | k |
(i) Find the value of k. [5]
(ii) Obtain the distribution function F(x) and draw its graph. [10]
- Weddell seals live in the Antarctic and feed on fish during long, deep dives in freezing water. The seals benefit from these feeding dives, but the food they gain comes at a metabolic cost. A set of researchers wanted to know whether feeding per se was also energetically expensive, over and above the exertion of a regular dive. They measured the metabolic cost of 10 feeding dives and for each of these also measured a non-feeding dive by the same animal that lasted the same amount of time. The data are given below:
| Individual | Oxygen consumption after non-feeding dive (mL $\mathrm{O_2\,kg^{-1}}$) | Oxygen consumption after feeding dive (mL $\mathrm{O_2\,kg^{-1}}$) |
|---|---|---|
| 1 | 42 | 71 |
| 2 | 52 | 77 |
| 3 | 60 | 83 |
| 4 | 67 | 96 |
| 5 | 82 | 107 |
| 6 | 82 | 113 |
| 7 | 81 | 121 |
| 8 | 81 | 80 |
| 9 | 96 | 128 |
| 10 | 104 | 143 |
Mention assumptions about the populations and carry out an appropriate non-parametric test of hypothesis that the energetic cost is the same for feeding and non-feeding dives at level $\alpha = 0.05$.
- In order to estimate two parameters $\theta$ and $\phi$, a number of independent measurements are taken, each having errors with mean zero and variance $\sigma^2$. Suppose there are
(i) n observations with mean $\theta$,
(ii) m observations with mean $(\theta - \phi)$, and
(iii) m observations with mean $(\phi - \theta)$.
Set up this in the form of a standard linear model. What are the least square estimates of $\theta$ and $\phi$? Find $\mathrm{var}(\hat{\phi})$, $\mathrm{cov}(\hat{\theta}, \hat{\phi})$ and $\mathrm{var}(\hat{\phi} - \hat{\theta})$.
- Consider a standard linear model with design matrix
$$X = \begin{bmatrix} -2 & -2 \\ -1 & -1 \\ 0 & 0 \\ 1 & 1 \\ 2 & 2 \\ -1 & 1 \\ 1 & -1 \end{bmatrix}$$
and unknown coefficients $\beta_1$ and $\beta_2$. Which linear combinations $\hat{\psi} = a_1\hat{\beta}_1 + a_2\hat{\beta}_2$ have largest and smallest variance subject to $a_1^2 + a_2^2 = 1$?
- In Simple Random Sampling with Replacement (SRSWR) (with usual notation), show that
(i) $E(\bar{y}) = \bar{Y}$, and
(ii) $\mathrm{Var}(\bar{y}) = \dfrac{N-1}{Nn} S_y^2$.
- With usual notation, show that the ratio estimator $\hat{R}$ is the best linear unbiased estimator of R mentioning the conditions under which the property holds.
- Explain Duncan's Multiple Range Test.
- Show that the approximate variance of the regression estimator $\bar{y}_r$ is
$\mathrm{Var}(\bar{y}_r) = \left(\dfrac{1-f}{n}\right) S_y^2 (1-\rho^2)$ (with usual notation).
- Distinguish between fixed effect model, random effect model and mixed effect model.
- Consider two independent i.i.d samples, each of size 10, from two bivariate normal populations. The results are summarised below.
$$\bar{x}_1 = \begin{pmatrix} 3 \\ 1 \end{pmatrix}, \bar{x}_2 = \begin{pmatrix} 1 \\ 1 \end{pmatrix}, S_1 = \begin{pmatrix} 4 & -1 \\ -1 & 2 \end{pmatrix}, S_2 = \begin{pmatrix} 2 & -2 \\ -2 & 4 \end{pmatrix},$$
where $S_j$, $j = 1, 2$ are sample covariance matrices and $\bar{x}_j$, $j = 1, 2$ are sample means.
Provide suitable tests for the following hypotheses at level $\alpha = 0.05$ and draw your conclusion.
(i) $H_0: \mu_1 = \begin{pmatrix} 2.5 \\ 1 \end{pmatrix}$
(ii) $H_0: \mu_1 = \mu_2$
(iii) $H_0: \mu_{11} + 2\mu_{12} = 4$, where $\mu_1 = (\mu_{11}, \mu_{12})'$
(You can use the following values:
$F_{0.95, 2, 17} = 3.5915$, $F_{0.95, 2, 18} = 3.55$, $F_{0.95, 1, 19} = 4.38$)
- Let
$$\mathbf{X} \sim N_3\left(\begin{pmatrix} 1 \\ 2 \\ 3 \end{pmatrix}, \begin{pmatrix} 11 & -6 & 2 \\ -6 & 10 & -4 \\ 2 & -4 & 6 \end{pmatrix}\right)$$
$Z_1 = X_2 - X_3$
$Z_2 = X_2 + X_3$
$Z_3 \mid Z_1, Z_2 \sim N(Z_1 + Z_2, 10)$
Derive:
(i) The joint distribution of $Z_1$, $Z_2$ and $Z_3$
(ii) The conditional mean of $X_3$ given $X_1$ and $X_2$
(iii) $\rho^2_{3 \cdot 12}$
- Mentioning clearly the notations, show that Horvitz-Thompson estimator of the population total
$$\hat{Y}_{HT} = \sum_{i=1}^{n} \dfrac{y_i}{\pi_i}$$
is an unbiased estimator of Y and variance is
$$\mathrm{Var}(\hat{Y}_{HT}) = \sum_{i=1}^{N} \left(\dfrac{1-\pi_i}{\pi_i}\right) y_i^2 + 2\sum_{i=1}^{N}\sum_{j>i}^{N} \left(\dfrac{\pi_{ij} - \pi_i\pi_j}{\pi_i\pi_j}\right) y_i y_j.$$
- Define BIBD. State the parametric relationships of the BIBD with usual notation. Also prove the inequality $b \geq v + r - 1$ (with usual notation).
- For a population with linear trend and $N = nk$ (N = population size, n = sample size, k = sampling interval) show that
$V_{st} : V_{sy} : V_{ran} :: \dfrac{1}{n} : 1 : \dfrac{nk+1}{k+1}$,
where $V_{st}$, $V_{sy}$ and $V_{ran}$ are respectively for sampling variances of the sample unbiased estimator of the population mean for stratified sampling, systematic sampling and SRSWOR.
- Consider two sons born first in n families.
Let
$X_1$: head length of first son
$X_2$: head breadth of first son
$X_3$: head length of second son
$X_4$: head breadth of second son
The measurements provide the sample variance covariance matrix
$$S = \begin{pmatrix} 91.481 & 50.753 & 66.875 & 44.267 \\ 50.753 & 52.186 & 49.259 & 33.651 \\ 66.875 & 49.259 & 96.775 & 54.278 \\ 44.267 & 33.651 & 54.278 & 43.222 \end{pmatrix}$$
that leads to the correlation matrix
$R = \begin{pmatrix} R_{11} & R_{12} \\ R_{21} & R_{22} \end{pmatrix}$,
where $R_{11} = \begin{pmatrix} 1 & 0.7346 \\ 0.7346 & 1 \end{pmatrix}$, $R_{22} = \begin{pmatrix} 1 & 0.8392 \\ 0.8392 & 1 \end{pmatrix}$,
$R_{12} = R_{21}' = \begin{pmatrix} 0.7107 & 0.7040 \\ 0.6931 & 0.7085 \end{pmatrix}$.
Obtain the canonical correlations and hence the first canonical variables and interpret your result.
- Grain yields per plant (grams) of paddy of nine varieties in a Randomised Block Design are presented below:
| Variety | Replication 1 | Replication 2 | Replication 3 |
|---|---|---|---|
| 1 | 21.0 | 20.0 | 19.5 |
| 2 | 19 | 18 | 18.5 |
| 3 | 18.5 | 18 | 18.9 |
| 4 | 27.5 | * | 27 |
| 5 | 31 | 32.5 | 32.6 |
| 6 | 31.5 | 30.5 | 32 |
| 7 | 25.3 | 25 | 26.6 |
| 8 | 39 | 40 | 38.5 |
| 9 | 39 | 38.5 | 40 |
Analyse the experimental data.
(Table value $F(2, 25) = 3.39$ and $F(8, 25) = 2.34$, at 5% level of significance)