,„,_ ,, ä i (All rights reserved) UNIVERSITY OF GHANA B.Sc. (Admin): SECOND SEMESTER EXAMINATIONS: 2018/2019 MAIN AND CITY CAMPUS ADMN 342/UGBS 302: RESEARCH METHODS (3 CREDITS) INSTRUCTIONS: Answer TWO uestions in Section A and All uestions in Sections B and C (The Quantitative Part). Answer Briefly but Clearly Each Part of a Question. Statistical Tables and Formulae Are Provided. Use TWO Searate Answer Booklets One for Section A and the Other for Sections B and C. TIME ALLOWED: THREE HOURS (3 HOURS) SECTION A: ANSWER TWO QUESTIONS IN THIS SECTION QUESTION 1 a) VVl1at is the importance of a research framework? b) Distinguish between a conceptual research framework and a theoretical research framework, c) Discuss tive factors which can influence the choice of an appropriate research topic in any research (5 marks) (5 marks) endeavour. (15 marks) QUESTION 2 a) A major importance of the literature review section of a study is to justify the need for that study. Examine how the literature review may be used to achieve this purpose. b) (15 marks) Agnes Dugan, a Level 300 HRNI student is struggling to put her references together in a research report. Guide Agnes in organising the reference sources below into a reference list using the APA referencing style. (10 marks) • Case for Building Real "The Business 23’°‘ Relationships with Customers," published in 2013 downloaded on June, 2013, from htts;//www.helscout.net/blo¤’relationshiPage 1 of8 EXAMINERS: DR. K. OHENE·ASARE, PROF. R. BOATENG & DR. J. OFORl—AMANFO • • The Business Case jbr Building Real Relationships with Customers published by Ciotti, G. (2013) and downloaded from hsz//www.helscout.net/blorelationshi/ on 23rd June 2013. A newspaper item headed "Roasted plantain business thrives" on page 11 of the Daily Graphic published on 1" February, 2014, by Steven Appiah, • A joumal article by Robert Duncombe and Richard Boateng with the title “Mobi1e phones and services in developing countries: a review of concepts, methods, financial issues, evidence and future research directions" published in the Third World Quarterly, 30(7), 12371258 in 2009. • A textbook from the library published by Milgrom, P., together with Roberts, J. in 2002, titled, 2“d Economics, Organization, and Management. edition. Englewood Cliffs, NJ: Prentice Hall QUESTION 3 a) There are multiple methods available to a researcher to administer a survey. Describe any four of the methods including in your description at least one advantage and one disadvantage of the method. (9 marks) b) Ama Martha intends to use observation as her primary data collection method to investigate the topic, ‘The practice of prostitution among teenage girls in the East Legon area of Accra". Identify four observation methods and demonstrate how Ama Martha can apply them in her research. (16 marks) SECTION B: ANSWER ALL QUESTIONS IN THIS SECTION (15 Marks) 1. Which of the following statements involve descriptive statistics as opposed to inferential statistics? a. The Alcohol and Firearms Department report that Ghana had 1,825 registered alcohol dealers b. 30% of the 380 magazine readers prefer double column articles. c. The FAA samples 425 traffic controllers so as to estimate the percent retiring due to job stress. d. From a sample of 350 players, a magazine reports that 23% of players’ parents did not play ball. 2. A variable within a range of real numbers is referred to as az a. continuous variable. b. categorical variable. c. discrete variable. d. parameter. 3. Ln a multiple regression model, there are four predictors and 60 observations. What are the degrees of freedom associated with the error sum of squares? a. 56 b. 4 c. 55 d. 3 Page 2 of8 EXAMINERS: DR. K. OHENE-ASARE, PROF, R. BOATENG & DR. J. OFORI·ANlANF0 4. In a multiple regression model, there are two regressors and 25 observations. If ESS = 0.0625 and TSS = 0.475, what is the value of the adjusted coefficient of detemiination? a. 0.8684 b. 0.1435 c. 0.9802 d. 0.8565 A student of UGBS as part of his long essay, would like to determine if there is a signiticant difference, at the 5% signiticance level, between the salaries of four government workers in and around the University of Ghana the salaries lecturers, nurses, administrators and police. The sample infomiation below shows in thousands . Use it to answer lecturers nurses administrators 7 3 3 3 4 ¤ 2 I 3 5. — 7 uestion 7 and 8. olice { 2 6 6 What is the value of the grand mean for testing the validity of this model? a. 5.49 b. 5.31 c. 3.67 d. 5 6. What is the value of the F statistic for testing the validity of this model? a. 7.7 b. 4.31 c, 5.7 d. 2.7 7. lf conducting a two-sided test of population means, unknown variance, at level of signiticance 0.05 based on a sample of size 20, the critical t—value is: a. 1.725 b. 2.093 c. 2.086 d. 1.729 8. When testing for the difference between the means of two independent populations with equal variances and with samples of sizes 111 Z 20 and 112 Z 20, what is the number ofdegrees of freedom? a. 39 b. 38 c. 20 d. 19 9. To investigate the effectiveness of a diet, a random sample of 16 female patients is drawn from a population of adult females using the diet. The weight of each individual in the sample is taken at the start and at the end of the diet. Assume that the population of differences in weight before a.nd Page 3 0f8 EXAMINERS: DR. K. OHENE—ASARE, PROF. R. BOATENG & DR. J. OFORI-AMANFO after the diet follows a normal distribution. Suppose the mean decrease in weights over all 16 subjects in the study is 4.0 pounds with the standard deviation of differences computed as 6.4 pounds. Let px - py = mean weight before the diet mean weight after the diet. In order to test if the diet is effective, what is the value of the test statistic? a. 2.5 b. 2.0 c. 1.8 d. 1.3 10. To investigate the effectiveness of a diet, a random sample of 16 female patients is drawn from a population of adult females using the diet. The weight of each individual in the sample is taken at the start and at the end of the diet. Assume that the population of differences in weight before and after the diet follows a normal distribution. Suppose the mean decrease i.n weights over all 16 subjects in the study is 4.0 pounds with the standard deviation of differences computed as 6.4 pounds. — py = mean weight before the diet - mean weight after the diet. In order to test if the diet is Let px effective, what is the appropriate critical value(s) at the 0.05 level of significance? a. 2.131 b. 2.120 c. 1.753 d. 1.746 11. Kcmprest, a real estate company is interested in identifying the factors that detemiine the price of a house. The company wants to run the following regression: Y= ,80 + ß1X1 + ß2X2 + ß3X3 + a where Y= price of the house in $1,000s, X} = number of bedrooms, X2 = square footage of living space, and X3 = number of miles from the beach. Taking a sample of 30 houses, the company runs a multiple regression and gets the following results: 9 = 123.2 + 4.59xj + 0.125x2 103.2, S51 = 2.13, $52 = 0.062, 51,3 = 4.17, R2 = 0.47, and E2 = 0.45 (adjusted). — 6.04x3, $50 = Determine the price that an individual has to pay for a 3 bedroom, 1,000 square foot house that is located three miles away from the beach. a. $201,422 b. $177,243 c. $243,850 d. $229,198 12. It is generally a good idea to compute R2, the adjusted R2, rather than just R2. This is done in order to a. avoid overestimating the importance of the independent variables* b. correct any problems that may arise from any of the model assumptions being violated c. avoid having a multiple regression model that contains too many variables. d. avoid conducting t tests for each independent variable e. harness the problem of autocorrelation 13. In a multiple regression y = 125+ 4'zoxl as Page 4 of 8 — 345% analysis, the least squares prediction equation is computed . Holding x, constant, if I increase xz by 2 units, what is the estimated EXAMINERS: DR. K. OHENE—ASARE, PROF. R. BOATENG & DR. J. OFORI-AMANFO change in the mean value of y? a. 1.25 b. -6.90 c. -5.65 cl. -1.45 e. 5.65 number of no more 14. To be classified as "safe," a certain factory is required to maintain an average than 2.8 minor accidents per week. A sample of 13 raridomly selected weeks produced a mean of we wish to test to see if 4,03 minor accidents and a standard deviation of 2.65 minor accidents. If the plant is “unsafe," what is the value of the appropriate test statistic? a. -1.67 b. -6.03 c. 6.03 d. 1.67 e. 1.23 15. Which of the following is NOT an assumption for the multiple regression model? a. Positive autocorrelation of error terms b. Normality of error terms c. Independence of error terms d. Constant variation of error terms e. At any combination of values of the independent variables, the error terms have a mean of 0 SECTION C ANSWER ALL QUESTIONS IN THIS SECTION (35 Marks) QUESTION 6 a) Carefully distinguish between multicollinearity and autocorrelation (4 marks) b) The Secretary of the Collegiate wants to determine how grade point average, GPA of a sample of students from University of Ghana depends on their high school GPA (HS), age of a student (A), achievement test score (AS), average number of lectures skipped each week (S), gender of a student (where M=1 if a student is male or 0 otherwise), whether or not a student owns a computer (where PC=1 if a student owns a personal computer or 0 otherwise), the means of transport to school (drive or use public transport, bicycle or walk; where D=1 if a student drives to campus or 0 otherwise, B=l if a student bicycles to campus or 0 otherwise); and the subject major of the student (finance, human resource, marketing and accounting; where F=1 if a student maj ors in finance or O otherwise, HR=l if a student majors in human resource or 0 otherwise, lVIR=1 if a student majors in marketing Page 5 0f8 EXAMINERS: DR. K. OHENE-ASARE, PROF. R. BOATENG & DR. J. OFORI-AMANFO or 0 otherwise). Use the scatterplot matrix, correlation matrix and durnrny regression output below to answer the questions that follow: i. Using just the scatterplot matrix, are the relationships between GPA and HS, between HS and A and between F and HR positive, negative or neutral? (6 marks) ii. Using the correlation matrix table, identify the three most strongly multicollinear variables and justify your reason for selecting these. Using the variance intlation factor, which variable(s) of the multicollinear pairs may be justitiably deleted? (6 marks) iii. Are the regression coefticients jointly signiticant? (2 marks) iv. Which independent variables are statistically sigriiticant at the 5% level? Interpret the coefticient of the variables marketing. (5 marks) v. Specify the regression model as you would in a research paper for a submission to a research journal. (3 marks) vi. What is the predicted GPA of a 20-year-old female student with a high school GPA of 3.0, an achievement score of 25, who skipped 2 lectures, owns a computer, drives and majors in human resource? (9 marks) SCATTERPLOT MATRIX (SELECTED VARIABLES) 25 GPA - ·· ,~=—·· 0.0 3.5 0.4 0.0 0.3 0.4 0.8 äi V; E HS 1EE FäiüäüäiS E II Ici F [il I 2S Q 2 HR2 @K S EH ä **2 2.5 3.5 Page 6 of8 20 24 28 0.0 0.4 0.8 0.0 0.4 0.8 EXAMINERS: DR. K. OI-IENE~ASARE, PROF. R. BOATENG & DR. J. OFORl—AMANFO CORRELATION MATRIX GPA HS AS A D PC M S GPA 1.00 HS 0.41 1.00 A -0.02 -0.26 1.00 AS 0.21 0.35 -0.08 1.00 s -0.26 -0.09 -0.08 0.12 1.00 M -0.08 -0.21 0.04 0.18 0.20 1.00 1.00 B F PC 0.22 0.04 -0.09 0.04 -0.21 -0.07 D -0.11 -0.19 0.27 -0.20 0.26 -0.08 0.02 1.00 0.08 0.14 -0.05 0.16 -0.13 0.13 -0.10 -0.38 1.00 0.08 -0.08 -0.11 1.00 B MR HR F 0.08 0.12 -0.22 0.18 0.06 0.04 HR 0.08 0.17 -0.49 0.08 0.06 0.05 -0.04 -0.11 0.07 -0.12 1.00 -0.05 0.02 0.05 0.08 0.01 -0.15 -0.79 MR -0.10 -0.19 0.37 -0.11 1.00 REGRESSION OUTPUT Regression Statistics Multiple R 0.53 RSquare 0.28 AdjustedR Square 0.22 Standard Error 0.33 Observations 141.00 ANOVA MS SS df 11.00 5.38 0.49 Residual 129.00 14.03 0.11 Total 140.00 19.41 Regression Coejficients StdError tStat F 4.50 P—va/ue Sig.F 0.00 LCl95% UCl95% WF Intercept 0.37 0.76 0.48 0.63 -1.13 1.87 HS 0.44 0.10 4.35 0.00 0.24 0.64 1-36 A 0.04 0.03 1.50 0.14 -0.01 0.10 1-75 1-32 A5 6 0.01 0.01 0.92 0.36 -0.01 0.03 -0.07 0.03 -2.42 0.02 -0.13 -0.01 1-28 -0.10 0.14 1-23 1-11 M 0.02 0.06 0.34 0.73 PC 0.14 0.06 2.29 0.02 0.02 0.26 0 0.01 0.08 0.13 0.90 -0.15 0.17 1-43 1-26 8 0.01 0.06 0.16 0.87 -0.12 0.14 F 0.16 0.23 0.70 0.49 -0.30 0.62 1-47 HR 0.08 0.12 0.64 0.62 -0.16 0.31 4-22 MR -0.01 0.10 -0.08 0.93 -0.21 0.20 3-45 Page 7 of 8 EXAMINERS: DR. K. OHENE-ASARE, PROF. R. BOATENG & DR. 1. OFORI-AMANFO 1 *1 1 1* 5. ‘d1"N-K-1,11 N=TSS df +1 8 2* 6. 3* RSS R2 =— TSS _MsR 4* LMSE - Xd 7.d=— n F1<—1,N—K,«z ,— utzpe R= 8.Ml’l R2 K ” N 1 ...;..9. |3itN_K_1’u><SE(ß) 10. -2R -1 - (1 - R 2 (N—K—l) = 11. x Zoizxi) N _- 1< 12. SSG 16. MSG? 20. Ul =Rl = K "· 12. ssW= E 2(x„ -2,)2 SSW 17. MS'W=¤ 21. U2 =RZ 25. Page 8 of8 — 18. 14. z=Lä 15. nä MSW RSS FK,N_K_1,a 19. MSR=T 22. U. +U2 =H1XI12 27. 23. taf=tN_La EXANIINERS: DR. K. OHENE—ASARE, PROF. R. BOATENG & DR. J. OFORI—AMANFO