Assignment Code: MCO-03/TMA/2021-22

Course Code: MCO-03

Assignment Name: Research Methodology and Statistical Analysis

Year: 2021-2022

Verification Status: Verified by Professor

Attempt all the questions:

Q1. What is meant by business research process? What are the various stages / aspects involved in the research process? (20)

Ans) The business research process comprises investigating all areas of a firm, its customers, and the market, and then applying that knowledge to make effective business decisions. Typically, a business will examine its own strengths and weaknesses, with a focus on how customers perceive its products. When business executives research the market, they often look at significant competitors as well as the industry in which they operate.

The Importance of the Business Research Process

Question Business research, according to Pro, is the act of acquiring, analysing, and using data in order to make informed marketing decisions. A market or industry overview is frequently the first step in the business research process. The main goal is to determine whether or not there is a market opportunity. One deciding criterion could be each competitor's market share or percentage of overall industry sales.

A tiny software company, for example, may discover that it has two big competitors. Competitors A and B may have a market share of 60% and 20%, respectively. Several smaller competitors may serve the remaining 20% of the market. The software company must decide whether there is sufficient prospective business in the market to generate a significant profit. Other industry dynamics, such as government regulation, trade policy, and other industry dynamics, must also be considered.

Methods of Research Study

There are a variety of methods for conducting research. Small firms, according to Bernard Marr & Co., may easily access a wealth of important data from internal sources such as regional sales statistics, social media, text analytics, and information held in huge public databases. The website of the United States Census Bureau, for example, contains access to tools that small businesses can use to locate surveys and customise reports based on census data.

Primary research is required for companies who seek precise information about their own customers. A corporation can analyse the needs and product preferences of its own customers through primary research. A customer satisfaction survey is an example of primary research. A customer satisfaction survey can assist a business in determining how satisfied its customers are with certain product features, product prices, and even customer service.

Business Research Process Applications

The business research process comprises analysing the data and looking for specific market trends or consumer preferences after acquiring data from primary and secondary research. The important results from the data will subsequently be used by management to establish specific business or marketing plans. If clients desire extra features, for example, modifications to a product may be made. During the analysis stage, any other necessary improvements to the product, service, or entry into a new market will be determined. After that, the company will structure all of these options for possible testing.

Alternatives to Consider

From the analytical stage forward, the business research process comprises putting specific possibilities to the test. Statistical models may be used in the testing to better anticipate future client behaviour, such as their intent to purchase things. Furthermore, new market testing may entail launching a product on a small scale, analysing sales and profits, and then expanding the product to a regional or national level. The goal of testing in the business research process is to improve the likelihood of success.

Solutions and Prevention

The process of collecting data and analysing it is continuing, even though the business research process normally concludes with real decision making. Because consumer preferences and technology change, businesses should continue to obtain feedback from the market and customers.

The following are some of the most important activities engaged in the research process:

1. Choosing a research challenge or a researchable topic.

2. Expertise of current theory, as well as knowledge and activity in that field.

3. More precise definition and clarification of the research problem.

4. Forming a research hypothesis or, at the very least, research goals.

5. The sources of data must be identified.

6. Data gathering equipment such as questionnaires, schedules, and scales are designed and built.

7. nstruments will be pre-tested and perhaps revised.

8. Formal data and information collection, such as through surveys, observations, and interviews.

9. The data is processed and analysed.

10. Data interpretation and formal write-up, i.e. reporting

Q2. (a) What do you understand by the term Correlation? Distinguish between different kinds of correlation with the help of scatter diagrams. (10)

Ans) Two variables, say x and y, are said to be correlated or connected if they vary or move together in the same or opposite directions. The link between the variables is thus referred to as correlation. The association is usually found in specific sorts of variables. For instance, there is a link between income and expenditure, absenteeism and production, advertisement costs and sales, and so on. The existence of a particular sort of link may differ from one set of variables to the next. Let's use Scatter Diagrams to explain some of the correlations.

Scatter Diagram

Scatter diagrams are created when several sets of data are plotted on a graph. A scatter diagram provides two forms of information that are both quite valuable. To begin, we can look for patterns between variables that suggest whether they are linked. Second, we can determine the type of relationship that exists if the variables are related. The scatter diagram could show a variety of correlations. The image below depicts some common patterns demonstrating distinct correlations between two variables.

Possible Relationships Between Two Variables, X and Y

When both the X and Y variables move in the same direction (i.e., both rise or decrease), the relationship is considered to be positive correlation [Fig. above (a) and (c)]. If X and Y variables move in opposing directions (i.e., if variable X increases while variable Y drops or vice versa), the relationship is considered to be negative correlation [Fig. above (b) and (d)]. The relationship between them is considered to be un-correlated if Y is unaffected by any change in X variable [Fig. above (f)]. The link between them is said to be linear-correlation if the number of variations in variable X bears a constant ratio to the corresponding number of variations in variable Y [Fig. above (a) to (d)], otherwise it is non-linear or curvilinear correlation [Fig. above (e)]. Because assessing non-linear correlation for data analysis is far more difficult, we usually assume that the relationship between two variables is linear.

(b) What do you understand by interpretation of data? Illustrate the types of mistakes which frequently occur in interpretation. (10)

Ans) The definitions below can help you understand what interpretation means.

After a careful review of selected facts, the task of generating conclusions or inferences and explaining their significance is known as interpretation.

1. It's an inductive process in which you generate broad generalisations based on similarities and connections between categories and patterns.

2. The goal of scientific interpretation is to identify a link between a study's data and the study's findings and other scientific information.

3. Simply said, interpretation is the transformation of a statistical result into an understandable description.

As a result, analysis and interpretation are essential components of the research process. The goal of analysis is to summarise the obtained data, but the goal of interpretation is to identify the broader significance of the research findings. The researcher goes beyond the descriptive facts to derive meaning and insights from the data in interpretation.

It is critical to note that, if necessary, measures are not taken, errors in interpretation can occur. Data interpretation is a tough process that necessitates a high level of competence, caution, judgement, and objectivity. Without these, there's a good chance that data will be exploited to prove things that aren't true. Before evaluating the data, take the following precautions.

1. The interpreter must be objective in his or her work.

2. The interpreter must be able to see the problem in its right context.

3. He or she must recognise the significance of many aspects of the situation.

4. Ascertain that all pertinent, appropriate, and accurate data is gathered.

5. Make sure the information is correctly categorised and analysed.

6. Check to see if the data has any restrictions. If that's the case, what are they?

7. Keep an eye out for potential sources of inaccuracy.

8.  Interpretations that go beyond the information / facts should be avoided.

9. The terms "factual interpretation" and "personal interpretation" should not be used interchangeably. It's best to keep them apart.

If these safeguards are performed during the interpretation process, reasonable conclusions can be reached. The work of interpretation is not simple. It necessitates the researcher's competence and agility. Interpretation is a skill that requires effort and experience to master. For the purpose of completing the process of interpretation, the researcher may seek the advice of experts. All study interpretations must have a comparison aspect. An important component of interpretation is comparing one's findings to a criterion, or to the results of other analogous investigations, or to normal (ideal) conditions, or to current theories, or to the opinions of a panel of judges / experts.

To prevent making misleading generalisations, the researcher must complete the work of interpretation only after evaluating all important elements affecting the topic. He or she should not draw any conclusions without first gathering evidence. He/she should avoid jumping to conclusions. He or she should take all reasonable precautions to ensure that the data is properly interpreted.

Q3. Briefly comment on the following: (4X5)

(a) The recognition or existence of a problem motivates research.

Ans) Research can't move forward without a problem since there's nothing to move away from or towards if there isn't one. As a result, the initial stage in research is to identify an issue, which might be either practical or theoretical. Research is sparked by the recognition or existence of an issue. It should be emphasised that research is the process of looking for truth/facts again and over again. Investigation cannot proceed until there is a problem to look for. As a result, an issue establishes the study aim or direction. In simple terms, an issue is "some obstacle that the researcher encounters in a theoretical or practical context." The objective of study is to solve this problem."

When we don't have enough knowledge to answer a question, we have a dilemma (problem). The goal of research is to find an answer to the question or problem. "Any position or circumstance in which one does not know how to respond or what to accept as true" is what we mean by a difficulty. When we are unable to appraise something accurately, we commonly say 'it is difficult.' As a result, when a researcher chooses a topic, he or she formulates a hypothesis or posits a theoretical assumption that this or that is true, and that this or that should be done. He or she gathers evidence (facts/data) to support his or her hypothesis. He/she claims the truth or answers the question/solves the problem based on the analysis of the data gathered. In most cases, the research problem should be phrased as an interrogative. Consider the following scenario:

1. What makes product X so popular compared to product Y?

2. How can labour productivity be increased?

3. Is it true that lighting boosts productivity?

4. Why is factory A profitable but factory B is losing money?

5. Is the audio-visual system more effective than the auditory system for teaching?

All of these issues/questions are searchable. In research, the goal is to discover solutions to issues. A single question/problem may spawn a number of/a series of sub-questions.

(b) Quantitative data has to be condensed in a meaningful manner, so that it can be easily understood and interpreted.

Ans) Quantitative data must be condensed in a meaningful way so that it may be comprehended and interpreted easily. Compute statistical derivatives, such as percentages, ratios, and rates, are one of the most used strategies for condensing quantitative data. These are straightforward derivatives. In addition, the data must be summarised and analysed. The computation of Central Tendency or Average, which provides a bird's-eye view of the complete data, is the first step in that approach.

To extract relevant and useful inferences from the data, statistical derivatives such as percentage, ratio, and rates must be used to analyse the data. They also provide useful information with minimal computation. A ratio is a mathematical expression that expresses the relationship between the magnitudes of two or more quantities. It's usually written as A: B: C. The ratio of any one category to the total of all categories is known as proportion. When the number of categories grows, it's a better derivative to employ.

A rate is typically represented in terms of per 100, per 1,000, and so on. A measure of central tendency yields a single representative value that the data set clusters around. Three commonly used measures are examined in depth. The most basic of all is mode, yet it is not always specified. The median divides observations into two equal sections and is especially useful when dealing with open-ended data. Although the arithmetic mean is determined using all of the observations, it is influenced by extreme results. The mean, on the other hand, cannot be estimated for qualitative data. The terms mean, median, and mode describe the sort of data distribution. Measures of central tendency are also known as location measures.

(c) Decomposition and analysis of a time series is one and the same thing.

Ans) A time series' decomposition and analysis are the same thing. The original data, or observed data, 'O,' is the consequence of the impacts caused by long-term and short-term causes, namely (1) Trend = T, (2) cyclical = C, (3) seasonal = S, and (4) irregular = I. Decomposition of a time series is the process of determining the values for each of the components. The Additive or Multiplicative models of analysis are used to decompose the data. The assumption we make about the nature and interaction among the four components determines which of these two models should be employed in time series analysis.

Additive Model

The additive model presupposes that the four components are self-contained. The pattern of occurrence and amplitude of movements in any component are unaffected by the other components under this assumption. The four components' values are expressed in the original units of measurement in this model. Thus, the original data or observed data, ‘Y’ is the total of the four component values, that is,

Y = T + S + C + I

where, T, S, C, and I represent the trend variations, seasonal variations cyclical variations, and erratic variations, respectively.

Multiplicative Model

Itis based on the notion that the four components' causes are interrelated. As a result, the original data or observed data 'Y' is the sum of four component values, as follows:

Y = T × S × C × I

In this model the values of all the components, excluding trend values, are expressed as percentages. In most cases, the multiplicative model is more suited and employed more commonly in business research for time series analysis. Because data relating to business and economic time series is the product of the interplay of a variety of factors, none of which can be held individually accountable for any single sort of variation.

(d) Research reports are the product of slow, painstaking, and accurate work. (4X5)

Ans) Research papers are the result of meticulous, time-consuming study. As a result, the report's preparation can be divided into the following primary stages.

Comprehend and Analyse the Subject Matter in a Logical Manner

The first stage, logical understanding of the subject matter, is largely concerned with the development of a subject. A subject can be developed in one of two ways: logically or chronologically. By using logical analysis, the logical development is built on mental links and relationships between one feature and another. The development of material from the simplest to the most complicated is frequently used in logical treatment. The development of chronology is based on a link or sequence in time or the occurrence of events. The order in which instructions are given is usually chronological.

Creating the Report's Final Outline

It is the second stage of the report writing process. After you've grasped the subject, the following step is to structure the report, order the pieces, and draw them out. This stage is also known as the organising and planning stage. The author's mind may be filled with ideas. He will not be able to produce a harmonious succession until he first creates his plan/sketch/design, and he will not even know where to begin and how to end. It's partly an issue of language, but it's largely a matter of preparing and organising the report for better communication of study findings.

Rough Draft Preparation

The report's writing/drafting is the third stage. This is the most crucial stage to the researcher, as he/she now sits to write down what he/she has done in his/her research study and what and how he/she wants to communicate the same. Here, factors such as who the readers are, how technical the problem is, the researcher's command of facts and techniques, the researcher's command of language, the data and completeness of his notes and documentation, and the availability of analysed results influence the clarity in communicating/reporting.

Report Completion

This is the final, and arguably most difficult, stage of any formal writing. The structure is simple to construct but polishing and adding finishing touches takes more time. Take, for example, the building of a home. The work is swift up to the roofing (structural) stage, but it takes a long time to finish the building. While polishing and finalising the report, look for flaws in the logical progression of the subject and presentation cohesion. He or she should also look at the mechanics of writing, such as language, usage, grammar, spelling, and punctuation.

Q4. Write short notes on the following: (4X5)

(a) Comparative Scales

Ans) The direct comparison of stimulus objects is the focus of comparative scales. The respondent is frequently asked to compare one brand, product, or feature to another. Data on a comparative scale must be evaluated in terms of relative values and only have ordinal or rank order features. The following four types of scaling techniques can be applied to comparative scales:

1. Paired Comparison Scale: A paired comparison scale is a comparative scaling approach in which a respondent is presented with two objects at a time and asked to choose one object (rate between two objects at a time) based on some criterion.

2. Rank Order Scale: Another sort of comparison scaling technique is the rank order scale, in which respondents are presented with numerous objects at the same time and asked to rank them in order of priority. This is an ordinal scale that represents the objects that are preferred and those that are not but does not indicate the distance between them.

3. Scale with a Constant Sum: Respondents are asked to allocate a fixed sum of units such as points, rupees, or chips among a group of stimulus objects based on some criterion in this scale. For example, you would want to figure out how significant pricing, smell, packaging, cleaning power, and lather are to consumers when choosing a detergent. To show the relative importance of the traits, respondents may be asked to divide a constant total.

4. Scale of Q-Sort: This is a comparison scale that sorts things based on their resemblance to some criterion using a rank order approach. The key feature of this methodology is that comparing responses from various respondents is more essential than comparing responses from different respondents. The respondent is given a large number of statements to describe the attributes of a product or multiple brands of a product in this method.

   
   

(b) Purpose of a Report

Ans) A report does not contain a complete account of what was done throughout the survey/research period. It is simply a statement of the most important information that are required to comprehend the investigator's conclusions. As a result, "by definition, a report is just an account." As a result, the report provides an account of the technique used, the discoveries reached, and the conclusions reached by the problem investigator.

When an inquiry is not conducted at the request of a third party, the report may be intended for the general public. Because research is basically a collaborative effort, it is critical that each investigator be aware of what others have discovered about the phenomenon under investigation. The objective of a report is thus to disseminate knowledge and to publicise generalisations so that they might be used by as many people as possible.

A study report has only one purpose: "it must inform." It must disseminate information. Thus, the objective of a report is to explain to interested parties the study's results and findings in sufficient detail and in such a way that each reader can interpret the data and decide the validity of the conclusions for himself. The findings of research must invariably be added to the overall body of knowledge. A research report is always a valuable source of information. All of this explains why producing a report is so important.

Report writing is a skill that is used by both academics and businesses. The goal, on the other hand, could be quite different. Reports are utilised in academia for thorough and application-oriented learning. Reports, on the other hand, are used to make decisions in organisations.

(c) Binomial Distribution

Ans) It is the most basic and often used probability distribution. It's been used to describe a wide range of business processes. A quality control manager, for example, needs to determine the likelihood of receiving defective products in a random sample of ten products. He can easily obtain the answer using tables of binomial probability distributions if 10% of the products are defective. It's also known as Bernoulli Distribution, after Swiss mathematician James Bernoulli, who invented it.

The binomial distribution with parameters n and p is a discrete probability distribution of the number of successes in a series of n independent yes–no experiments, each with its own Boolean-valued outcome: success (with probability p) or failure (with probability q = 1 p) in probability theory and statistics. A single success/failure experiment is also known as a Bernoulli trial or Bernoulli experiment, and a sequence of outcomes is known as a Bernoulli process; the binomial distribution is a Bernoulli distribution for a single trial, i.e., n = 1. The popular binomial test of statistical significance is based on the binomial distribution.

In a sample of size n drawn with replacement from a population of size N, the binomial distribution is widely used to model the number of successes. Because the draws are not independent if the sampling is done without replacement, the resulting distribution is a hypergeometric distribution rather than a binomial one. The binomial distribution, on the other hand, maintains a decent approximation for N considerably bigger than n and is commonly utilised.

(d) Skewness

Ans) Skewness is a measure of the asymmetry of a real-valued random variable's probability distribution around its mean in probability theory and statistics. Positive, zero, negative, or undefined skewness values are possible.

Negative skew denotes that the tail is on the left side of a unimodal distribution, while positive skew suggests that the tail is on the right side. Skewness does not follow a simple rule when one tail is long, and the other is fat. A zero value, for example, indicates that the tails on both sides of the mean balance out in the overall distribution; this is true for a symmetric distribution, but it can also be true for an asymmetric distribution with one tail long and thin and the other short and fat.

The direction of dispersion around the distribution's centre is determined by the skewness measure. Measures of central tendency only show one representative figure of the distribution, whereas measures of variance only show the dispersion of individual values around the mean. They provide no indication of the spread's direction. Two distributions may have the same mean and variation, but the form of their distributions may be very different. Asymmetrical distributions are those in which a distribution is biassed on either side of its average. As a result, skewness denotes a lack of symmetry in a distribution. On both sides, symmetry means that the values of variables are equidistant from the average. In other words, symmetrical distribution refers to a balanced pattern of distribution, whereas asymmetrical distribution refers to an uneven pattern of distribution.

Q5. Distinguish between the following:

(a) Primary and Secondary Data

Ans) The differences between primary and secondary data is given as below:

1. The word "primary data" refers to data that was collected for the first time by the researcher. Secondary data is information that has already been obtained by investigatory authorities and organisations.

2. Primary data is current information, whereas secondary data is information from the past.

3. Primary data is gathered to solve the problem at hand, whereas secondary data is gathered for reasons unrelated to the situation at hand.

4. Primary data collecting is a time-consuming procedure. Secondary data collection, on the other hand, is quick and simple.

5. Surveys, observations, experiments, questionnaires, personal interviews, and other primary data gathering methods are used. Secondary data collecting sources, on the other hand, include government publications, websites, books, journal articles, internal records, and so on.

6. Primary data collection necessitates a significant investment of time, money, and labour. Secondary data, on the other hand, is relatively affordable and readily available.

7. Primary data is always tailored to the researcher's needs, and he is in charge of the research's quality. Secondary data, on the other hand, is not tailored to the researcher's needs, and he has no control over the data quality.

8. Primary data is available in its unprocessed state, whereas secondary data is a refined version of primary data. Secondary data is created when statistical methods are applied to primary data.

9. When opposed to secondary sources, data gathered through primary sources is more dependable and accurate.

(b) Estimation and testing of hypothesis

Ans) The differences between estimation and testing of hypothesis is given as below:

1. The approach of estimating an unknown parameter of a population using Random Samples from the same population is known as point estimation. The process of rejecting or not rejecting a statement or a hypothesis that has been established concerning the parameter is known as hypothesis testing.

2. The approach of estimating an unknown parameter of a population using Random Samples from the same population is known as point estimation. The assumption is that the parameter to be estimated is a constant with a single value, and that the sample Statistic calculated from the sample accurately estimates that value. It is represented as a point in the parameter space. As a result, the term "point estimation" was coined. A method like this is Maximum Likelihood.

3. The process of rejecting or not rejecting a statement or a hypothesis that has been established concerning the parameter is known as hypothesis testing. This is accomplished by computing a Test Statistic from the population's sample(s) and comparing it to an ideal standard value. The "risk" of reaching an incorrect judgement is predefined. This refers to the likelihood of rejecting the initial hypothesis if it is right. The Null hypothesis is the most basic hypothesis regarding the parameter, and an Alternative hypothesis is also created at the same time. The Alternative (H1) is accepted if the Null (H0) is rejected.

(c) Sampling and Non-Sampling Errors

Ans) The differences between sampling and non-sampling errors is given as below:

1. Sampling error is a statistical error that occurs when the sample used to represent the population of interest does not completely represent the population of interest. Non-sampling error occurs when survey activities are conducted and is caused by causes other than sampling.

2. The difference between the true mean value for the sample and the population causes sampling error. Non-sampling error, on the other hand, is caused by a lack of data and incorrect data processing.

3. Non-sampling error can be random or non-random, whereas sampling error can only happen in a random sample.

4. Only when a sample is taken as a representative of a population does sample error occur.

5. Non-sampling error, on the other hand, occurs in both sampling and complete enumeration.

6. Sampling error is mostly related to sample size; as the sample size grows, the likelihood of mistake reduces. Non-sampling error, on the other hand, is unrelated to sample size, hence it will not be reduced by increasing sample size.

(d) Bibliography and footnote (4X5)

Ans) The differences between bibliography and footnote is given as below:

1. Bibliographic notes provide extra sources linked to the material, whereas content footnotes provide further information about the content. The footnote is located at the bottom of the page, or at the foot. Within the body of the text, it is indicated by a superscript number. The superscript number, as well as any additional explanatory or bibliographic information, appears at the bottom of the page.

2. If specific sources are utilised to create content footnotes, they should be referenced using parenthetical citations within the footnote and then complete citation information in the Works Cited, or Bibliography, page. Bibliographic footnotes direct readers to specific, related external sources without providing much explanation. The Works Cited page should include offer complete citation information for these sources.

3. The bibliography page, often known as the Works Cited page, is the final component of a paper. It gathers all of the citation information for each source cited in or studied for the article in one place, giving your readers a comprehensive picture of the works that influenced your thought.

4. In contrast to a footnote, which may simply give the title of the work, the entire citation information found in this section tells your readers when and where a source was published. Furthermore, the bibliography contains no information other than the citation information.