Business Research 1 Research 4.2 Steps in Research Process 1.3 Research Methods versus Research Methodology 1.4 Business Research (eae In today's world, research has become an important activity in overall social life. Research provides a framework to conduct a research. Research in common parlance refers to a search of knowledge. Research is a scientific and systematic search for pertinent information on a specific topic. Hence, research methodology is a science of research & study of research methodology provides a way and guiding principles for research. 1.1.Research; Research is known as the provider of the specific knowledge needed to succeed in researching and utilizing the best and most appropriate data for decision making. It is collection of information on a c2rtain ideas or theories to gain better knowledge on something. Research can be done through reading source material or performing experiments. It will also provide the skills needed to effectively communicate research results to a specific audience for maximum impact and effective decision making. Ne EEE (==«a Com. (Sem. = It) poe ia Com Research Methodology For Business A ” sca & Definitions: yf Meaning: Research Is @ systematic structure of investigation undertaken in order to discover new facts. It provides a structure for decision-making, Research is an inseparable cart of human knowledge. It is a process that takes the assistance of the scientitic method in solving problems. Research is a Way of thinking, It clarifies the thought process. Research is undertaken in natural and social Solences, It always expects 2, piece of work that advances human. knowledge. Today's research became’ an mportant activity in overall social lite, Methodology is essential to perform any search activity. Method means System or order. Method means way of doing ething. Research methodology provides a framework to conduct a research. It be said that research methodology is a science of research. Methodology provides a way and guiding principles for research. Hence, study of research methodology became very important in today's academic career. 8) Definitionsgey i 1) Redman and Mory : “Research is a systematised effort to gain new knowledge.” 2) John Best: “Research is a more systematic activity directed towards discovery and the development of an organised body of knowledge.” 3) Webster's Dictionary : “Research is a careful or critical inquiry or examination in seeking facts or principles; diligent investigation in order to ascertaining something.” 4) Encyclopedia of Social Sciences : “Research is the manipulation of things, concepts or symbols for the purpose of generalising to extend, correct or verify knowledge, whether that knowledge aids in construction ot theory or in the practice of an art.” 5) Shorter Oxford English Dictionary : “Research is an investigation directed to the discovery of some fact by careful Study of a subject; a course of critical or scientific inquiry.” —_ eeiW): Research Methodology For Business M.Com.(Sem.- pi ii h: a " B14. Characteristics of Good Researcl & Research is actually an act ‘of studying something carefully and extensively in order to research should be attain deep knowledge in the same. For being successful, systematic, arranged, summarized and recorded properly. Reseaich is not only a process that is limited to the field of science. It can, as well, cater to people and scholars trom artistic, historic or any other field where an individual is willing to do extensive study to get relevant information. Research can be creative, exploring or just reassuring in nature. Therefore, the characteristics of a good research are as follows: 1) Systematic: It means that research is structured with specified steps to be taken in a specified sequence in accordance with the well defined set of rules. Systematic char acteristic of the research does not rule out creative thinking but it certainly does reject the use of guessing and intuition in arriving at conclusions. 2) Logical: \ This implies that research is guided by the rules of logical Teasoning al process of induction and deduction are of great value in carrying out research, Induction is the process of reasoning from a part to the whole whereas deduction is ind the logical the process of reasoning fram some premise to a conclusion which follows from that very premise. In fact, logical reasoning makes fesearch more meaningful in the context of decision making, 3) Empirical: It implies that research is related basically to one or more aspects of a real situation: and deals with concrete data that provides a basis for external validity to reseal results. 4) Replicable: This characteristic allows research results to be verified by replicating the study thereby building a sound basis for decisions. The research design and are replicated or repeated to enable the researcher to arrive at valid and cor fesults,M. Com. (Sem. - Ill) H 5) Analytical: Research Methodology For Business Research utilizes i : i } a analytical procedures in gathering the data, whether historical, descriptive, and experimental and case study 6) Methodical: iN Research is conducted in a met mi r without bias using systematic hodical manner wi method and procedures,6. Types of Research: The systematic, rigorous investigation knowledge or validate existing knowledge is called of a situation or problem in order to generate ne as Research. Its various types are as follows: Survey Research Concept al vs. Empirical Action Research Quantitative vs. Qualitative Evaluation Research Applied vs. Fundamental Descripti ve vs. Analyticalm..com. (Sem. My) Research Methodology For Business ‘Types of Research 4) Survey Research : Survey research is a technique whereby the researcher studies the whole population with respect to sociological and psychological variables. Survey research studies large and small population by selecting and studying samples chosen from the population. It is mostly devoted to the study of characteristics of the population under investigation, Survey research is approached through the method of personal interviews, mailed questionnaires and personal discussion besides indirect oral investigation. The success of survey research depends upon the willingness and the co-operative of the sample selected for the study. The different categories of survey research are personal interview, mail questionnaire and panel technique and telephone survey. 2 Case Study Research : The case study is an intensive study through which one can know precisely the factors and causes of a particular phenomenon. It is a very good method of collecting information about an individual, a family or a group of persons. Case data may be gathered exhaustively of an entire life cycle of a social unit or a definite section of it. Study of social psychology without case study is like a law court without testimony. It is consideredias gateway and destination to abstract knowledge. In this study, a large variety of units is selected for study and the size of the unit may be quite large to cover an entire community. It aims at deep and through study of a unit. It deais with every aspect of a unit and studies it intensively. 3 Action Research : Applied research is also known as action research. It is a recent addition to the categories of research. The aim of applied research is to discover a solution for Some practical problems. It is concerned with search for ways of using scientific knowledge to solve practical problems. \t is a research through launching of a direct action with the objective of obtaining workable solutions to the given problems. The methods used for this type of research are usually personal interviews and the —— eee5) 4) 6) Applied vs. Fundamental: Research Methodology @ personal values of the jduals are one © associated with action research. Evaluation Research: f Every country In the world Is intensively engaged in implementin ; as in the planned programs, There is need to evaluate these programs oF projects In 4 context in which they are launched, Evaluation research is concerned with measuring the effectiveness of these programs. Evaluation research is primarily her directed to evaluate the performance of the developmental projects and ot ted. are the three types oO 9 target-oriented ‘i ation, economic programs that have already been implement Coneurrent evaluation, alyation phasic or periodic evaluation and terminal ev ntinuing processiof an inspec evaluation research. Conourrent evaluation Is a cor of the project that has been launched, Phasic or periodic evaluation takes place at the project. Terminal evaluation ist different phases or stages of performance of evaluation of the final phase of the project. Descriptive vs. Analytical: Descriptive research includes surveys live research is description of the state of affairs, as s and fact-finding enquiries of different kinds The major purpose of descript exists at present. In social science and business research, we quite often use term Ex post favto research for descriptive research studies. The main characteris ‘of this method is that the researcher has no control over the variables; he report what has happened or what is happening. Most ex post facto rese projects are used for descriptive studies in which the researcher seeks to such items as, for example, frequency of shopping, preferences of people, a i data. Ex post facto studies also include attempts by researchers to discover 6 even when they cannot control th i : at i descriptive ‘esearch are survey Pe te a ol 5 of resoattial correlation methods. In analytical rese oe na arch, on the other hand, the resea use facts or information already avai available, and analyze th make 5 nal evaluation of the material. i =~ .om. (Sem. = lil) Research Methodology For Business Research can either be applied (or action) research or fundamental (to Basic or pure) research. Applied research aims at finding a solution for an immediate problem facing a society OF an industriaVbusiness organisation, whereas fundamental research is mainly concerned with generalisations and with the formulation of a theory. "Gathering knowledge for knowledge's sake is termed ‘pure’ or ‘basic’ research." Research Concerning some natural phenomenon or relating to pure mathematics are examples of fundamental research. Similarly, research studies, concerning human behaviour carried on with a view to make generalisations about human behaviour, are also examples of fundamental research, but research aimed at certain conclusions (say, a solution) facing a concrete social or business problem is an example of applied research. Research to identify social, economic or political trends that may affect a particular institution or the copy research (research to find out whether certain communications will be read and understood) or the marketing research or evaluation research are examples of applied research. Thus, the central aim of applied research is to discover a solution for some pressing practical problem, whereas basic research is directed towards finding information that has a broad base of applications and thus, adds to the already existing organized body of scientific knowledge, Quantitative vs. Qualitative: Quantitative research is based on the measurement of quantity or amount. It is applicable to phenomena that can be expressed in terms of quantity. Qualitative research, on the other hand, is concerned with qualitative phenomenon, i.e., phenomena relating to or involving quality or kind. For instance, When Wie are interested in investigating the reasons for human behaviour (i.2., why people think or do certain things), we quite often talk of ‘Motivation Research’, an important type of qualitative research, ‘This type of research aims at, discovering the underlying motives and desires, using in depth interviews for the purpose. Other techniques of Such research ‘are word association tests, sentence completion tests, story completion tests and similar other projective techniques. Attitude or opinion research i.e., research designed to find out how people feel or what they think about 4 particular subject or institution is also qualitative research. 1.148) Conceptual vs. Empirical: lology For Business T sciences where the Research Method ehavioura’ behaviour. Through such pecially important in the b tives of human ‘otivate people to behave in a particular thing. It may be - tice is relatively a difficult arch is S| e underlying mo! ious factors which mi ‘Gualitative rese aim is to discover th research, we can analyse the vari particular manner or which make people like or dislike a stated, however, that to app! while doing such research, one sho! ly qualitative research in prac job and therefore, uld seek guidance from experimental psychologists. a(s) or theory. It is generally Conceptual research is that related to some abstract ide pts or to reinterpret existing used by philosophers and thinkers to develop new conce ones. On the other hand, empirical research relies on alone, often without due regard for system and theory. | coming up with conclusions which are capable of being verif it as experimental type of research. In such @ e, and actively to g experience or observation it is data-based research, ied by observation 0 experiment. We can also call research, it is necessary to get at facts firsthand, at their sourc: about doing certain things to stimulate the production of desired information. In sut a research, the researcher must first provide himself with a working hypothesis guess as to the probable results. Researcher then works to get enough facts (da to prove or disprove his hypothesis. He then sets up experimental designs whit thinks will manipulate the persons or the materials concerned so as to bring fol desired information. Such research is thus characterised by the onal oe a the vieae under study and his deliberate manipulation of of em to study its effects. Empirical r i i certain variables affect ae te a "oa oe 4 experiments or empirical studies i 2 bid cone aa ; es is today considered to be the most support possible for a given hypothesis. ‘- a | other forms 6) Practical Value: ie practical value. However, In all as! Basic research does not emphi noe. research, practical value Is of great importa 6 Wal See rested in som hat can bet A hypothesis is an explanation for a phenomenon ti : a roves it, For the duration of testing, the \yp ; concept is a i ideally either proves OF dispr ideally ether prev ——— ; to be true, and the goal of the researcher is to rigoro! very important part of the scientific method, and it als sly test Its terms. The ciplines as Salem | 0 holds true in other dis rd the hypothesis that the grains contaminated with ergot, s a hypothesis, he or she does well. For example, some historians have put forwa! Witch Trials were brought about by the consumption of resulting in a mass hysteria. When someone formulates so with the intention of testing it, and he or she should not know the outcome of potential tests before the hypothesis is made. 2.2.1_Meaning and Definitions : Janations that can account for our observations of the ibe cause-and-effect relationships between 42 Hypotheses are potential exp! external world. They usually desc proposed mechanism or process (the cause) and our observations (the effect). A) Meaning: The word hypothesis (plural is hypotheses) is derived from the Greek word: ‘hyposthenia’ meaning ‘to put under’ or ‘to suppose’ for a hypothesis to be pul forward as a scientific hypothesis, the scientific method requires that one can testit Etymologically hypothesis is made up of two words, “hypo” (less than) and thesis? r mean less than or less certain than a thesis. It is the presumptive statement of @ proposition or a reasona le gues: z : the researcher seeks to prove ae emme — ae, com. - ll (Sem. - Ill) | —Fefinitions: Research Methodology for Business webster’s New International Dicti i ‘onary of English Lan ‘4 proposition, condition o¥ guage: f i. out its ‘ect s Which is assumed, perhaps without belief, in a 088 and by this method to test its accord with which are known or may be determined" Kerlinger: | nypothess “= 8 Conelural statement of the relation between two or more a are always i in declarative sentence form and they relate, either enerally or specifically Vai ly cally var rable o variables." Goode and Hatt: jypothesis Is a proposition which can be put to a test to determine its validity. It ay seem contrary to, Orin accord with, common sense.” ) George A. Lundberg ; T thesis is a tentative justification, the (validity Yof which femains to be eee nnn thesis is a tentative assumption drawn from knowledge and theory which is sed as a guide in the investigation of other facts and theories that are yet unknown. s a guess, supposition, or tentative inference as to the existence of some fact, condition, or relationship relative to: some phenomenon, which serves to explain ‘such facts as already.are known to exist in agiven area of research and'to Quide the for new truth, 2.2.2 Qualities of Good Hypothesia research Methodology fOr Busing, com. «t(Sem.-l!) Closest to Things Observable Must be Specific Related to Available Tehniques Empirically Testable Related to \ Body of Theory 1) The Hypothesis Must be Conceptually Clear ; Clear definitions of the concepts and variables used in the hypothesis Should given both formally and operationally, An ambiguous hypothesis characterised by undefined concepts cannot be tested. The concepts embodied in the hypothesis should be defined in a commonly accepted and communicable manner. The Hypothesis Must be Specific : Hypothesis must be specific, rigid and reasonable in its content and definition, A hypothesis should include a clear statement of indexes which are to be used, For 2 example, the concept of social class needs to be explicated in terms of indexes such as income, occupation, education, etc. Specific formulations have tne obvious advantage of ensuring that research is practicable and significant, It increases the validity of the results. 3) The Hypothesis Should be Empirically Testable : A usable hypothesis should have empirical reference The concepts embodied it the hypothesis must have an empirical correspondence. No usable heaters embody moral judgments. 4) It Should be Reiated to Body of Theory ; Hypothesis should be consistent with ‘ a substantial body of established facts. TH hypothesis selected must be in Continuation with theory already evolved.com. (Ser. -) Research Methodology for Business Fational of hypothesis. If the hypothesis is Ip 10. quality, support, correct or refuse the lative only by building on an existing body This requirement conoems the has related to some theory, Fesearch will he theory. A science, however, can be cum of fact and theory. jt Should be Related to Available Techniques : i The hypothesis should be related to available techniques of testing. The researcher who does not know what techniques are Avallable to test his hypothesis is in a poor way to formulate questions, The hypothesis, therefore, should be formulated only alter due thought has been given to the methods and techniques that can be used to measure the concepts and variables incorporated in it. It Should be Closest to Things Observab| a ea {t is expected that a usable hypothesis should be Closest to things observable Failing this, it would not be possible to test their accord with empirical facts. A good hypothesis may be formed in such a manner that the deductions can be made from it. In spite of all the above characteristics, a good and usable hypothesis should be simple and brief. Importance of Hypothesis importance, advantages, utility, or functions of the hypothesis may be summed up pilows: lat what is the main focus of study. Rives Point to Enquity : | . Wypothesis gives point to enquiry. It makes the enquiry more specific and to theion of the facts nati adequate expla! 3) rs expla Mss z Hypothesis provides the hypothes's: fig res0arer The relationship ex, E. si ic 4) Tools of Reseal a we ) theses are import ant as 100 all i ih. ~ el hesis tls the researone! in the hypothes! need to be collected. Provides Direction : Hypothesis helps in deciding th knows the direction, he can mak ich to proceed, If the dhe can find out the m 5) direction in out his path an which he can reach his goal. Helps to Draw Conclusions : aie Hypothesis is not only usetul in proseeding in our study on right butit is important in drawing proper conclusions. 7) Save Time, Money and Energy : sis helps to save time, money and energy. It helps to avoid unnecessary actions in research process. 6) A clear hypothe: 8) Helps in Building a Body of Scientific Knowledge : Hypothesis helps in building a body of scientific knowledge which is generated through the route of development of explanation, hypothesis & verification of the: hypothesis, revision of hypothesis and retesting of hypothesis, 9) Help to Suggest a Theory : : ‘ Hypothesis helps the social hi ps ‘ocial scientists to Suggest a theory that may explain. cand 10) Helps to Solve the Problems ‘i - A problem can be scientitica | an ly Solved if itis Teduc ’ ed to hypothesis form,con Se ——; Types of Hypothesis -— nding upon the ‘ ding UP Nature of the i Classi 'eation is carried out as follows; esearch Hypothesis; an a prediction or @ hypothesized Telationship is to be tested by scientific ethods, it I i cm The research hypothesis is a lependent variable to. a dependent variable. y @ research hypothesis must contain, at least, one independent and one endent variable. A research hypothesis must be stated in a testable form for its per evaluation. As already stressed, this form should indicate a relationship etween the variables in clear, concise, and understandable language. Research yootheses are classified as being ditectional/or non-directional. dictiv 4 rectional hypothesis: TI yootheses, whigh stipulate the direction of the expected differences or onships, are terms as ditectional hypotheses. For example, the research sis: ‘There will be @ positive relationship between individual's attitude is 2 directional esearch ypothe: wards high caste Hindus and his sosio-economic status,” sotesig. This hypothesis slpllates that incvcuals. wih favoreble attitude towards high caste Hindus will generally ‘come from higher socio-economic Hindu 3 re il does stipulate the di ecti if the relationship. Simila 'y, the amilies and therefo it ic jon oF : ai: " la will exhibit low anxiety than adolescent ypothasis; “Adolescent DOYS¢) d) boys direction of the di pesto — it SU - 4% f hypothesis pecause t 1 ok arch IpU a is a directional re! eon grours 7 r with tow 12" F ifferenc® betwe' ional hypothesis: : speclly " ’ foes not ps . othesis. For example, the 4 which ts 0 necirectional rest i - ba ie adaptability of fathers and be difference in : a «there is difference in ly lve directional research hypothesa, , ; ‘i 1Q" are no! adolescent girls of high |Q and low. a “neon thera cota will Although these theses stipulate there : a yp A eoerh hypothesis can take either statistical form, me | declarative form, the null form, or the question form Declarative hypothesis: When the researcher | makes 4 positive stateme! ? the hypothesis takes the declarative form For example, the hypothesis: “] academic achievement of extroverts IS significantly higher than that of the }f : introverts,” is stated in the declarative form. In such @ statement of hypothesis, the is theoretical formulations of what should researcher makes a prediction based on hi happen if the explanations of the behaviour he has given in his theory are correct. Non-direct! Aresearch hypothesis, oF relationships, '§ a There will hypotheses: ig of thelr childr towards rearins en’ OF difference is not specified. nt about th Null hypothesis: In the null form, the researcher makes a statement that no relationship exists. The i “There is no significant difference between the academic achi toad .... of non, aaa is an example of null hyp oth e tested statistically, they are often termed as: hypotheses. They are also called the testing hypotheses whel hypotheses are tested statistically by converting them into null ‘2 a where it seems to hold good itis due to mere chan ss na reject the null hypothesis by showing that the out. ce. & is for the hoo ae cong mentioned in the d dismissed as having occurred by chance, Sash na 212- til) auestion Form hypothe, e question form hypott S12 wt te aucome wt bo 8 researcher js interested in to test anxiety of The declarative form Of the povremmednsinuon Be “Teaching chieron through the their test anxiety» G ‘through, Programmed instruction their test amity: This Statement shows that no ‘ instryetion ang test anxiety, tatement inthe form sw ‘aching children through anxiety ) The null form woulg be material will have NO effect on relationship exists between: terms, for students taught by Method A equals the mean reading achievement of the Population taught by Method B.” Therefore, researcher can Say that statistical hypotheses cro, concerned with populations Under study. ‘They use inferential statistics, to draw conclusions about population values even though they have access to only a Semple of participants. in order to use inferential statistics, researcher need to (arslate the research hypothesis ino a testable form, is called the mul fypoinests An alternative or declarative hypothesis indicates the situation corresponding to ts ated hypothesis lifer depending on When the null hypothesis is not true. The state —=fil) ¢ in the course of ty M.Com. -i1(Sem- ain facts so of y ei ily © i ition j hy Working Hypotheses remporatll tentative Propo Thaticng |. cher assume i : When a reseat ter, he he may ‘ working hypothesis é pratiminary study of 4 P1 fi final, Such a course of action juesses are not Zz Formulation of hypothe cain ar these 9 Tey 5 or tentative gene! ad t0 successful formulation i Hypotheses are guesse! hee rot le alone ‘i r ‘ accidents. Collection of information alot oe speculation and im: aging ol e hypotheses. Hypotheses are the products a tone and explanations, and panjy knol guesswork. They are based partly on™ theses and de cin S mulating hypo! conceptual. There are no precise rules for for ied. However, there are certain from them that can be empirically verified. akes him fra ¢ considers consequences oh thernaree n. Some O! necessary conditions that are conducive to their formulatio’ 1) Richness of background knowledge: . f : y after making observations of A researcher may deduce hypotheses inductivel behaviour, noticing trends or probable relationships. Fer example, a classroom sis of his experience and his teacher daily observes student behaviour. On the ba: attempt to relate the knowledge of behaviour in a school situation, the teacher may behaviour of students to his own, to his teaching methods, te changes in the school environment, and so on, From these observed relationships, the teacher may inductively formulate a hypothesis that attempts to explain such relationships. Background knowledge, however, is essential for perceiving relationships among the variables and to determine what findings other researchers have reported on the problem under study. New knowledge, new discoveries, and new inventions should always form continuity with the already existing Corpus of knowledge and, therefore, it becomes even more essential to be well versed with the already existing knowledge. Fersons who have rich experiences and academ! ic background may formulate hypotheses Correctly, but those who have : can never formulate them. ™ acai a ——— alic logic or mathematics, This is Possible only when the researcher has a tile intellect and can make use of it for restructuring his experiences. Creative tion is the product of an adventure, sound attitude and agile intellect. In the 1eses formulation, the researcher works on numerous paths. He has to take a int effort and develop certain habits and attitudes, Moreover, the researcher Saturate himself with all possible information about the problem, then think atit, and proceed further in the conduct of the study, and Other Practices: also lead the researcher to clues that he might find useful in the n of hypotheses and for finding solutions to problems.TOS wlll be Sutficlont, sampling 18 a fundamental aspect of Statistics, Leer ea eoliection, sampling Involves chagsinyy a pe data that will result with, There aire two pon-probabillty sampling 1 but Unlike the other mathods of data mothor! or Sampling which further influences major catagorios in Sampling: Probataility and | 24.1 Meaning: Sampling Is the progass of | dlacting units (0.g., people, organisations) from a population of interest’ so that by studying the sample may fairy generalise our results back to the population trom which they ware chosen, Lot's begin by covering some of the key terns io sampling like “population® and “sampling frame." A Sampling is a part of the total population. It cah be an individual element or a group of elements selected trom the population, Although it is a subset, itis representative of the population and suitable for Tesearch in terms of cost, convenience, and time, The sample Group can be selected based on a probability or a non probability approach. A sample usually consists ot various units:of the population. The size of the sample is represented by "ni". 2.4.2 Definition: 1) Sampling may be defined as {he selection of apart of a group or an aggregate with @ view to obtaining information about the whole, A sampling mosetae is a technique of selacting a sample from a given population, 2) Sampling may be defined as ‘the act, process, or fechiigie of selecting a representative pa of population for thefBurpese of determining the charactensics of the whale population.”‘ation UB" tie prom # POPE ngs sre SETEENG OF lag Sampling is 2” Impar impact that ita have sampling, theo they are the-subject. #9 tis on the asing foundation t Some size, sampling frame, $ amplirig techniques, 3 tum: 1) Popuiation: The word population is different when 5 used in resezrch as Cone pared wita the way think cas oD under nonmal circumstances. Generally this ter aa lon of @ country (oF region), such ‘Sinattiaien ae Howe populati . Such as the in research (and the theory of sampling}, re ee : jon has a citterent meso.ee Research 7p) sets Ol Face book ortwaer fer Business ¢) Presidents and CEQs of Fonune $09 or FTSE-100 companies ¢) Nurses working at hospitals in, the State of Karmataka, gy cases(Le., organisations, institutions, Countries, ete.) a) Recruitment agencies in Mumbai, India p) Law firms in Delhi, India ®) The Jain Intemational Trade Organisation (ITO) d) The indian Parliament e) Countries that ara members of MCCIA ¢ Pieces of data a) The breaking distances (in kpmi/mi) of a particular model of car 6) University applications in the Maharashtra in 2011 ©) Households with broadband subscriptions in the town of Kolkala, West Benyal When thinking about the population, (t interest comes in studying, It is important to be precise. 2 Units: Sampling units refers to specific place or location thet can\be used during sampling process Hurtier classification of Sampling Units; ee ra lade, WAPIE lateral stein cl ona oencrn ante, Exampie. lo Above example the population of Facebook users is $00 million(or more), Sachof these Facebook users would be a‘ unit, So in population tolal there are 500 units. in the example. ! CEOs (or Presidents) of Fortune 500 companies, the CEOs (or Presidents) would be units, 6} Sometimes the word unitis teplaced with the word cases. As highlighted in the Population examples above, somtimes the populations, that are interasted in eyenaatons, institutions, and eountrias. In such cases, it is: often more. ‘appropriate t reter to each of these (eg. recnitinent agencies, Iaw firms)esearch methode = potion that consists ot only one CASE (2.9. the interé ed in? population that has many there must be hundreds), ype world Trade ae st wat isting of data (ot pleces it 5 mn mes rater 10. populations const of data) instead jts:or'oases ’ Example: ay interested in cust : time points (e. to examine u omer transactions at a particular g., 1st April 2009 and 41st March 2010): pemaps pecause Mey warit he effect of certain promotions on sales figutes- 3) Sample: ig selected fora study. In addition, itis dents of the study, af choosing @ representall part of research methodology. elements with which 10 conduct 4 called as subjects oF fespon ive portion of the enti Sampling means Process population tis an integral It involves selecting a group of people. events, behaviors, OF othe study. Example: ‘The poputation of tampet population, and only 100 students ate study. 4) Sample size: 9 BSN students are included as the ASN students fs 600, only 20 chosen as samples for the actual The size of is anit tne sample's an important problem to be dacided in case ot samei0d | This is because ine si sae has a diet beating:upon accuracy, time, cost and administration of the survey. : _ Large samples are generelly hard tp manage and cent Yor detaled study, But may be essential for teprasentativeness.Reigten se Ol) Fe nena tN Bars " a Research Methodology for Business nn any gmail, depending Uppn the ‘Sludy it ane cer ee pe fludy. The i, meas . Thi a) The type of data analysis to be dere ie ; ; b) The ses Precision ofthe estimates one wishes to achieve “ ¢) The kind and number of comparisons that will be made d) The number of variables that have to De'examined simultaneously e) How heterogeneous the ‘sampled population is. 8) Determining the Sample size Following three criteria need to be specified to determine the appropriate samples size: | @ Level of Precision: | Also called sampling error, the level of precision, is the range in which the true value ‘of the population is estimated to be. This is range is expressed in percentage points. Thus, if a fesearcher finds that 70° of farmers in the sample have adopted a recommend. technology with a precision rate of #5%, then the researcher can conclude that between 65% and 75% of farmers in the population have-adopted the new technology: b) The Confidence Level: iA, NY The confidence interval is the staiistical measure of the number of times out of 109 that results can be expected to be within a specified range. Example: A confidence: interval of 90% means that results of an action vill probably meet expectations 90% of the time. The basic idea described in Cer.tral Limit Theorem is that when a population is repeatedly sampled, the average value of an attribute obtained is equal to the true population value. In other words, ifa confidence interval is 95%, it means 95 out of 100 samples will have the true population value within range of precision.5) id atieiputes under consideration, the ition 3 is @ popul nding upon the jp fre more heterogerieo! population is, degree of variabilty varies cons! atan optimum evel of precision Note that an either 10% of 80%, This is req the larger the sample size evel of var ability th a proportion a2 that a [2092 major! is because 10% ity does not or does, and 80% means . r consideration: ample size including: using a respectively, have th g, imitating. sample size of ber of approaches to determine the $ using published table: jas to calculate a sam There are num census for smalier populations, similar studies, and applying formul Universe: The term universe is used (0 de segment.of society, so tong as it can pe replicated, c@n people, teenagers, institutional investc's, editors, politician is most relevant to t be made to identify the universe that to study the opinions of college student ple size fenate whatever body of people is being studied. Any represent a universe: elderly s, arid soon. Effort must he issue at hand li, for ts, it is necessary to example, one wishes dents, or whether it decide whether the universe should be limited to full-time stu should also include non degree and part-time students, The way in which these decisions are made wili have’an important bearing on the outcome of the survey and possibly on its usefuiness. The universe must be defined in the light of the objectives of the survey. It can be expressed .in geographical terms (locality, municipality, district, province, country oF some inte) i ; , fs intermediate category) or in sectored terms (urban population, pottery manufacturers, fuel wood producers). It is also nece: i definition of the universe, because its et ee eee E 7 ih COmpasiti ia over time: It is acssieailetihanas ion and characteristics can change a se be given spatial limits that coincide with standard or official : Qroupings (political, 2 in counties, | administrative, : 80 that its dimensions can be Natural, etc.) in common 7 ‘estimated from information alreadyced TOME. INS being the basis en which to Gavelon the sampling design ling frame is the intormaton that locates and defines the Consist of Rousing censuses and maps H, Quarter, ete; maps of forest cover With types of housing lists: in smal ocalities. Sampling trame is the actual Sé! of units from which a Sample has been drawn: in the case of a simple random sample, aii units from the Sampling frame have an equal dmensions of the universe and may grouped by locality, distre wegetation of land use or chance to, be drawn and to occur in the Sample, In the ideal case, the sampling frame should coincide with the poputation of interest. 4) A) Practical Approach for Determining the Sample Frame Expected : ‘The creation of a sample frame is critical to the Sampling process; if the trame is wrongly defined the sample will nat be representative of the target population. The frame might be ‘wrong’ in three ways - a) {it contains too many individuals, so that the Sample ftame contains the-target Population plus others who. should not be included: want to Say that the membership has been under-defined b) Mt contains too few individuals, so that typ apemple trame-contain’ the tamyet population minus some others who ought to be’ included: it said that the membership has begn ovei-defined £) It’contains the wrong set of individua's, so that the sample frame does not ‘necessarily contain the target population; It says that the membership nas been ill-defined, 8) Creating a Sample Frame is Done in Two-stages: a) Divide the Target Population Into Sampling Units. Examples of valid sampling units might include people (individuals), households, trees, light bulbs, soil or water samples, and cities,‘at make up the Target Population, e a list (for example, of names, M. Com, - Il (Sem. =~ i) b) Create a Finite Li For a discrele population thi identi numbers): ; addresses, OF identity aes ape ae e except in terms of Jes for 4 study of contamin: pola specific number of st of sampling u ntinuoUs population this ‘list! may not collected. For example, specifiabl ’ Es collecting water samp! ant levels, researchers t the sample fr 5, each contain hig case del in sale \s made u| are only able to say tha’ 50-milliliter sample bottle The sampling frame in tl rerepresents have an unlisted 9 jing @ water sample initely differs from the population. For the categories which eithe! umber, and who wi ho don't like to participate In telephone people). Such diff rest is a main cause have no a telephone example, it unde! ere not at home at the (e.g. the most poor), time of calls (e.9- employed people), e busy and active of inte ‘erences between the interviews (e.g. mor of bias in surveys sampling frame and the population and other methods aimed at random sampling. Types of sampling: The general aim of all sampling met the target population. By this it mean that, asm from the sample survey is the same (allowing for in as researcher would find if they carne population, When selecting 2 sampling method they need some minimal prior knowledge of the target population; can estimate a sample size required to achieve a reasonable estimate (with accet nods is to obtain a sample that is representative of uch as possible, the information derived evitable variations in the estimates due to imprecision) d out a census of the target with this and some reasonable assumptions they recision and a at and accuracy) of population characteristics. Two standard categories of the pling method or type exist. These two categories are called: A) Probability Sampling And B) Non-Probability Sampling: eeArea Sampiing Mutt stage Sampling A) Probability Sample : Probability sampling (a term due to Deming, [Deming}) is,a sampling process that utilises some form of random selection. Ini probability sampling, each unit is drawn with known probability, or has a non zero chance of being selected in the.sample, Guch samples are usually selected with the help of random numbers, With probability sgmpling, a measure of sampling variation can be obtained objectively from the sample itself. In probability samples, each member of the population has a known non-zero probability of being selected. Probability methods include random sampling, systematic sampling, and stratified sampling. In non probability sampling, members are selected from the population in some nonrandom manner. These include convenience sampling, judgment sampling, quota sampling, and snowball sampling. The advantage of probability sampling is that sampling error can be caleutated., : 1) Simple Kandom Sample : : Random means without any reason or without any purpose. This is a simple meaning of the worid ‘random’. In simple random sampling, each element in the poputation has an equal and independent chance of being selected. The | ii ___i_, ~~ 1)2) 3 ) esearch Methodology for Businoss 4 s ensured py allocating SOMe Probabjtiy 3 i e sample. It also makes the Selection { d size. This sampling Method jg mpl aracter of sal ing included in th of cases In the desire precisely re] representative chi each unit of population for bell possible combination ent of sample 'S le random sampling. a number of methods like lottery methog ple the population to be sampled shoulg of every presentative of the Universe bias-free. This measurem' Sampling procedures do in simp! ; elected by using dom samt 2 approximately of equal size. The sample units are S tippet’s tables. While dra\ be clearly defined. Different un! It is a simple method and {ree from! in deciding whether a particular unit can be sampling method is unsuitable if units are strictly random basis is frequently not pos: wing a ran its should bs bias. TI e representative OF not. However, random not of equal size, Selection according to ne researcher need not exercise his brain sible, as It is very difficult to have completely catalogued universe. \ ‘Systematic Sample : Systematic sampling is similar to the simple ran the first unit is selected with the help of random ni automatically according to some predetermined patt in which every K” item (e.g. every tenth item) is selecte popuilation or a stratum. The number K is called the sampling interval. The items of dom sampling. In this method oniy umbers and the rest get selected em, A systematic sample is one d in a list representing a a population are arranged in & systematic order on the basis of its important characteristics. This method is popularly used in those cases where a complete list of the population from which sample is to be drawn is available. The main advantage of systematic sampling is its simplicity, operational convenience and even spread of sample over the population. The technique is faster and less subject to error than simple random selection, Stratified Random Sample:population stratum with the help of oa Number may be taken from wach {andom sampling, The main objective i Iective in stratification is to Secure a more reliable sample, The 8 Sal success les in the strat depend on the strata, So, itis essential that should be large enou '@ must be taken note of and also that each stratum NOUN in size So that selection of items on random basis becomes and failure of the study will very much different variabl L 2H ne aa In this method, investigator has greater control over the sample Area sampling is a special form of cluster sampling in which the sample items are ¢lustered on a geographic area basis. In this kind of sampling, maps rather than lists or registers serve as basis. Within the area, the researcher may select all the members of the area or a part of the area may be selected, In the area sampling, the boundaries of the area must be well defined. Normally, a town or area is divided into: blocks and random sample is adopted to choose “blocks. Instead ‘of the researcher attempting to carry out all this exercise on his own, the divisions already existing may be preferred. Generally, governmental agencies use area sampling to collect information about the effectiveness of their programmes like education of malaria, implementation of family planning etc. Agriculture departments and other organisations connected with agriculture use area sampling extensively: for the purpose of compiling agricultural statistics. To conduct studies on a wider geographic area, area sampling is the best method. 5) Cluster Sampling: Cluster means number of persons or objects in a small or close group. When sample is selected from 2 small or close group it is called as cluster sampling. In cluster sampiing, the population is divided into clusters and random sample has been drawn either from all clusters or selected clusters, These clusters may be city- wards, social units. The sampling of clusters from the population is done by simple or stratified random sampling methods. For example, a researcher wants to study the problems of rural farmers producing onion. He wants sample of 10 per cent farmers from theResearch Methodology for Business er cent of the villages (clusters) M, Col villages in the district, He may sol in the distriot and then yse as sample w villages than to 3 in the district. ic sampling frame of all rk cost Is comparatively jow. However, the pared to sampling by elements. ject at random 10 p tor all the farmers test a group of farmers scattered at producing onion. Itis easier to test all farmers in @ fo random throughout all the village The cluster sampling is useful when bas! fe, With this sampling fieldwo! as COM! elementary units is not avallabli efficiency of cluster sampling !S less Multi Stage Sampling: ‘As the name implies this meth 6} procedure, which is carried od refers to a sampling population 1S distributed into a number of first stage f these first stage units by some suitable ther subdivided into second stage e suitable method, Further out in several stages The sampling units and a sample 's taken of these first sample units is ful en by Som if required. The method adopted in the first stage may be the method. Each o units and from these again a sample is tak stage may be added same or different for subsequent stages. Usually, multistage samples are applied to at the study can be precise Compared with simple random sampling, Multistage Sampling results in greater economy. The cost of sample preparation is greatly reduced by lists of individual big enquiries covering a considerable geographical area, so th and apt to the situation. convenience and the fact that the multistage approach does not require complete elements in the population Multistage sampling leads to more study. Each successive stage results in the reduction of the sample frame. precision in the 7) Advantages of Probability Sampling: The following are the basic advantages of probability sampling methods: a) Less Dependeticy: Probab! i lity sayio does not depend upon the existence of detailed information about the universe for its effectiveness, b) Unbiased Estimation: Probability sampling i Provides estim: i i i ala ae ales, which are essentially unbiased 204 i ne ee saneWM GOM aE ASem. + iif 6) Evaluate Thy Mla Rony eee or Binns I Is possible ow VALAtH thy folative eay, ffi when probability SAITPliNG Ie used , il ~ “si 6) Disadvantages of Probability Sampling Dewpite the great ADVANI a8 of brobaboiity, SACI WCtniANES menuonud shore It hae cortaly Weriitentienrys HSCausE of wbyoh EAI CAbY oosepepun chien Used In prig ae 160, These Nenitations ave 4) Probability SAmpliNg requires 4 vary high level A SKN) 80 wyperence for Ke use b) Itroquiras a fot of 1M6 10 plan and execute 4 p KOLADWNY Serpe, 9) Tho costs involved In Probability sampling are laryor 86 compared wy non probability bampling, B) Non. Probability Sampling Non probability Sampling oF judgment eampling depends on) Subjective judgment The Non probability method of sampling is 8 process where probabilities cannot be Assigned to the unite objectively, and hence it becomes ailfloult to detennine the rollabllity of the sample results in tors of probability. Non probability sampling ie well sulted for exploratory research intended to generate now ideas that will be Systematically taated later. However, if the 92al is to learn about a large population, it is Imperative to avoid judgment of non probabilistic Samples in survey research, Unlike probability sampling, under norprobability sampling certain elements of the Population might have a zero chance of being picked, This is because NO one can't accurately determine the chances/probabiity of picking a given glement so they do hot know whether the odds of picking that eloment are zero of Greater then zero, Non-probability gampling may Nol alvays be 4 consequence of the samplers ignorance of the total number of elements in the population but may be a result of the samplers bias in the way ho chooses the sample by excluding some elements, 1) Judgment Sampling/ Purposive Sampling: Purposive nor-probabilly sample is also known ae judgmont or judgmental I ic breaks down into three different methods; 4) Most similar/diasimilar cases, camelfon the pasis of own knowledge of the at is the population ig The individuay le population, : on ® particul *pon-randomily selected based uestions : ted to answer necessary se characteristics are select ye to select participants based on intemal useful if a researcher wants to about a “certain matter sic, This method ' ulation in which m: fall is nearly im q_ method Purposive non- ery similar but warn that knowledge of said characters! any members of the subset small subset of a larger pop umeration 0! probability samelie study “2 possible” Pilot studies are are easily identified but the ent wel suited to this type of nom jing are V _ ‘i obability samp! probability sampling and stratified pr there is a crucial difference between the two: Researchers using purposive sampling do not “select respondents randomly from each group within the stratification categories" where as stratified sampling includes ran respondents, not only those randomly selected, “who possess the characteristic are included”. Convenience Sampling : Convenience sampling is also known as accidental sampling. In this sampling, the researcher selects the cases that are easily accessible to him. For example, if one wants to study the behaviour of nurse, the researcher stands outside the hospital and ask the opinions of those who come out of the hospital about nurse's behaviour. This method is adopted to survey quickly public opinion. Convenience fina i ; si sampling is quick and economical, but the representativenese is no significant in this samplin i ae ig. Converience sampling includes participants who are ¥ available and ayree to participate in a study. Conveni ing called accidental. This is y. Convenience sampling is often . a relative! fe Siete ly easy choice for researchers when a group of be found to survey or 5 may include goi Suestion. For example ‘going to a place of business (mal : surveying those people who are aya | restaurant, etc.) and questioning TESCaICHS is inlet in vhat pony nn eet being questioned. he techniques from @ dom sampling at its core. All convenience sampllegoe mw, com.- ll (Sem. - 11) consumer Perspective Research = 9° t0 a hair salon and a barber shop ang convenience s i ment after geting their hair cut. Wha ampling includes Only those read = oe for sloppiness. iliac gen se @ Tesearchar poll those patrons leavi sie 3) Quota Sampling: Quota s i ; ampling is a method, Which is commonty used in Markating researches arr: ing ches ant election polls. It is a type of Stratified judgment sampling In quota sampling ee Of stratifie In quot 4 eines Of prefixed size are taken from each stratum of a Stratified population using judgment-sampling techniques. In this sampling, the Population is. classi according to the property under study. ied Quota is fixed according to the proportion of different clase in the population, The interviewer is assigned a quota of respondents. It is a less costly and convenient method. It can be completed in a very short period of time. However, @ i not tepresentative and it is biased sampling method Quota sampling is similar to stratified sampling only that in this case, after the population is divided into groups, the elements are then sampled from the group using the sampler's judgment, and as a consequence the method loses any aspect of being random and can be extremely biased. Quota sampling is 2 good method to use to nonrandom select groups based on gender, age, race, and ethnicity, to name a few. In Quota sampling respondents are selected non-randomly on the basis of their known proportion to the population. It divides the population group into subgroups and based on the proportions. 4) Snowballing Sampling Method: Snowball sampling is a special non-probability method used when the desres sample characteristic is rare. It may be extremely difficult or cost prohibitive to locate respondents in these situations. Snowball sampling relies on referrals from initial subjects to generate aduitional subjects. While this technique can dramatically lower search costs, it comes'at the expense of introducing bias because the technique itself reduces the likelihood that the sample will represent a good cross section from the population. — TS ~~ —CSmon nique used t jdenttly ee hn are hard t0 rocate- e initial respondents are selected py riate candidates for study wnereby "es are obtained on espondents the basig of procedu! P additional d to identify elements of rare thereafter, mee em. This technique 'S use! facturer is interested in marketing g le, a manu the market for this product is mahogany croquet set for senior adult players, aS ot vey ique | small, the researcher is required 10 use this technid! i us, he may initially survey, say 100 people using probabity ayers, he can ask them for the names of the other has advantage in term: because sample units ar for projecting data beyond sample, approp it relates to a set probability methods and * of information provi ns by referrals: Fo populatior fer to accomplish the task economically. Th samples. If he finds 10 croquet P| =" s of reduced sample sizes players. Although this technique : and costs, it involves a hgh level of bias @ not independent, le design Accordingly, it is an Inappropriate sampl Advantages of Non Probability Sampling: 5) y Sampling are as follows: The advantages of Non-probabilit Useful in Descriptive Comments: Non-probability sampling methods can be useful when descriptive comments about the sample itself are desired. There are also other circumstances, such as in applied . 5 social research, whens unfeasible or impractical to conduct probability sampling, a) b) No Need A Formal Plan Of Action : Most non-sampling methods require some effort and organization to complete, but others, like convenience sampling, are done casually and do not need a formal pian of action. More Accurate : This is more ; your aan ae because researcher are targeting a specific group, therefore similar to g answer. what the rest of the population (of this group) wil d) Less Expensive : C}M, Com. - Il (Sem, » 111) less on the bagis of Revenioh Methodology to Husinvens a non ) Probablity sampis than on the bile sample ON a protwabiity 6) Disadvantages of Non Probabitit Y Sampling; ow a) No way to Estimate the Probabil lity ; MMs . In Non-probability Sampling, since Slements are chosen Arbitrarily, there Is no way 16 estimate the Probability of any one elarn init baing includ 164 IN the sample, Alas, b) No Assurance : No assurance jis given that Gach Item has a change of being Included, making it impossible either to estimate Sampling varlability or to identity possible bias ¢) Reliability Cannot be Measured ; Reliability cannot be measured in non-probabiliy sampling; the only way to addrows data quality is to conipare some of the survey results about the population Still, there is no assurance acceptable level of error, d) No Way to Measure Precision ; with available information 6 that the estimates will mest an Statisticians are reluctant to use these methods because there is no way to measure the precision of the resulting sample. &) Assumption Based : In non-probability sampling, there is an assumption that, there is an even distribution of characteristics within the population, =e —_—,Dee etiam ne eee Co er en ed Pern een tere pie Ee eT od nd arenes Cache abet aksdeuoseduabranteaelaneecaies Can be emallar to achiove the cama Ee naan Pep aa Tas Ai a le al nee Cl tacetaedaendibaed llc temankenenedikitocata he Cee eae Ce en Ce ey od rare hada pameers tent Fe Nias et Sechaba Cee a ca eee etre ods (ae Sear teenie acetic aeccatd Paeeore ie eacaesenaaan paneiaareneep nue pebe snipes AER SS es es cd se ee Ce ee ee semaner innPr aOme inetiveorireteieE et tt ed Tine posrienor esr oe ee ‘Sampling ed lene ee tn eee eee ‘Frame Cee Taal CO Tn ee ey pin i Se Ce Re ed ce ee BT cell aid De eo + Precision: Random sampling is generally more precise than cluster sampling 6s it reduces the risk of bies due eteciie + Variability: Cluster sampling is less precise if there is high variability within clusters. + Representativeness: Cluster sampling may not be as representative of the population if the clusters are not uel aan {t's important to choose the sampling method that is most appropriate for the specific research question and: fre eerie ra) ee ee eaten Ce ne eee an ET]