Chapter-4-part-1-and-2 (1).pdf

Learning Outcomes After studying this chapter, the student should be able to: 1) Determine what is the right research design for the study; 2) Learn how to sample respondents; 3) Know what is the appropriate sample size; 4) Identify what is the appropriate research instrument; 5) Learn how to validate the survey questionnaire; Learning Outcomes After studying this chapter, the student should be able to: 6) Develop a Cover Letter; 7) Develop a Close-Ended Questions, Scales, Rating, and Ranking Questions 8) Determine the Ethical Issues in Business Research; and, 9) Learn how to report the statistical treatment. BUSINESS RESEA RCH WRITING: PART 3 Research Methodology is a detailed outline of how an investigation will take place. Research Methodology typically include how data are to be collected, what instruments will be employed, how the instruments will be used, and the intended means for analyzing data collected. Research Methodology comprises the following components: 1) Research Design 2) Research Locale 3) Sampling Plan (Population and Sample) 4) Research Instrument 5) Data Collection 6) Statistical Treatment of Data 7) Ethical Consideration refers to the overall strategy that you choose to integrate the different components of the study in a coherent and logical way, thereby, ensuring you will effectively address the research problem; it constitutes the blueprint for the collection, measurement, and analysis of data. a strategy for answering your research question using empirical data. 4 Types of Data: 1. Nominal Data - also known as categorical data, represent categories or labels with no inherent order or ranking ( e.g., color, gender) 2. Ordinal Data - represents categories with a meaningful order or ranking, but the intervals between categories are not well- defined or equal (e.g., educational levels, customer satisfaction ratings). 3. Interval Data - present values with a meaningful order where the intervals between values are equal. However, there is no true zero point, and ratios between values are not meaningful (e.g., IQ scores, Temperature). 4. Ratio Data - represent values with a meaningful order, equal intervals, and a true zero point, where a value of zero indicates the absence of the attribute being measured (e.g., weight, height, income) EXERCISE 1. The course of the students in a statistics class. a. Nominal b. Ordinal c. Interval d. Ratio EXERCISE 2. The amount of gasoline pumped by the next 10 customers at the Shell station. a. Nominal b. Ordinal c. Interval d. Ratio EXERCISE 3. The temperature in the classroom. a. Nominal b. Ordinal c. Interval d. Ratio EXERCISE 4. The socioeconomic status (low, middle, high) of the graduate students. a. Nominal b. Ordinal c. Interval d. Ratio AREAS OF STATISTICS Descriptive statistics – Methods of organizing, summarizing, and presenting data in an informative way EXAMPLES: Level of intelligence Level of service quality Level of temperature Inferential statistics – The methods used to determine something about a population on the basis of a sample Population –The entire set of individuals or objects of interest or the measurements obtained from all individuals or objects of interest Sample – A portion, or part, of the population of interest Draw conclusions about a population based on a sample ESTABLISHING FOCUS EXERCISE 1. What is the extent of the start-up’s marketing strategy in terms of product, price, place, and promotion? 2. How does the start-up’s financial performance measure up in terms of profitability, return on investment (ROI), and return on equity (ROE)? 3. Is there a significant relationship between the start-up’s marketing strategy and its financial performance? a. Descriptive Statistics b. Inferential Statistics TYPES OF VARIABLES EXERCISE 1. The marital status of the students in a statistics class. a. Qualitative b. Quantitative c. Polynomic d. Dichotomic e. Discrete f. Continuous EXERCISE 2. The amount of gasoline pumped by the next 10 customers at the Shell station. a. Qualitative b. Quantitative c. Polynomic d. Dichotomic e. Discrete f. Continuous EXERCISE 3. The programs offered in the business administration department. a. Qualitative b. Quantitative c. Polynomic d. Dichotomic e. Discrete f. Continuous A college dean is interested in learning about the average age of faculty. Identify the basic terms in this situation. The population All the faculty members at the college A sample Any subset of that population. For example, we might select 10 faculty members and determine their age. The variable is the “age” of each faculty member. The data 30 What is the right research design for the study? For most studies, the descriptive research design is the right choice. Even if the research would entail a compli cated research design, there is still the element of descriptive research that would be needed- be it an academic research (basic business research) or applied business research. Descriptive Resear ch would just need minimal explanation and there would be no statistical testing (e.g. hypothesis testing) What is the right research design for the study? If the problem would require measurement that cannot be covered by the descriptive research design, then the research designs could be used: correlational research design an d causal research design. The difficulty level of these research designs increases as the skills of the researchers in using them are also expected to be developed. Some tools of correlational research design are to be discussed in this course. The causal research design is beyond our scope and it is normally tackled in the doctoral study program, not at the undergraduate level. Guidelines for using Correlational Research Tools: 1. If the problem involves hypothesis testing, decide on: a. Hypothesis of relationships (between variables) - use Pearson R correlation (for parametric data), or Kendall's tau B, Spearman's rho or chi -square (for non- parametric data). This is discussed in Ch apt er 5. Guidelines for using Correlational Research Tools: b. Hypothesis of difference - use: b.1. Paired t- test - for comparing a pair of variables (interval scales or ordinal) b.2 Independent Sa mp le t -test - for comparing a variable (interval or ratio scaled) with a nominal variable with two categories only. This is discussed in Ch apt er 5; or b.3 O ne-Way ANOVA - for comparing a variable (interval or ratio scaled) with a nominal variable with at least three or more categories. Guidelines for using Correlational Research Tools: 2. If the problem is to know which factors/variables are valued by the respondents, then the right technique is a multivariate technique called factor analysis. If the researcher would like to know which variables are important an d the unimportant ones will be eliminated (data reduction), then the right technique is still Factor Analysis. This is discussed extensively in Chapter 7. Guidelines for using Correlational Research Tools: 3. If the problem is to know which of the variables (called independent variables) would explain or predict a particular variable (called depen dent variable), then the right technique is another multivariate technique called multiple regression analysis. This is discussed extensively in Chapter 8. 4. If the problem is to know how to group (segment) the respondents based on their preferences and profile them by cross- tabulating their demographic data, then the right technique is cluster analysis. Cluster Analysis is not covered in this course. RESEARCH LOCALE For research locale, researcher should describe briefly the place of the study with a supported map. Usually, it is required to present two maps: Philippines ma p and local ma p (with an arrow pointing to the specific locale in the Philippines map) SAMPLING PLAN Population and Sample How should the respondents be properly sampled? Students and researchers have to decide on the right sample size. Som e schools have standar d sample size for the students to follow or adhere to. Sample sizes are based on the m ar gin of error an d confidence level. For example, under graduate students are expected to have the fam ous 100 sample size (based on 9.78% m ar gin of error an d 68.3% confidence level); for the gr ad uate school students, it is 377 (based on 5 % m ar gin of error an d 95% confidence level). Try using Raosoft sample calculator (www.raosoft.com). In fact, when you are done with your sampling, you can now measure your actual sample size with Raosoft calculator and see the final margin of error and confidence level easily. SAMPLING PLAN Population a n d S a m p l e What is the appropriate sample size? As to the appropriate sam ple size, it depends on the school, the panel of examiners, or the contr acted researcher, It should, however, be 100 or more. The problem with a bi g sa mpl e size is the cost an d time involved: it be com es so expensive and it requires a m u ch longer period to gat her the data. SAMPLING PLAN What is preferred - random sampli ng or purposive sampling? If the objective of the study is to generalize the result acr oss the population, then use random sampling. If the objective of the study is to determine the ta rget market for a particular organization and is not necessary to generalize it acr oss the population ( because the purpose is like a c as e study), then use purposive sampling. Purposive Sam pli ng starts by qualifying the respondents first, then selecting them once qualified by the quota method. For example, a c o mp a n y wants to know its target market’s preference for its new product. Its current customers are co mpo sed of Millennial a n d Generation X a n d are generally female. To conduc t sampling, it must qualify the respondents first b as ed on generation a g e (Millennial born: 1981-1999; Generation X, born: 1965-1980) a n d sex (female). SAMPLING PLAN Note that convenience sa mp ling is not covered in the discussion here a n d it is not appropriate for research. Convenience sa mp ling is gathering d a t a b as ed on whoever is available during the time of survey, regardless of qualification a n d of sa mp ling frame. Type of Ran dom Sampl ing 1. Simple R a n d o m S a mp li ng – if the population is known 2. Stratified R a n d o m S a mp li ng – if the population is known 3. R a n d o m S a mp li ng B a sed on Poisson Distribution – if the population is not known SIMPLE RANDOM SAMPLING To sa mpl e the population using simple r an dom sampling, the researcher h a s to have a sa mp ling frame. A sampl ing frame is the list of the target population (especially if the target population is not large enough). SAMPLING PLAN SIMPLE RANDOM SAMPLING Fr om the list of respondents included in the sa mp ling frame, the researcher will draw the sa mpl e randomly. A go od randomizer is available on the Internet. Just g o to www.randomizer.org. It h a s a n instruction on how one c a n draw a sa mpl e from the target population. For example, If a student researcher would like to sa mpl e the target student population of the Department of Business Administration, he/she h a s to secure the sa mp ling frame first - the list of students enrolled a t the Department of Business Administration. The best source of this is the Registrar's Office. Upon proper request, a student c a n obtain the alphabetical list of students. To convert this list in a sa mp ling frame, the students on the list should be numbered (e.g. if there are 60 0 students, number the students from 1 to 60 0 b as ed on their alphabetical arrangement). SAMPLING PLAN SIMPLE RANDOM SAMPLING Then, once the sa mp ling formula is determined (let us a ssu me 100 respondents), draw the 100 respondents using the randomizer. For example, the first number drawn is 14. B a sed on this number, g o to the sa mp ling frame a n d identify the 14th student a n d m ar k the student a s respondent 1. Continue with the process until you get a n d label the 100 students. However, a n additional 20 students (20% allowan ce for no n-participation) should be drawn also; in c as e some students in the list would refuse to participate, then there is a buffer. SAMPLING PLAN STRATIFIED RANDOM SAMPLING Another way to r an dom sa mp ling is through stratified r an dom sampling. Here, if the target population h a s a natural grouping a n d some groups m a y have more respondents tha n the other groups, then the right r an dom sa mp ling a pp r o ac h is to stratify the sa mpl e b as ed on the population distribution. A stratum (plural strata) refers to a subset (part) of the population (entire collection of items under consideration) which is being sampled. For example, if we will use the generational a g e a s basis for stratification, then let us identify the population for e a c h group. In D a va o City: Millennials (575,152 or 33.3% a s of 2017); Generation X (248,714 or 14.4% a s of 2017); a n d B a b y Boomers (126,084 or 7.3% a s of 2017). If we use the three strata for sa mp ling purposes ( assu ming the sa mpl e size is 377), then the stratified distribution is a s follows: Strata Population Computation Sample Size Millennial 575,152 (575,152/949,950) x 377 228 Generation X 248,714 (248,714/949,950) x 377 99 Baby Boomers 126,084 (126,084/949,950) x 377 50 Total 949,950 377 On c e the stratified distribution a n d the s am pl e size are computed, e ac h stratum should h ave the respo ndents rand omly selected. SAMPLING PLAN POI SSO N DISTRIBUTION - is a discrete distribution that measures the probability of a given number of events happening in a specified time period. In some cases, the population is not known. If this is the case, c a n we still do r a n d om s am pl i n g without an y s a m pl i n g frame? The answer is yes. Just use Poisson distribution a n d the need for a sa mp ling frame is substituted. For example, A researcher wanted to study the mall shoppers in D a va o City. However, there is no list of mall shoppers in D a va o City to use a s a sa mp ling frame. So, the researcher h a s to g o to the mall a n d intercept the shoppers a s they g o on shopping. How could the respondents be randomly selected? Prior to go ing to the malls, the researcher h a s a guide for selecting the respondents b as ed on the selected da y s a n d selected hours where the shoppers most likely frequent in the mall. S ee next slide. SAMPLING PLAN Guide Sampling Procedure per Mall Time/Day* Wednesday Friday Saturday Sunday Total 1-2:00 pm 1 1 1 1 4 2-3:00 pm 1 1 1 1 4 3-4:00 pm 1 1 1 1 4 4-5:00 pm 1 1 1 1 4 5-6:00 pm 1 1 1 1 4 6-7:00 pm 1 1 1 1 4 Total 6 6 6 6 24 *Based on the study (Te, 2007) that the shoppers prefer to shop in the afternoon, late afternoon, and early evening during Wednesdays, Fridays, Saturdays, and Sundays. SAMPLING PLAN POI SSO N DISTRIBUTION The enumerator (research assistant) will be guided by the sa mp ling procedure in selecting the respondents randomly. Here, the enumerator will wait a t the specific mall entrance a n d a pp r o ac h the shopper for survey questionnaire participation a t the specific time. If the shopper declines, then the enumerator will a pp r oa ch the next shopper, a n d another shopper, until there is a taker for a particular time guide. O nc e there is a taker who is willing to fill up the questionnaire, the enumerator will thank the respondent a n d wait for the next period (another period b as ed on the guide). but next time, the enumerator will move to another entrance (to stimulate randomness) a n d select the second respondent. SAMPLING PLAN POI SSO N DISTRIBUTION The sa mp ling procedure would take several da y s until all the respondents in the guide are ac cou nted for; it c a n even be done simultaneously through the different malls a t the s a m e time with the help of more enumerators. This process of r an dom sa mp ling is b as ed on Poisson distribution a n d mall intercept. END OF PART 1 OF CHAPTER 4 Next Topic: PART 2 of CH AP T E R 4 R E SE A R CH ME T HOD OL OGY AN D ST ATIST ICA L T OOL CHAPTER 4 PART 2 RESEARCH METHODOLOGY AND STATISTICAL TOOLS P r e pa r e d by: Prof. Millisa E. Sramo sin g- Equi t, M B A LEARNING Ident ify w h a t is t he appropr iat e 4 res ea rc h i ns t r um e nt OUTCOMES: 5 L e a rn h o w to val idat e t he survey quest ionnair e 6 D e v el o p a Co ve r Let ter D e v el o p a Cl ose -E n d e d Ques tions, 7 Sc ales , R at i ng, a n d R a n k i n g Q ues t ions LEARNING D e t e r m i n e t he et hi cal is sues in 8 bu s in es s research; a n d OUTCOMES: 9 L e a rn h o w to report t he statistical i ns t r um e nt RESEARCH INSTRUMENT W h a t is t h e ap p r o pr i at e r e s ea r ch However, in s o m e cases, t he d e pt h int erview i n s t r u m e n t for g a t h e r i n g w ou l d provi de s o m e i ns ig ht s t hat m a y not b e c a pt ur e d in t he surv ey quest ionnaire, a n d q ua n t it a t iv e r e s e ar ch d at a ? t h us e n h a n c e t he study. In genera l, quant it at ive res ea rc h w ou l d n e e d just T he res ea rc h i ns t r u m ent s ho ul d b e d es i g ne d a s u r v e y q u e s t i o n n a i r e a s t he res earc h to a ddr es s all t he ques t i ons in t he p ro bl e m ins tr um ent. st at ement , and no unn ec es s ar y quest ion/i tem s ho ul d b e inserted. In s o m e cases, d e p t h i n t er vi e w is a ppl ie d to c o m p l e m e n t t he surv ey questionnaire. A s m u c h as possible, t he res ea rc h i ns t ru m ent que s t ion a n d ins tr uc t ion s ho ul d b e eas y to T here is however, s o m e p ro b l em s w h e n t he t wo follow. res ea rc h i ns t r u m ent s are u s e d in o ne s t ud y - t he quali ta ti ve resul t ( u s i n g d e p t h int erview) m a y If t here is a n e e d to translat e it in local c on t ra di c t wi t h t he quant it at ive result ( u s in g vernacular, t h e n ha v e a s epa rat e version for it s ur ve y quest ionnaire). to serve t hos e t hat m a y c o m p r e h e n d it better. RESEARCH INSTRUMENT W h at is the appropriate research instr ument for gat he rin g quantitative rese arch data? A s m u c h as possible, a n s we r i ng t he res earc h i ns t r um e nt (s urvey quest ionnair e) s ho ul d not t a k e m or e t h a n 15 m inut es ; and, if possible, t he filling u p t he surv ey ques t ionnai re s ho ul d b e T he p r ob l e m wi t h s t a nda rdi z ed ques t i ons is s uper vi sed by t he en um e ra t or to m i ni m i z e t hat it m i g h t not fully a ddr es s t he res earc h m i s s i ng da t a or err oneous entries. p ro bl e m s as t he c ont ext it ( st anda rdized) wa s de ve l oped wi t h m a y b e dif ferent f r om t he If t he que s t ion s in t he surv ey ques t ionnai re are d e s i g n of t he researcher. a d o p t e d f r om a n exi st i ng st udy, it is c all ed a When y ou a do pt a s t anda rdi z ed s t a n da r di z ed s ur ve y ques t ionnai re. ques t ionnai re a n d s o m e of t he variables y ou are l oo k i ng for are not in c lu d ed , t h e n it A s t a n da r di z ed que s t io nna i re m a y b e t a k e n is nec es s ary to also m e n t i on it in your study. f ro m t h e st udies/l iterat ures m a d e b y pre vi ous a n d e xi s t i ng researchers/writers. RESEARCH INSTRUMENT W h a t is t h e ap p r o pr i at e r e s ea r ch i n s t r u m e n t for g a t h e r i n g q ua n t it a t iv e r e s e ar ch d at a ? T he researc her m u s t carefully eva luat e if t he s ta ndar diz ed survey ques t ionnai re suits his/her s tudy b y c om p a r i ng it to t h e In t h e e v ent t ha t s o m e of t h e v aria bles ar e not c onc e pt ua l f ramework, s ubproblem s , a n d pr e s en t i n t h e s t a n da r di z ed quest ionna ire, t h e n variables b e i n g studied. it w o u l d b e bet t er t o s u bj e c t t h e ques t i onna ir e t o a s c al e s reliability t est c al l ed ( Cr onba c h's N o t all s t a nd a rd i z ed s u rv ey q u es t ion n a i res Alpha). are of g o o d qualit y. E v e n if it is a pub li s hed one, y ou ha v e to b e r e m i n d e d t hat onl y a few If t here are available s t and ar diz ed peop le va lidat ed t hat ques tionnaire. ques tionna ires, t he res earc her m a y a d op t et hic al pr ac t i c es s u c h a s a s k i n g pe rm i s s ion f r om t he In addition, y ou ha v e to c h e c k if that a ut hor a n d proper citation. quest ionna ire is f r om a res earc h pu bl i sh ed in honor abl e s pa c e s b ec a u s e t here are a n u m b e r of pre dat ory j our na ls lately. RESEARCH INSTRUMENT W h a t is t h e ap p r o pr i at e r e s ea r ch T he exper ts s ho ul d also b e familiar wit h i n s t r u m e n t for g a t h e r i n g res earc h a n d require t he s t ude nt to s u bm i t q uan t it at iv e r e s e ar ch d at a ? t he p ro b l em s ta tem ent, c onc e pt ua l f ramework, resea rch d es i gn and t he ques t ionnai re as basis for ra t ing t he A res earc her m u s t exert effort t o c o ns t r u c t a validation sheet. s urv ery que s t io nna i re t ha t is a ppr opri a t e for his/her st udy. A self-de ve lo ped quest ionna ire m a y t ak e t i m e before it c a n b e perf ec ted b ut it is a If t he que s t ion s in t he surv ey ques t ionnai re are g o o d start for a spi r ing researchers. de ve l oped b y t he researcher, it is c all ed a self- d e v el o p ed s u rv ey questionnaire. A m o n g t he i m por t an t r em i nder s in pr epa ri ng a survey quest ionna ire is to avoid T he re is a n e e d t o h a v e it v al i dat ed b y t he c on s t r uc t i n g s t a t e me nt s t hat are ans wera ble experts. S o m e s c ho ol s w o u l d requi re t hree b y yes or n o w h e n t he w a y to a ns wer is expert s. t h r o u g h t he us e of Li kert Scale. RESEARCH INSTRUMENT W h a t is t h e ap p r o pr i at e r e s ea r ch i n s t r u m e n t for g a t h e r i n g T h e s c al es reliability t es t will ev al ua te t he suitability of i t e m s in e a c h variable. q uan t it at iv e r e s e ar ch d at a ? Y o u m a y c on s id er 3 0 or m o r e r es p ond en t s for Moreover, t he researc her must av oi d t h e reliability t est s b u t t he s e indi vidua ls s h ou l d c on s t ru c t i ng s t a t e me nt s t hat are do ubl e no t b e i n c l ud ed in y our a ct ua l r es pon de nt s barreled. Y o u c a n n ot m e a s u r e t w o t h i n g s in one s ta tem ent. a s y o u p ro c e e d wi t h y our st ud y. Lastly, it is bet ter to ex c l ude neutr al a ns we rs as The s urv ey que s t ion nai r e s h ou l d al so be a m o n g t he c ho ic e s in t he L iker t Scale. pr et es t ed to at least 3 0 r es pon de nt s to c h e c k if t he r e s po nd en t s u nd er s t oo d t h e que s t io ns in t h e O n e of t he beha viora l distortions a m o n g ques tionna ire. res ea rc h r es po nde nt s is t he cent ral t e n de n c y or If t h e p r e t e s t e d s u r ve y q u e s t i o n n a i re h a s t he pref erenc e to c h oos e t he m i dd l e answer. s cal es , t h e s c a l e s ( int erval or rat io s ca le ) A self-d ev e l o pe d s ur ve y h a s t o g o t h r o ug h should be measu red for reliability using C r o n b a c h ' s a l ph a. reliability a n d val idit y tests. RESEARCH INSTRUMENT W h a t is t h e ap p r o pr i at e r e s ea r ch i n s t r u m e n t for g a t h e r i n g q uan t it at iv e r e s e ar ch d at a ? Cronbach's alpha (a; or coefficient alpha) de v e l op ed b y L e e C r o n b a c h in 1951, If t h e resul t of C r on ba c h' s a l p ha is 0.50 or below, m e a s u r e s reliability or int erna l c ons is t enc y. t her e is a n e e d t o revis e t h e scales. "Reliability" is h o w well a t es t m e a s u r e s w ha t it should. A validit y test will require expert validators w h o are expert in b ot h res ea rc h and t he F o r ex a m pl e, a c o m p a n y m i g h t g i v e a job topi c/industry b e i n g st udied. T he se va lidators sa ti sf act ion s urv ey t o their em pl oy ee s. H i g h will ev aluat e t he s t a t em e nt a n d i t e m s in e a c h of reliability m e a n s it m e a s u r e s j ob satisfaction, t he variables, and may provi de w he r e a s l ow reliability m e a n s it m e a s u r es r e c o m m e n d a t i on s for t he i m pr ov e m e n t of t he s o m e t h i n g els e (or pos si bl y n o t hi n g at all). surv ey questionnaire. SURVEY QUESTIONNAIRE DESIGN T he res earc h i ns t r u m ent is a n i m por t a nt tool for a dd r es s i n g t he p r ob l e m a n d m e a s u r i n g t he p r o b l e m a n d s ubprobl em s. F or quantit at iv e research, t he res earc h i ns t r u m ent is nor ma l ly t he s urv ey ques tionna ire. F or qualitat ive research, t he res earc h i ns t r um e nt s c ou l d b e a d e p t h interv iew, fo c us g r o u p dis c uss ion, or observat ion. W e fo cu s our di scu ssion o n Su rv ey Questionnaire. T he s u rv e y q u e s t io n n a i re c a n either be s ta nda rdiz ed, self-de v el op ed or hy br id ( c om b in a t i on of s t a nd a rd i z ed a n d self-developed). It is s t a n d a r d i z e d if t h e q u e s t i o n n a r i e is p a t t e r n e d a ft er a n e xi s t in g q u e s t i o n n a i r e a n d s u c h h a s b e e n a p p l i e d a n d p u b l i s h e d i n a jo urnal. A s t a nda rdi z ed quest ionna ire n e ed not b e va lidat ed a s it w a s alrea dy va lidat ed before. SURVEY QUESTIONNAIRE DESIGN T he researcher, if he/ she opt s fpr t he s t a nda rdi z ed questionnaire, m u s t s ee k t he c o ns e nt a n d per mi s si on of t he writer/author (of t he article wh er e t he ques t i ons are derived) to us e it in his/h er (researcher) current paper. T he p r o bl e m wi t h s t a nd a rd i z ed quest ionniar e, a s ide f r o m g e t t i n g t h e pe r m i s s i on t o u s e it, is h o w c los e it is in a n s w e r i n g t h e p r o bl e m a n d s ub pr obl em s. T hat is w h y s o m e resea rchers w ou l d us e a hy b ri d quest ionnair e, wh er e s o m e ques t i ons are self- de v e l op ed t o a dd r es s t h e s peci f ic probl em. A self-de v e l op ed que s t ion nai r e is d e s i g n e d b y t he resea rcher wi t h t he h op e of a dd r es s i n g t he pr ob l em s a n d s ubprobl em s. T he s c hool pr og ra m , a n d ev e n t he C o m m i s s i o n o n H I g h e r E d u c a t i o n ( CH E D ) , w ou l d require a self- de ve lo ped quest ionna ire to b e va lidat ed b y exper ts (at leas t t wo experts, in s o m e case, t hree experts). SURVEY QUESTIONNAIRE DESIGN T hes e exper ts w ou l d review t he quest ionna ire for its appr opria t enes s ( c o m p a r i n g it wi t h t h e c on c ep t ua l f ram ework, s t a t e m en t of t he probl em, hy pot hes is t es t i ng of t he c o nc ep t pa pe r or proposal, a n d statistical m et hodol ogy ) , t h e n rate it (scale of 1-5, wh er e 5 is very g o o d a n d 1 is very poor), a n d c o m m n e t o n it at t he c o m m n e t section. F or a hy b ri d quest ionnair e, t h e self-de v e l op ed qu es t io ns s h ou l d b e val idat ed. Howev er , it m u s t i nfor m t h e va lidator w h i c h pa rt is no t s ta nda rdiz ed. T he self-de ve lo ped surv ey quest ionna ire a n d s t a nda rdi z ed surv ey quest ionna ire s ho ul d b e d e s i g n e d in s u c h a w a y t hat t he r es po nde nt will not t a k e m u c h of his or her t i m e in a n s we r i n g t he ques tionniare. A ty pi cal 5-p a g e que s t ion nai r e w o ul d t a k e 15 m i n u t e s for t h e r e s po nd en t s t o fill up. A s m u c h a s possible, t he filling u p s ho ul d b e s uperv is ed b y t he resea rcher or t rained e num e r at or to m i ni m i z e erroneous ent ries or m i s s i n g da t a ( un a ns we re d portions). SURVEY QUESTIONNAIRE DESIGN S o m e statistical appl ica t ions w ou l d b e sens itive to m i s s i n g da t a a n d will ha v e its pr oc e s s i ng a bort ed if t he m i s s i n g da t a are quit e s ubs ta nti al ( ar ound 10%). O n e of t he p re d i c a m ne t s of t he s t ude nt s in c o m i n g u p wi t h a surv ey quest ionn a ire is t he t a s k of c h oo s i n g t he ri ght re sp ons e a nc h or s for t he ques t i ons in t he surv ey questionnaire. D e p e n d i n g o n t he need, t hey m a y c ho os e f r om t he list w h i c h m a y b e appl ic abl e to their study: ( not e t ha t a 7-poi nt likert s c al e w a s m o s t l y pref erred in c o n d u c t i n g s oc ia l s t udi es s u c h a s B u s i n e s s Res earch). 7-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. 7-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. 7-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. 7-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. 5-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. 5-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. 5-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. 5-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. 5-POINT Va gi a s, W a d e M. (2006). Li ker t-ty pe s ca l e r es ponse a nchors. C l e m s on Inter na ti ona l Insti tute for To ur i s m & L IKE R T S C A L E R es e a r c h De ve l op me nt , D e p a r t m e n t of Pa r ks, Re c re a ti on a n d To ur i s m M a na g em e n t. C l e m s o n Uni versity. SURVEY QUESTIONNAIRE DESIGN Th e survey que stio nnaire s h ou l d h av e a cov er letter that states w h o is th e researcher, w hat is th e purpos e of the research, a n d the as surance that the data will b e treated with confidentiality. Th e cov er letter co ul d b e in a se parate sh ee t of pap e r or it co ul d b e in tegrate d in th e questionnaire. Th e que stio nnaire s h ou l d also b e arra n ge d in th e s e q u e n ce of questions, startin g with th e difficult ones. Th e qu es tion s ab ou t th e d e m o g ra p h i c data of th e re spo nd en ts are better pre se n ted at the last part, so the re spo nd ents c an ac co m pl i s h t h e m easily. B U S I N E S S R E S E A R C H C L A S S A C L C Co l l e ge of B u k i d n on SAMPLE COVER LETTER SURVEY QUESTIONNAIRE DESIGN W h e n d e s i g n i n g a survey questionnaire, av oid th e o pe n - e n d e d qu e s tio n s as m u c h as possible. A n o pe n - e n d e d qu e stio n wo u l d require m u c h of the re spondent's time as he/she wo ul d thin k first before he/she co ul d c o m e u p with th e answer. C h a n c e s are, th e re sp on de n t w ou l d just s kip th e question. A s m u c h as possible, g o for close-e n d e d questions, wh e re the option s are listed for the re spo nde n t to ch oo s e from. Howeve r, in clu de a n option – oth ers (please specify) ; this will ad dre s s wh at e v er is m i s s e d in th e opinions listed. B U S I N E S S R E S E A R C H C L A S S A C L C Co l l e ge of B u k i d n on SAMPLE CLOSE-ENDED QUESTION 1. W h i c h s pe ci al t y st or e d o y o u n o r m a l l y visit a n d b u y m e r c h a n d i s e f r o m a t t h e m al l ? P l e a s e c h e c k t h e a p p r o pr i a t e box. SURVEY QUESTIONNAIRE DESIGN If t he ques t i on is a bo ut r atin g , b e s ur e to speci fy t he r a n g e a n d t he v alue at e a c h point or t he v alue at t he ex t r em e points. F or exa mp le, "Please rate o n a s cal e of 1-7, wh er e 7 is hi g hl y v al ued a n d 1 is leas t v al ued - for e xt r em e or bipolar; plea se rate t he s cal e o n a s cal e of 105, wh er e 5 is hi g hl y agree, 4 is agree, 3 is neither a g re e nor di s ag re e (neutral), 2 is di s ag re e a n d 1 is hi g hl y di s ag re e - L ik er t Sc ale. In research, w e nor ma l ly pr es e nt t h e posit iv e first ( hi g her va lue) a n d t h e n eg a t i v e (lower va lue) last. If t h e qu es t io n is a b ou t r an k ing , b e s ur e t o s pec if y w h a t is first ( norm a ll y 1), w h a t is s e c o n d (2), w h a t is t hird (3), a n d s o on. T h e n u m b e r in r an k i ng, un li k e in r a t i ng s h ou l d no t b e r epe a t ed a n d b e u s e d onl y onc e. SAMPLE LIKERT SCALE QUESTION 1. W h a t attr acts y o u to yo ur pr efe rr ed ma ll? P l e a s e rat e o n a s c a l e of 1-5 b y c h e c k i n g t h e a ppropri at e box, wher e: 5 - S t ro ng l y A g r e e 4- Agree 3- N ei th er a g r e e nor d i s a gr e e (neut ral) 2- D i s a g re e 1- S t ro ng l y A g r e e SAMPLE RANKING QUESTION B U S I N E S S R E S E A R C H C L A S S A C L C Co l l e ge of B u k i d n on PAIRED COMPARISON QUESTION WHAT ETHICAL ISSUES SHOULD BE AVOIDED IN BUSINESS RESEARCH? E T H I C A L I S S U E S T O AVOID R e s ea r c h s ho ul d b e g r o u n d e d o n ethics. T he resea rcher s ho ul d b e t rans parent wi t h t he res earc h pr oce ss a n d findi ngs, ev e n if it w ou l d m e a n not m e e t i n g his/her res earc h objective. T he reader of t he res earc h pa pe r s ho ul d not b e misl ed. A n y mi s r ep re s e nt at ion is unethical. If s t u de nt s are inv olv ed in d o i n g da t a ga t he ri ng , t he s c hool polic y a bou t it s h oul d b e obs erved; otherwise, it is unet hical. If a researcher is d o i n g a c ont ra ct ed resea rch for a part icular c o m pa ny , he or s he s hou ld not a c c ep t a res earc h-related activit y fr om t he c o m p a ny ' s compet itors; ot her wi se it is also unethical. E t h i c a l c o n s i d e ra t i o n s h o u l d b e o b s e r v e d i n t h e e nt i re r e s e a r c h p roc ess. E T H I C A L I S S U E S T O AVOID A s o n e pr epar es for t h e r ese arch pr oposal, w h i ch co n t ain s t h e C h apt e r s 1 ( I N T R O D U C T I O N A N D R R L ) a n d 2 ( R E S E A R C H M E T H O D O L O G Y ) , et hical con sider at ion s m u s t b e pl a ce d o n t h e int egrit y of t h e st u d y a n d i n cl u d e d o n t h e last part of C h ap t e r 2 (as pr act ic ed b y s o m e schools). T h e re search er s h ou l d se e to it t hat the Title, C o n ce p t u al F r am e wo r k, Research Q ue st io ns, a n d I n s t r u m e n t s are O R I G IN A L. A s m e n t i o n e d, s t an d ar di z e d su r v e y qu e st i on n ai re s m a y b e u s e d b y a s k i n g pe r m i ss io n fr om t h e au t h or b y e m ai l i n g him /h er, or b y c o n t a ct i n g h im / h e r in social m e di a, a n d b y pr o pe r cit atio n of t h e person. As t he re se ar ch er pr oce e ds wit h t he dat a gat h er in g, it s h ou l d st art b y s e c u r i n g pe r m i ss io n fr o m t h e m a n a g e m e n t of t h e in st it ut ion b e i n g stu di ed. D a t a g a t h e r i n g m a y entail cost, b u t t hat is part of t h e proce ss. O n e m u s t n ot m a k e u s e of co n n e ct i o n s to r u n u n e t h i cal da t a g a t h e r i n g as c o m p a n i e s t a ke t his act i on wi t h appr o pri at e sanct ions. E T H I C A L I S S U E S T O AVOID R e s po nd e nt s m u s t b e i nfo rm e d of t he pu r po s e of t he s t ud y a n d h o w t hey are g o i n g to a n s we r t he s urv ey ques tionna ire. Th e researc her m u s t r esp e ct t h e r e sp o n d e nt if he / she c h o o se s n ot to par ticip ate in t h e d at a collection. T he researcher s hou ld also a ss ur e t he r es p ond en t t hat t he da t a pr ov id ed will b e t reat ed wi t h conf identialit y. If it will b e s ha re d to others wi t hout t he c o ns e nt of t he res pondent , t h e n it is unet hical. W h e n d e s i g n i n g t he surv ey questionnaire, it s h ou l d h a v e n o r e s po nd en t n a m e. T h e r e s po nd en t will just b e a s s i g n e d a n u m b e r for c h e c k i n g p ur po s e s o n m i s s i n g da t a or er ro neous entry. C l a i m i n g t h e w or k s of ot her re sea rc her s a s one's o w n is no t onl y un et h ic a l b u t al so I L L E G A L ; t here is a S T I F F P E N A L T Y F O R P L A GI A R I S M. C o p y i n g a n d p a s t i n g t h e w o r k s of o t h e r r e s e a r c h e r s is a f o r m of p l a g i a r i s m if it i s n o t p ro p e rl y c i t e d or p a ra p h r a s e d. E T H I C A L I S S U E S T O AVOID P L A G I A R I S M is th e practice of t ak in g s o m e o n e else's wo rk or ideas a n d p as s i n g t h e m off as one's own. B a s e d o n th e article pu bl ish e d by S h ab e (2018), pl agiaris m take s various forms: 1. D I R E C T P L A G I AR I S M Dire ct pl agiaris m is th e m o s t ob v iou s fo rm of plagiarism. This m e a n s t a k in g s o m e o n e else's ide as or w ork a n d c l ai m i n g t h e m as y our own , wi th ou t citation. E v e n if y o u de lete or c h a n g e a co u p le of w or ds he re a n d there, it is dire ct p la gia ris m if th e ma jo rity of th e stru ctur e a n d w o r d s a re th e sa me. D ire ct p la g i a r ism is o n e of th e wo rst ty pe s of p lag iar ism. It often re sults in expulsion, and, if it also violates copyright, pos sibl e crimin al charge s. E T H I C A L I S S U E S T O AVOID 2.P AYING F O R SO M E ONE ELSE'S W OR K. T his o n e is self-explanatory. If y o u p a y s o m e o n e to wr ite a n e s s a y for yo u, it is P L A G IA R I S M. T h e w o r d s s u b m i t t e d are N O T Y O U R S a n d are ther efore P L A G I A R I Z E D. Th is also i n c l u d e s h a v i n g a F R I E N D or F A M I L Y M E M B E R W R I T E Y O U R E S S A Y F O R Y O U a n d t h e n Y O U H A N D IT I N W I T H Y O U R N A M E O N IT. 3. S E L F - P L A G IA R I S M. Self-p l a g i a r i s m c a n b e tr icky a n d is fr e qu en tl y un in ten tio nal. Th e r e are c o u p l e of ve rsi on s of self- p lag i ar ism ; t h e m o r e se ri ou s b e i n g t u r n i n g i n a p a p e r y o u al re ady s u b m i t t e d for a g r a d e to an o th e r class. B e c a u s e y o u h a ve t u r n e d thi s p a p e r i n alr eady, it is n o l o n g e r n e w a n d or i gi nal work. E T H I C A L I S S U E S T O AVOID 4. P A R A P H R A S I N G W I T H OU T A S OU R C E. Pa r ap hr asi n g itself is not pl agi ar ism so l o n g a s yo u properly cite your sorces. Howe ver , p a r a ph r a si ng b e c o m e s pl a gi ar ism w h e n yo u r ead different sources, pull out s o m e ke y points, a n d t he n rewrite th ese point s a s if they wer e your o w n ideas. If yo u d o not cite your sour ces for all th e n on - original idea s referenced in your paper , t he n yo u ar e c o m m i t t i n g plagiar ism. Ac ci de n ta l p la g i a r i sm is frequently c au s e d b y p ar aph r asi ng with out a source. It is si m ple a n d ea sy to avoid. Ju s t r e m e m b e r to properly cite your source. HOW SHOULD THE STATISTICAL TREATMENT BE REPORTED? WHAT SHOULD BE TESTED STATISTICALLY? In the statistical treatment part, the researcher will report that statistical tools he/she applies in me asu rin g the data. It sh ould include h ow the data will b e processed by the statistical software either frequency, percentage, ratio, descriptive statistics, a n d other quantitative me asu reme nt s (such as multivariate techniques). If the major me asu rin g tool is ba se d o n multivariate data analysis, the statistical process (treatment) m u st b e discussed briefly. SAMPLE STATISTICAL TREATMENT Th e d e m o g r a p h i c profile of t he r e s po n de n t s is interprete d a n d a na lyz ed u s i n g f r eq u en cy coun t, pe r ce nta g e , a n d ratio. For the statistical tool, the resear cher c an use the S P S S soft wa re for th e c om p u t a t i o n a n d a nalysis of w i e g h t e d m e a n, C r o nb ach 's alpha., o ne - w a y AN O V A , a n d factor analysis. Fa ct or analysis is u se d to de te r m ine whe th er there are sig nificant factors within variables. The pr incipal c o m p o n e n t analysis w as appl ied b y th e re se archer in this study. I n inte rpr eting th e si g nif ic a nc e of factor loa ding , t he r ese ar che r u s e d t he g ui de li ne s for ide nt ifyin g sig nifica nt factor l oa di n g b a se d o n s a m p l e size. A factor l oa di n g of 0.325 b a se d o n 0.05 si g nif ic anc e level w a s co ns id e r ed sig nif icant b a se d o n a s a m p l e size of 300. NEXT STEP: GATHERING THE DATA TIPS ON HOW TO GATHER THE PRIMARY DATA THROUGH A SURVEY QUESTIONNAIRE O n c e t h e p r op o sal (c ha pt e rs 1 a n d 2 for A P A F o r m at ) is p r e s e n te d a n d ac ce p te d , t h e n e x t st e p is to g a t h e r t h e data. T h e fo l l ow i n g g u i d e l i n e s m a y help: F o r C o l l e g e s t u d e n t s ( w o r k i n g i n di vi d u al l y or co ll ect ive ly a s a g ro up ): 1. T h e e n u m e r a t o r s (th e o n e s g i v i n g t h e su r v e y q u e s ti o n n a i r e a n d r e tr i e vi ng it after fi ll in g u p t he q u es ti o n na i r e) s h o u l d h a ve s o m e prior tr a i ni n g o n h o w to c o n d u c t t h e sur vey. I n thi s case, th e s tu d e n t s are t h e e n u m e r a t o r s as it will b e e x p e n si ve to hi re t h e ser vice s of e x p e r i e n ce d e n um e r ato r s. T h e e n u m e r a t o r s ar e n o r m al l y p a i d p e r r e s p o n d e n t b as i s (w i t hi n t h e r a n g e of P h P 100-150/re spondent). T h e c o st al so i n c l u d e tr a ns po r t ati o n (if t h e ar e a is far) a n d m e a l or s n a c k a l l o w a n c e (e spe ci al ly if t h e d a t a g a t h e r i n g w o u l d t a k e m o r e t h a n 3 hours). 2. T h e s tu d e n t /e n u m e r a t o r s h o u l d b e a m i a b l e w h e n a p p r o a c h i n g t h e r e s p o n d e n t a n d b e c ou r t e ou s a s well. 3. S tu d e nt s , a s w e l l a s o th e r r ese ar che r s, s h o u l d h a v e p a t i e n c e a s t he r e w ill b e m o r e r eje ct io n or n o n - p ar ti c i pa ti o n b y t h e r e sp o n d e n t s. Th is is tr ue b e c a u se t h e cu l tu r e of r e se ar ch is n o t well a d o p t e d i n t h e Phil ipp iin es. TIPS ON HOW TO GATHER THE PRIMARY DATA THROUGH A SURVEY QUESTIONNAIRE 4. To m i n i m i z e rejection, a t o k e n is n o r m al l y g i v e n after t h e p ar ti c i pa ti o n of r e sp o n d e n t s. T h e token, to c a t c h t h e atte n ti on of t h e r e spo n de n t, is m e n t i o n e d o n c e t h e e n u m e r at o r will a s k t h e par tici pati on of t h e r e sp o n d e n t b y e x p l a i n i n g briefly w h a t t h e r e se ar ch su rve y is all about. 5. Try to l i mi t t h e q u e s ti o n n a i r e to a m a x i m u m of 5 p a g e s s o t ha t t h e fi ll in g u p t i m e w ill n o t t ak e m o r e t h a n 15 m i n u te s. 6. C h e c k for a n y u n a n s w e r e d p o rt i o ns i n t h e r e s p o n d e n t' s for m. R e q u e s t it to b e filled up , i n c ase th er e is o n e or m o r e fo und. N o t e th at m i s s i n g d a ta m a y p o s e a p r o b l e m d u r i n g d a ta p r o c e s si n g a n d d a ta inter pretati on. S o m e softw are will n o t e v e n p r o ce s s it if m i s s i n g d a ta h a ve r e ac h e d t h e critical level ( w h i c h vari es f r o m softw are to software). 7. O n c e t h e d a ta are g ath e r e d, e n c o d e it i n t h e S P S S. SUMMARY Research Methodology is a detailed outline of how an investigation will take place. Includes how data will be collected, what instrument will be employed, how the instrument will be used, and how the data collected will be analyzed. Students and researchers have to decide on the right sample size. They can use random or purposive sampling. Types of random sampling : a) simple random sampling, b) stratified random sampling, c) random sampling based on Poisson distribution Quantitative research needs a survey questionnaire as the research instrument. A reliability test through Cronbach’s alpha is applied on the questionnaire’s interval scales. Qualitative research’s instrument includes depth interview, focus group discussion, or observation. Questionnaire can either be standardized, self-developed, or hybrid. Close-ended question, Likert scale question, ranking question, paired comparison question, open ended question have been included in this chapter. Ethical consideration should be observed. Some tips in gathering primary data through survey questionnaire. B U S I N E S S R E S E A R C H C L A S S A C L C Co l l e ge of B u k i d n on END OF CHAPTER 4 PART 2 N ex t Topic: C ha p t e r 5 R es e a r c h Me as urem ent , A ppli c at io ns a n d Int erpret ations

Chapter-4-part-1-and-2 (1).pdf

Document Details

Tags

Related

Full Transcript

Upgrade to continue