Sie sind auf Seite 1von 11

Quantitative Techniques - I Topic wise unsolved questions from Previous Years Exam papers

EXERCISE 4 MEASURES OF ASSOCIATION : Conceptual understanding of Scatter plots, Line of Regression, Correlation calculation by product moment method and ranks method, Simple Regression, Plane of Regression and Multiple Regression. Test of Correlation Coefficient and Regression equations Q 1: PC World has given ratings for the top 15 notebook PCs. The performance score is a measure of how fast a PC can run a mix of common business applications in comparison to their baseline machine. The performance scores and the overall ratings for the 15 notebooks has been shown in the following table : Notebook Performance Score Overall Rating AMS Tech Roadster Compaq Armada Compaq Prosignia Dell Inspiron 3700 Dell Inspiron 7500 Dell Latitude Cpi Enpower ENP Gateway Solo HP Pavillion IBM Think Pad Micro Express Mocron TransPort NEC Versa SX Sceptre Soundx 5200 115 191 153 194 236 184 184 216 185 183 189 202 192 141 67 78 79 80 84 76 77 92 83 78 77 78 78 73

Sony VAIO 187 77 Compute the Karl Pearson's correlation Coefficient. What does the sample correlation coefficients tell about the relationship between the performance score and the overall rating? (PGDM End Term Exam 2007) (10 marks) Q 2: A firm administers a test to sales trainees before they go into the field. The management firm is interested in determining the relationship between the test scores and the sales made by the trainees at the end of one year in the field. The following data were collected for 10 sales personnel who have been in the field one year.

Salesperson Number 1 2 3 4 5 6 7 8 9

Test score(T) 2.6 3.7 2.4 4.5 2.6 5.0 2.8 3.0 4.0

No. of units sold (S) 95 140 85 180 100 195 115 136 175

10 3.4 150 Find the regression equation and predict the number of units sold when the test score is 11.5. (PGDM End Term Exam 2007) (10 marks) Q 3: Sales of major appliances vary with the new housing market : when new home sales are good, so are the sales of dishwasher, washing machines, drillers, and refrigerators. A trade association complied the following historical data(in thousands of units) on major appliances sales and housing starts: Housing Starts(thousands) Appliances Sales(thousands) 2.0 2.5 3.2 3.6 3.3 4.0 4.2 4.6 4.8 5.0 5.0 6.0 7.0 7.2 7.7 8.4 9.0 9.7

5.0 10.0 Develop an equation for the relationship between appliances sales and housing starts and estimate the value of appliances sales when the Housing Starts is 6.0 (PGDM End Term Exam 2007) (10 marks) Q 4: Find out Spearman's coefficient of correlation between the two kinds of assessments of postgraduate student's performance in a college: Name of Students A B C D E F G H I Internal Assessment (out of 100 marks) External Assessment (out of 100 marks) 51 49 63 72 73 74 46 44 50 60 47 36 60 58 66 50 30 35 (PGDM End Term Exam 2007) (10 marks)

Q 5: Sam Spade, owner and general manager of the Campus Stationery Store, is concerned about the sales behaviour of a compact cassette tape recorder sold at the store. He realizes that there are many factors that might help explain sales, but believes that advertising and price are major determinants. Sam has collected the following data: Sales (units sold) Advertising (no. of ads) Price ($) 33 61 70 82 17 3 6 10 13 9 125 115 140 130 145

24 6 140 (a) Calculate the regression equation to predict sales from advertising and price (b) If advertising is 7 and price $ 132, what sales would you predict. (c) Calculate the Standard error and interpret it. (d) Test the data with F- test (ANOVA Table) (PGDM HR End Term Exam 2008) (4 x 3 = 12) Q 6: The following are salary and age data for the 10 Senior Managers of a company. With 5% level of significance does rank correlation of age and salary suggest that older persons get higher salaries? Does coefficient of determination has any importance in the given situation. Salary 67000 60000 57500 59500 50000 55000 59500 63000 69500 72000 38 28 34 (PGDM HR End Term Exam 2008) (10 marks) Q 7: Bank of Lincoln is interested in reducing the amount of time people spend waiting to see a personal banker. The bank is interested in the relationship between waiting time (Y) in minutes and number of bankers on duty (X). Customers were randomly selected with the data given below : X 2 3 5 4 2 6 1 3 4 3 3 2 4 Y 12.8 11.3 3.2 6.4 11.6 3.2 8.7 10.5 8.2 11.3 9.4 12.8 8.2 (a) Calculate the coefficient of determination and interpret it. (b) Since waiting time of the customers were ascertained by picking them on random basis, test the data with the help of the tabulated values of 't' as given below at 5% level of significance : (PGDM HR End Term Exam 2008) (10 marks) Q 8: A financial consultant gathered the following information relating to the return from the security / share which he had advised to his client vis-a-vis the stock market return. The returns pertains to past 8 months and are in terms of percentages. Month 1 2 3 4 5 6 7 8 Stock Market Share 12 10 14 15 13 18 10 14 9 16 13 16 14 18 7 4 Age 29 25 30 35 27 31 32

(i) Develop an estimating model that best describes the data and estimate the return from the security if market return is 19%? (ii) Find the coefficient of Determination and interpret it. (iii) Test the data with the help of the tabulated values of t' as given below at 5% level of significance : d. f 1 2 3 4 5 6 7 8 Values 12.706 4.303 3.182 2.776 2.571 2.447 2.365 2.306 (iv) Comment on the performance of the financial advisor keeping in mind the volatility (PGDM Mid Term Exam 2008) (4 x 5 = 20) Q 9: Impact of Selling Price and Sales Promotion Expenses on the Market Share of Shampoo. The CEO of a firm manufacturing a wide variety of consumer non-durable products was recently concerned with increasing the market share of one of its major products, namely, a particular brand of shampoo sold in 500 ml bottles. The product was manufactured in collaboration with a foreign company and its target market was high income households in fifteen major cities of the country. It was launched about two and a half years back. Data collected on its market share indicated considerable variation from one quarter to another. In order to predict the market share for the next couple of quarters, the CEO and his senior colleagues carried out a brainstorming exercise in which several cause variables were identified. It was noted that some of these were measurable / countable and others were not. While the firm's selling price and expenditure on sales promotion and R & D were measurable in appropriate monetary units, the number of distribution channels and the size of sales force were countable. It was also observed that the number of major competitors and their selling prices had a bearing on the firm's market share. The brainstorming exercise further revealed that factors like the firm's brand image, customer satisfaction with its products, major competitor's brand image, government policies on important and taxation etc also had an impact on its market share. The results of the exercise are shown in the following table : Nature of Control Measurable / Countable Within firm's control 1. Firm's selling price 2. Firm's expenditure 3.Customer satisfaction 4. No of Distribution Channels 5. Size of sales force 1. Number of major competitors 2. Major competitor's selling price

Non Measurable / Non Countable 1. Firm's brand image

Beyond firm's control

1. Competitor's brand image 2. Government policies

While the firm's brand image was difficult to measure, a customer satisfaction survey would provide data for the quantification of the level of customer satisfaction. The management, however, decided not to undertake such a survey immediately. In order to predict the market share of shampoo, it focused on those cause variables for which the data were readily available. The choice narrowed down to two cause variables, namely, (i) the firm's selling price and (ii) its expenditure on sales promotion Data Collected on the market share of the shampoo along with its selling price and expenditure on sales promotion during the past ten quarters are shown in the table given below:

Quarter 1 2 3 4 5 6 7 8 9

Market (%) 26 22 31 35 29 22 38 30 35

Share Selling (Rs) 102 108 105 98 107 112 102 108 112

price Expenditure on Sales Promotion (Rs Millions) 10.8 9.6 12.9 13.8 12.2 10.0 15.6 14.2 19.8

10 42 115 20.3 (a) Find out the multiple regression equation and estimate the market share if the price of a bottle of shampoo is fixed at Rs 100 and the firm spends Rs 20 million in sales promotion in quarter 11. Give the deviation in the forecasted value. (b) By what percentage does the market share of shampoo (i) fall for every one rupee increase in its selling price and (ii) increase for every one million rupees increase in sales promotional expenses? (c) Discuss the effect of multi-collinearity (if any) in the given situation. (d) Test the multiple regression model at 5% level of significance. (PGDM End Term Exam 2008) (4 x 4 = 16) Q 10: Answer the following Objective Type questions (a) Under the least squares method, the best fitting regression line is the line (i) on which the maximum number of data points lie (ii) which minimizes the sum of the squares of the vertical distance from each plotted point to the line (iii) which maximizes the sum of the squares of the vertical distance from each plotted to the line on which the regression (iv) Which tries to give importance to Error values (v) None of the above (b) If SSR and SST are equal, then what will be the strength of relationship _________ (c) The assumptions mentioned in the regression method of least squares for the ascertainment of the regression line can explain the: (i) Cedasticity perfectly (ii) Cedasticity partially (iii) Homos cedasticity correctly (iv) Hetros cedasticity correctly (v) None of the above (d) Which of the following is true regarding a security with beta equal to 0.875 in a bearish market: (i) The price of the security will increase more than the market performance

(ii) The price of the security will increase equal to the market performance (iii) The price of security will decrease more than the market movement (iv The prices of security will decrease but less than the market increase (v) None of the above (e) Which of the following is not true with regard to the simple linear regression (i) There may be other factors that may cause changes in both the dependent and the independent variables (ii) There is one independent variable and one dependent variable (iii) The relationship between the independent and dependent variables is a relationship of association (iv) There are no errors involved when we estimate the regression line using simple regression (v) None of the above (f) In a scatter diagram, if the plotted points lie on a straight line parallel to the Y-axis, then (i) perfectly +ve correlation exists (ii) perfectly -ve correlation exists (iii) Linear relationship exists (iv) No relationship exists (v) None of the above (g) If the value of the standard error of the estimate is zero, then (i) The observations are more scattered from the regression line (ii) The observations lie closer to the regression line (iii) The observations lie above the regression line (iv) There is no variation from the regression line (v) None of the above (h) Beta is a measurement of : L1 -> Non Diversifiable risk; L2 -> Systematic risk L3 -> Diversifiable risk (i) L1 and L2 (ii) L1 and L3 (iii) L2 and L3 (iv) All the L1 , L2 , L3 (v) None of the above (i) Which of the following is a false statement about the Product Moment Correlation Coefficient: (i) It assumes a linear relationship between variable (ii) The value of variable gets affected by extreme values (iii) It gives one value to ascertain the nature of the relationship (iv) It can return any numeric value independent of sign (v) None of the above (j) Select the ODD combination (i) Weight of diamond and its cost (ii) Temperature and the usage of woolen clothes (iii) Level of production and health benefits given to workers (iv) Rainfall and production (v) None of the above

(k) With the help of the least squares method, we estimate (i) X-intercept (ii) Y-intercept (iii) Population Regression Line (iv) Scatter diagrams (v) None of the above (l) Which of the following is NOT an assumption of CVP analysis (i) All the costs can be segregated into fixed and variable costs (ii) All the business entities are either a profit center or a cost center (iii) There can be only two type of costs (iv) Fixed cost always gets recovered automatically (v) None of the above (m) There are 12 employees in two departments of an organization. An employee performance survey was conducted for both the departments and employees of both the departments were ranked on the basis of their individual scores. The summation of squares of differences in ranks is 91. What is the rank correlation coefficient? (i) 0.681 (ii) 0.868 (iii) 0.318 (iv) 0.131 (v) None of the above (n) _______________ is used to measure how well the regression line explains the variation of the dependent variable (o) Suppose the fraction of variation in Y that is unexplained by the independent variable is X is . Then r square is : (i) (ii) (iii) 15/16 (iv) 18/60 (v) None of the above (p) If Y = a + bX, the sample regression line, and Y = A + B X, the true unknown population regression equation, are equivalent, then the following must be true (i) The estimation equation is a perfect estimator of the dependent variable (ii) All the data points are on the regression line (iii) r square equals to 1 (iv) All the above (v) None of the above (q) Under the least squares method, the best fitting regression line is the line (i) on which the maximum number of data points lie (ii) which minimizes the sum of the squares of the vertical distance from each plotted point to the line (iii) which maximizes the sum of the squares of the vertical distance from each plotted to the line on which the regression (iv) Which tries to give importance to Error values (v) None of the above

Q 11: Dr Jhamjham has recently taken over a small firm. This firm is in the business of manufacture and distribution of plastic bottles with the brand name 'Quench Pet Bottles'. Dr Jhamjhan has reviewed the advertisement expenses of the firm and has ascertained that the advertisement budget is on the higher side. Dr Jhamjham wants to cut down the cost of advertisement and is contemplating to go ahead with only one mode of advertisement out of the two currently in use viz. Hoarding (Billboards) and Newspaper. Dr Jhamjham wants to take an informed decisions as lot many companies do buy advertising without considering its effect. However, the marketing manager is trying to make the case that you have to spend money to make money. Spending on hoarding advertisements or the newspaper advertisement, in the manager's opinion, has a direct result on sales. There are records for 7 months in the following table: Monthly Expenditure on Hoardings (in Rs ' 000) Monthly Expenditure on Newspaper Ads. (in Rs ' 000) Monthly Sales Revenue (in Rs ' Lakhs) 25 16 42 34 10 21 19 20 09 30 15 10 11 10 34 14 48 32 26 29 20

(a) Develop an estimating equations that best describes these data and comment on the mode of advertisement that has a better relationship with the Sales Revenue? (b) If the company fixes the advertisement budget at Rs 28000, which method of advertisement will be preferable? (c) Test the authenticity of the data at 5% level of significance. (d) If the confidence intervals can be calculated with the help of the following formula: Confidence Interval = y (t 0.05 ) x (Se)

(where y --> Y Cap ; (t 0.05 ) --> Tabulated t value at 5% ; Se -> Standard Error) Find out the confidence intervals for above set of data and interpret the results. (PGDM End Term Exam 2009) (4 x 5 = 20 Marks) Q 12: A company manufactures two products, E1 and E2. The sales (in units) and profits for the last five months are given in the following table: Month 1 2 3 4 5 E1 12000 14000 10000 14000 16000 E2 16000 13000 11000 8000 10000 Profits (in rupees '000) 192 87 - 181 -216 - 08

(a) Find out the fixed cost of the company (b) The contribution per unit for each of the product (c) Comment on the fixed cost component of the company and the marginal cost for each product (d) Test the data with F-tables (PGDM End Term Exam 2009)

(4 x 4 = 16 Marks) Q 13: Rimzhim a PGDM student as part of the Summer Internship project (SIP) has joined the Treasury Department of a large Public Sector Bank. The Treasury Department of the banks invests the money that they have, in the various Government Bonds which happens to be one of the several Government Securities (G-Secs). Herein, Rimzhim got attached to the 'work group' that was actively involved in purchasing government bonds. One of the main task of this 'work group' was to forecast the interest rate of G-Sec bonds based on the various Macroeconomic factors and US Treasury Yields for its decision making process, whether to invest in these securities or not? Rimzhim collected the data (refer Table 2) related to the Indian 10 year bond yield and US 10 year bond rate for the financial year 2009-2010. After having collected the information, Rimzhim is totally puzzled with lot of doubts that have arisen in her mind. Please help her out in clearing these doubts: (a) She wants to ascertain whether any relationship exists between the US 10 year bond rate and the Indian 10 year bond yield or not? (b) Should we measure the strength the relationship? If yes! Measure the strength. (c) How to have a trust on the legitimacy of the data used to measure this relationship? Help Rimzhim in testing out the data at 5% level of significance. (d) What inferences can be drawn from the above three parts {part (a) to part (c)} (PGDM Mid Exam 2010) (3+3+3+1 = 10 marks) Table 2 : Indian and US bonds 10 years bond data for financial year 2009-10 Month Apr-09 May-09 Jun-09 Jul-09 Aug-09 Sept-09 Oct-09 Nov-09 Dec-09 Jan-10 Feb-10 Mar-10 Indian 10 yr bond yield 6.24 6.71 7.00 7.00 7.30 7.17 7.30 7.24 7.69 7.54 7.82 7.82 US 10 yr bond rate 3.12 3.50 3.54 3.48 3.40 3.31 3.40 3.20 3.84 3.60 3.62 3.83

Q 14: Answer the following questions. Questions (a) to (e) carry 1 mark each. (a) What is a ARIMA model? (b) What is Hetros-Kedasticity in multi-variate data analysis? (c) Explain the concepts of Collinearity and Multi-Collinearity. (d) Why the value of Y-intercept in CVP analysis has +ve sign for TC(x) while it has -ve sign for TP(x)? What does it signify. (e) What is meant by structural relationship between variables. Give illustrative examples. (PGDM End Exam 2010)

Q 15: An expert witness in a case of alleged racial discrimination in a state university school of nursing introduced a regression of the determinants of Salary of each professor for each year during an 8-year period (n = 423) with the following results, with dependent variable Year (year in which the salary was observed) and predictors Year Hire (year when the individual was hired), Race (1 if individual is black, 0 otherwise), and Rank (1 if individual is an assistant professor, 0 otherwise). Interpret the results. Variable Intercept Year YearHire Race Rank R square = 0.811 Coefficient - 3 816 521 1 948 - 826 - 2 093 - 6 438 Adj R Square = 0.809 (PGDM End Exam 2010) (10 Marks) Q 16: Professor Tamtam's Exploratory Research on Divorces and Suicides in few major cities Professor Tamtam was returning back to his home town after the completion of an official trip abroad. He reached the airport quite early and checked in his baggage. When he became free from the baggage and got the boarding pass in his hand, he realized that the time left for the departure of the flight is nearly five hours. Prof. Tamtam decided to roam around in the huge airport complex. He was passing through so many shops and retail outlets with sparkle of light everywhere. Then he entered a small restaurant and ordered food for himself. Since there was enough time in his hand, he started watching the movie which was coming on the television kept in the restaurant. It was a HORROR movie which was showing some a person committing suicide. The restaurant owner possibly didn't liked the movie and tuned in to another movie, this movie was related to a court case wherein the Judge was pronouncing verdict on a divorce case. In between Prof. Tamtam finished his food and came out of the restaurant. When Prof Tamtam returned back to his hometown he collected data related to the suicide rate, the size of population and the yearly divorce rate in eight major cities of the country as given below : (All figures are in Lakhs) City Population Divorce Rate Suicide Rate 1 2 3 4 5 6 7 8 1358 2840 2698 592 7950 646 4400 1266 60.8 68.2 34.4 53.68 58.2 37.4 65.2 65.0 23.2 32.2 18.6 18.2 16.8 15.4 22.6 16.8 T - 29.4 29.8 - 5.5 - 4.3 - 22.3

(a) Fit a most suitable mathematical model on the above data. Predict the value of the Dependent variable taking 100 as the value of all the independent variables. (b) Calculate the value of Coefficient of Multiple Determination and its Adjusted value. (c) Calculate the Standard Error (d) Test the above values through ANOVA table. (PGDM End Exam 2010) (4 x 2 = 10 Marks)

Das könnte Ihnen auch gefallen