Mains PYQs
UPSC IFoS Mains Statistics paper 2 2021 questions
- Distinguish between defects and defectives in SQC. Give some examples of defects for which the c-chart is applicable. How do you calculate control limits for a c-chart ?
- If $T$ is a random variable representing the hours of failure for a device with following pdf :
$$f(t) = t\, e^{-t^2/2}; \; t \ge 0$$
find the reliability function and hazard function. If 50 devices are placed in operation and 27 are still in operation 1 hour later, find approximately the expected number of failures in the time interval from 1 to 1.1 hours using hazard function.
- Solve the following linear programming problem graphically :
Minimize $Z = 20x_1 + 20x_2$
subject to
$x_1 + 2x_2 \ge 1$
$2x_1 + x_2 \ge 2$
$2x_1 + 3x_2 \ge 3$
$3x_1 + 2x_2 \ge 4$
$x_1, x_2 \ge 0$
- A company has a team of four salesmen and there are four districts where the company wants to start its business. The profit per day (in ₹) for each salesman in each district is estimated as given below :
| Salesman | District 1 | District 2 | District 3 | District 4 |
|---|---|---|---|---|
| A | 16 | 10 | 14 | 11 |
| B | 14 | 11 | 15 | 15 |
| C | 15 | 15 | 13 | 12 |
| D | 13 | 12 | 14 | 15 |
Find the assignment of salesmen to various districts which will yield maximum profit.
- Using the Rule of Dominance, solve the game with the following pay-off matrix :
| Player A's strategies \ Player B's strategies | 1 | 2 | 3 | 4 | 5 |
|---|---|---|---|---|---|
| 1 | 2 | 5 | 10 | 7 | 2 |
| 2 | 3 | 3 | 6 | 6 | 4 |
| 3 | 4 | 4 | 8 | 12 | 1 |
- Show the probability that at least one of the two points $\bar{X}$ and $R$ goes outside the control limits
$$1 - \left[S(\sqrt{n}\,T - 3\rho) - S(\sqrt{n}\,T + 3\rho)\right] \cdot \left[P\left(\frac{R}{\sigma} \le D_2 \rho\right) - P\left(\frac{R}{\sigma} \le D_1 \rho\right)\right]$$
where $\rho = \frac{\sigma'}{\sigma}$, $T = \frac{\mu' - \mu}{\sigma}$,
$$S(x) = \int_x^{\infty} e^{-\frac{1}{2}t^2}\, dt$$
assuming that the control charts are based on $\mu'$ population mean and $\sigma'$ as population standard deviation, where the actual values of these parameters are $\mu$ and $\sigma$ respectively.
- The time to failure in operating hours of a critical solid state power unit has the hazard rate function given by
$$\lambda(t) = (0.003)\left(\frac{t}{500}\right)^{1/2}; \text{ for } t \ge 0$$
(i) What is the reliability if the power unit must operate continuously for 50 hours ?
(ii) Determine the design life if a reliability of 0.90 is desired.
(iii) Compute the MTTF.
(iv) Given that the unit has operated for 50 hours, what is the probability that it will survive a second 50 hours of operation ?
- Use Simplex method to find an optimal solution to the following LPP :
Maximize $Z = 3x_1 + 2x_2$
subject to
$-x_1 + 2x_2 \le 4$
$3x_1 + 2x_2 \le 14$
$x_1 - x_2 \le 3$
$x_1, x_2 \ge 0$
Does it indicate the existence of an alternative optimal solution ? If yes, obtain it.
- Define renewal function and renewal density function. Derive the following forward renewal equation :
$$U(t) = f_1(t) + \int_0^t U(t - \tau) f(\tau)\, d\tau$$
- The Optimal Simplex table of the following LPP :
Maximize $Z = 10x_1 + 15x_2 + 20x_3$
subject to
$2x_1 + 4x_2 + 6x_3 \le 24$
$3x_1 + 9x_2 + 6x_3 \le 30$
$x_1, x_2, x_3 \ge 0$
is given below :
| $C_B$ | $X_B$ \ $C_j$ | $x_1$ (10) | $x_2$ (15) | $x_3$ (20) | $x_4$ (0) | $x_5$ (0) | b |
|---|---|---|---|---|---|---|---|
| 20 | $x_3$ | 0 | -1 | 1 | 1/2 | -1/3 | 2 |
| 10 | $x_1$ | 1 | 5 | 0 | -1 | 1 | 6 |
| | $Z_j - C_j$ | 0 | 15 | 0 | 0 | 10/3 | Z=100 |
Perform the sensivity analysis to check whether optimality of the table is affected if the profit coefficients are changed from (10, 15, 20) to (7, 14, 15).
- Show that the Markov Chain with transition probability matrix
$$P = \begin{bmatrix} 0 & 1 & 0 \\ \frac{1}{2} & 0 & \frac{1}{2} \\ 0 & 1 & 0 \end{bmatrix}$$
(rows and columns indexed by states 0, 1, 2)
is irreducible, periodic and all its states are persistent.
- The number of customer complaints received daily by an organisation is given below :
| Day | Complaint |
|---|---|
| 1 | 2 |
| 2 | 3 |
| 3 | 0 |
| 4 | 1 |
| 5 | 9 |
| 6 | 2 |
| 7 | 0 |
| 8 | 0 |
| 9 | 4 |
| 10 | 2 |
| 11 | 0 |
| 12 | 7 |
| 13 | 0 |
| 14 | 2 |
| 15 | 4 |
Does it mean that the number of complaints is under statistical control ? Establish a control scheme for the future. Draw control chart.
- At a certain petrol pump, customers arrive in a Poisson process with an average time of 5 minutes between arrivals. The time intervals between services at the petrol pump follow exponential and as such the mean time taken to service a unit is 2 minutes. Then find the average number of customers in the queuing system and how long, on an average, a customer has to wait in the queue ?
- Write the applications of duality. Use Dual Simplex method to find the solution of the following LPP :
Minimize $Z = x_1 + 4x_2 + 3x_4$
subject to
$x_1 + 2x_2 - x_3 + x_4 \ge 3$
$-2x_1 - x_2 + 4x_3 + x_4 \ge 2$
$x_1, x_2, x_3, x_4 \ge 0$
- Explain seasonal component of a time series. Explain Ratio to Moving Average method for measurement of seasonal variation in a time series data.
- For the General Linear Model given by
$$\mathbf{Y} = X\boldsymbol{\beta} + \mathbf{U}$$
with assumptions $E(\mathbf{U}) = 0$, $E(\mathbf{UU}') = \sigma^2 I_n$, $X$ is a set of fixed numbers with $\rho(X) = k < n$, $\mathbf{B} = (\beta_1, \beta_2, \ldots \beta_k)'$ and $\mathbf{U} = (U_1, U_2, \ldots U_n)'$.
Obtain ordinary least square estimator $\hat{\boldsymbol{\beta}}$ of $\boldsymbol{\beta}$ and show that it is unbiased estimator of $\boldsymbol{\beta}$. Hence find $\mathrm{Var}(\hat{\boldsymbol{\beta}})$.
- Define Age-specific Fertility Rate and the Total Fertility Rate (TFR). Also define Gross Reproduction Rate (GRR).
- Describe the logistic growth model in population projection. State the situation when time series data would follow logistic law. Also state the limitation.
- What is measurement scale in statistics ? Also describe the types of measurement scales with example in each type.
- Define Autocorrelation of order $k$ and Correlogram. For an infinite series generated by the moving average of a random component with equal weights, the correlogram is given by
$$r_k = \begin{cases} 1 - \frac{k}{m} & \text{for } k \le m \\ 0 & \text{for } k > m \end{cases}.$$
- State the need of standardization of Crude Death Rate (CDR). Also compute and compare the standardized CDR of the populations A and B in the following table :
| Age group (in years) | Death rate per 1000 population: Population A | Death rate per 1000 population: Population B | Standard Population |
|---|---|---|---|
| 0 – 4 | 3.0 | 10.0 | 1000 |
| 5 – 14 | 2.8 | 6.0 | 1500 |
| 15 – 24 | 1.0 | 2.0 | 1100 |
| 25 – 34 | 0.8 | 2.0 | 900 |
| 35 – 44 | 2.0 | 3.0 | 800 |
| 45 – 59 | 4.0 | 6.5 | 500 |
| 60 – 74 | 10.0 | 15.0 | 400 |
| $\ge$ 75 | 25.0 | 30.0 | 300 |
- (i) Describe standardization of scale by Z-score and Min-Max scaling in psychometric measurements.
(ii) Describe percentile and find the percentile from the following data :
The scores obtained by 10 students are 38, 47, 49, 58, 60, 65, 70, 79, 80, 92. Using the percentile formula, calculate the percentile for score 70.
- Calculate Fisher's Ideal Index from the following data and verify that it satisfies time and factor reversal tests :
| Commodity | 2015-16 Price | 2015-16 Value | 2016-17 Price | 2016-17 Value |
|---|---|---|---|---|
| A | 10 | 100 | 12 | 96 |
| B | 8 | 96 | 8 | 104 |
| C | 12 | 144 | 15 | 120 |
| D | 20 | 300 | 25 | 250 |
| E | 5 | 40 | 8 | 64 |
| F | 2 | 20 | 4 | 24 |
- Describe various columns of a life table. Also, fill in the blanks in the portion of the table given below with question mark (?).
| Age (X) in years | $l_X$ | $d_X$ | $p_X$ | $q_X$ | $L_X$ | $T_X$ | $e^0_X$ |
|---|---|---|---|---|---|---|---|
| 4 | 100000 | 500 | ? | ? | ? | 5110000 | ? |
| 5 | ? | 400 | ? | ? | ? | ? | ? |
- Describe the present statistical system in India and the role of National Statistical Office.
- Prove the following relationship between the force of mortality ($\mu_X$) at age $X$ and the expectation of life ($e^0_X$) at age $X$.
$$\mu_X = \frac{1}{e^0_X}\left[1 + \frac{d}{dX} e^0_X\right].$$
- What are the consequences of multicollinearity and the consequences of auto correlated disturbances ? For the General linear model given by
$$\mathbf{Y} = X\boldsymbol{\beta} + \mathbf{U}, \text{ where } \boldsymbol{\beta} = (\beta_1, \beta_2, \ldots \beta_k)', \; \mathbf{U} = (U_1, U_2, \ldots U_n)'$$
with the assumption $E(\mathbf{U}) = 0$ and $E(\mathbf{UU}') = \sigma^2 \Omega$ where $\sigma^2$ is unknown but $\Omega$ is known symmetric positive definite matrix of order $n$.
Obtain the generalized least squares estimator $\hat{\mathbf{b}}$ of $\boldsymbol{\beta}$ with variance of $\hat{\mathbf{b}}$. Also obtain unbiased estimator of $\sigma^2$.
- What is the significance of cost of living index number ? The following table gives the per capita income and the cost of living index of a community. Calculate the real income taking into account the rise in the cost of living.
| Year | Cost of living index (Base 2001) | Per capita income (₹ in "000") per year |
|---|---|---|
| 2001 | 100 | 360 |
| 2002 | 104 | 400 |
| 2003 | 115 | 480 |
| 2004 | 160 | 520 |
| 2005 | 210 | 550 |
| 2006 | 260 | 590 |
| 2007 | 300 | 610 |
| 2008 | 320 | 650 |