BUS204 Final Exam - Chapter 6: Beginning the Research Process PDF

**BUS204 Final Exam** **Chapter 6: Beginning the Research Process** Applied research starts with a management problem. A well-defined management provides the foundation for defining the research problem. If research is the logical next step in the decision-making or problem-solving process, we nee...

**BUS204 Final Exam** **Chapter 6: Beginning the Research Process** Applied research starts with a management problem. A well-defined management provides the foundation for defining the research problem. If research is the logical next step in the decision-making or problem-solving process, we need a research problem to guide our actions as a researcher. 1. **Research Purpose/Objectives** The goals that will be achieved by conducting research. The objective cannot be determined until there is a clear and shared understanding of the managerial decision to be made. We often describe this understanding as a **problem statement.** A good problem statement includes both a statement of the **research objective(s) and the research question(s).** The **purpose or objective of the study** explains why the study is being done. The statement of the research objective(s) should be brief, but nonetheless communicate clearly the focus of the project. **Examples of Research Objectives** - To find out what motivates consumers to buy a product online. - To study the effect of leadership style on employees' job satisfaction. - To investigate the relationship between capital structure and profitability of the firm. Once the purpose of the study has been identified, one is able to formulate the research question(s) of the study. **The research question(s)** specify what you want to learn about the topic. They guide and structure the process of collecting and analyzing information to help you to attain the purpose of your study. **Examples of Well-defined Research Questions** - To what extent do the structure of the organization and type of information systems installed account for the variance in the perceived effectiveness of managerial decision-making? - To what extent has the new advertising campaign been successful in creating the high-quality, customer-centred corporate image that it was intended to produce? - How has the new packaging affected the sales of the product? - Has the new advertising message resulted in enhanced recall? **There are three basic types of questions that research projects can address:** - Exploratory - Descriptive - And casual questions **Exploratory Research Questions** **Exploratory research questions are typically developed when:** - Not much is known about a particular phenomenon - Existing research results are unclear or suffer from serious limitations - The topic is highly complex - There is not enough theory available to guide the development of a theoretical framework Exploratory research often relies on qualitative approaches to data gathering such as informal discussions (with consumers, employees, managers), interviews, focus groups and/or case studies. As a rule, exploratory research is flexible in nature. Whereas the focus of the research is broad at first, it becomes increasingly narrower as the research proceeds. The results of exploratory studies are typically not generalizable to the population.  **Descriptive Research Questions** - The objective of a descriptive study is to obtain data that describes the topic of interest. For instance, if we want to know what percent of the population likes Coca-Cola better than Pepsi in a double-blind test, we are interested in describing consumers' taste preferences. - Descriptive studies are often designed to collect data that describe characteristics of objects (such as persons, organizations, products or brands), events or situations. - Descriptive research is either quantitative or qualitative in nature. - It may involve the collection of quantitative data such as satisfaction ratings, production figures, sales figures or demographic data, but it may also entail the collection of qualitative information. For instance, qualitative data might be gathered to describe how consumers go through a decision-making process or to examine how managers resolve conflicts in organizations. - Sometimes the researcher is interested in associations among variables to describe populations, events or situations. - For instance, a researcher might be interested in the relationship between job involvement and job satisfaction, arousal-seeking tendency and risk-taking behaviour, self-confidence and the adoption of innovative products or goal clarity and job performance. Such studies are correlational in nature. - **Correlational studies** describe relationships between variables. While correlational studies can suggest that there is a relationship between two variables, finding a correlation does not mean that one variable causes a change in another variable. **Descriptive studies may help the researcher to:** - Understand the characteristics of a group in a given situation (for instance, the profile of a specific segment in a market). - Think systematically about aspects in a given situation (for instance, factors related to job satisfaction). - Offer ideas for further probing and research. - Help make certain (simple) decisions (such as decisions related to the use of specific communication channels depending on the customer profile, opening hours, cost reductions, staff employment and the like). A close-up of a text Description automatically generated **Causal Research Questions** - Causal studies test whether or not one variable causes another variable to change. - In a causal study, the researcher is interested in delineating one or more factors that are causing a problem. - Typical examples of causal research questions are: 'What is the effect of a reward system on productivity?' and 'How does perceived value affect consumer purchase intentions?' - The intention of the researcher conducting a causal study is to be able to state that variable X (the independent variable) causes variable Y (the dependent variable). So, when variable X is removed or altered in some way, problem Y is solved (note that quite often, however, it is not just one variable that causes a problem in organizations). **In order to establish a causal relationship, the following conditions should be met:** - The independent and the dependent variable should covary(be subject to change in accordance with a variable.) - The independent variable (the presumed causal factor) should precede the dependent variable. - In order to establish causality, the researcher should control the effects of 'extraneous' variables to make sure that variation in the dependent variable is not due to factors or variables other than the independent variable included in the experiment. - **An extraneous variable** is a variable that has an unintended influence on the results of a study. Extraneous variables confound the results when they are allowed to change systematically along with the two variables being studied. Hence, such variables distort the results and make it impossible to draw meaningful conclusions from the results as they allow for alternative explanations for the results.  - Researchers often aim to answer different types of research questions in a single project. For this reason, it is quite common to conduct exploratory research before moving to descriptive or causal studies in order to develop a thorough understanding of the phenomenon under study. Indeed, the three types of research (exploratory, descriptive and causal) are often viewed as building blocks, where exploratory research lays the foundation for descriptive research and causal research builds on descriptive research. A white paper with black text Description automatically generated **There are three key criteria to assess the quality of a problem statement: it should be relevant, feasible and interesting.** - **Relevant:** A research problem is relevant if it is meaningful from a **managerial perspective**, an academic perspective or both. From a managerial perspective, research is relevant if it relates to (1) an information problem that currently exists in an organizational setting or (2) an area that a manager believes needs to be improved in the organization. From an **academic perspective**, research is relevant if: (1) nothing is known about a topic, (2) much is known about the topic, but the knowledge is scattered and not integrated, (3) much research on the topic is available, but the results are (partly) contradictory, or (4) established relationships do not hold in certain situations. - **Feasible (capable of being done or carried out)** A good research problem is relevant but also feasible. A problem statement is feasible if you are able to answer the research questions within the restrictions of the research project. These restrictions are possibly related to time and money, but also to the availability of respondents, the expertise of the researcher (a problem statement may be too difficult to answer) and the like. A frequent problem in terms of feasibility is that the problem statement is both unclear (the research objective and research questions are not precise enough and/or ambiguous) and too broad in scope. Indeed, it is important that you develop a narrowly defined research question that can be investigated within a reasonable amount of time, and with a reasonable amount of money and effort. For instance, the question 'How do consumers behave?' is far too general to investigate. - **Interesting** A third characteristic of a good research problem is that it is interesting to you. Research is a time-consuming process and you will go through many ups and downs before you present the final version of your research report. It is therefore vital that you are genuinely interested in the problem statement you are trying to answer, so that you can stay motivated throughout the entire research process. 2. **Exploratory Study** *(optional)* An **exploratory study** is used when a problem is unclear or not well-defined. Its purpose is to explore the situation, gather information, and refine the problem so it becomes easier to address. It helps researchers clarify decisions and plan the next steps effectively. Techniques: - **Secondary (historical) data**: Using existing data or records from the past. - **Previous research**: Reviewing studies already conducted on similar topics. - **Experience survey**: Asking experts or stakeholders for their insights. - **Pilot/Case Study**: Testing on a small scale or examining a specific example closely. 3. **Problem Definition** - The process of defining and developing a decision statement. - A written expression of the key question(s) that a management wishes to answer. - It must be well stated and should capture research objectives in a way that invites **multiple solutions.** **Significance of the problem definition stage:** - A problem well defined is a problem half solved. - An orderly definition of the research problem **provides direction** to the investigation. - Effective problem definition helps make sure the research objectives are **relevant and useful** - meaning the results will actually be used. - If this step falls apart, the entire research design is misguided. **Problem definition -- Translating decision statements** Translating a decision statement means breaking down a general managerial issue or decision into specific, actionable research elements. It involves identifying the symptoms, probable problems, objectives, research questions, and hypotheses to ensure the problem is well-defined and the research is directed effectively. - The research process should not begin until the problem has been clearly defined using a **decision statement**. - **Decision Statement**: the specific managerial decision to be clarified or problem to be solved. - Once the decision statement is written, the researcher can ask: "What information is needed to address this situation?" - taking us to the next stage: **research design**. **Components:** 1. **Situation**: - The bakery is struggling to establish itself in the market. 2. **Symptoms**: - Observable signs, like customers preferring national brands or hesitating to try the bakery\'s products. These indicate potential underlying issues. 3. **Probable Problem**: - The likely causes of the symptoms are explored. For instance, customers may dislike the taste or not appreciate the bakery\'s style of production. 4. **Decision Statement**: - The core managerial questions to address, such as how to attract more customers or whether to redesign the bakery for better appeal. 5. **Research Objectives**: - Define what the research aims to achieve, like identifying factors influencing customer attitudes or improving perceptions of the bakery. 6. **Research Questions**: - Specific questions that the research will answer, such as how situational factors affect taste perceptions. 7. **Research Hypotheses**: - Testable statements, such as \"Bakery\'s local products are preferred by families\" or \"An exciting atmosphere improves customer attitudes.\"  **THE RESEARCH PROPOSAL** - After you have defined the research problem, you are ready to start your research. First, however, you need to communicate the problem statement and a number of other important aspects of the study -- such as the scope of the study, the procedures to be followed, the time frame and the budget -- to all the parties involved. This brings us to the research proposal - Before any research study is undertaken, there should be an agreement between the person who authorizes the study and the researcher as to the management problem, the research problem to be investigated, the methodology to be used, the duration of the study and its cost. This ensures that there are no misunderstandings or frustrations later for either party. This is usually accomplished through a research proposal, which the researcher submits and gets approved by the sponsor, who issues a letter of authorization to proceed with the study. **Research proposal:** The **primary** **communication document** between the researcher and the research user (sponsor). - The research proposal is a written statement of the **research design** - Presents an overview of some of the basic questions that managers and researchers typically must answer when planning a research design - It always includes - *a statement explaining the [purpose of the study], and* - *a [definition of the problem], often in the form of a decision statement.* - It also outlines the research methodology with details of procedures that will be used during **each stage of the research process**. - Also includes: *schedule of costs and deadlines* - Preparation of the proposal forces the researcher to think critically about each stage of the research process. - It will go through a cycle of acceptance, modification, or rejection. - Management will evaluate in terms of the usefulness of information and budget. - The proposal must be explicit about sample selection, measurement, fieldwork, and data analysis. - Once the proposal is accepted, the researcher conducts the research, going through the appropriate steps discussed in the research design process.  A close-up of a questionnaire Description automatically generated **Example of a Research Proposal** **Research Proposal to Study Retention of New Employees** **Management Problem:** Employee turnover is 40 percent within the first three years of recruitment. This is undesirable since turnover has a negative effect on productivity, it brings about extra costs, and it leads to less profits. The management objective is to reduce undesirable employee turnover with 50 percent within the next 12 months. **Purpose of the Study:** To find a solution to the recurring problem of 40 percent employee turnover within the first three years of their recruitment, and more specifically to: - draw up a profile of the employees who quit; - assess if there are any special needs of the new recruits that require to be met; - determine the reasons for employees leaving the organization in the first three years. **Research Question:** How can small- to medium-sized firms increase the organizational commitment of their employees? **Scope of the Study:**This research analyzes the problem of high turnover of employees within small- to medium-sized firms. **Relevance of the Study** The cost of employee turnover to firms has been estimated to be up to 150 percent of the employees' remuneration package (Schlesinger & Heskett, 1991). There are both direct and indirect costs involved. Direct costs relate to leaving costs, replacement costs and transition costs, while indirect costs relate to the loss of production, reduced performance levels, unnecessary overtime and low morale. The results of this study provide managers with the means to decrease the costs of employee turnover. **The Research Design (i.e., Details of the Study)** Survey instruments. First, we will interview a small number of employees who have joined the company in the previous three years. Based on these exploratory findings, we will administer a questionnaire to all of the employees who have joined the company in the past three years. **Data collection:** The interviews will be conducted during office hours in the conference hall of the organization at a prearranged time convenient to the interviewees. The questionnaire will be given to the employees to be completed by them in their homes and returned anonymously to the box set up for the purpose by the specified date. They will all be reminded two days before the due date to return their questionnaires, if not already done. **Time Frame:** The time frame necessary for completion of this research project is approximately five months. During these five months, periodic reports will be provided on the progress being made. **Budget:** The budget for this project is in Appendix A.1 **Selected Bibliography** Bateman, T. S. & Strasser, S. (1984) A longitudinal analysis of the antecedents of organizational commitment. The Academy of Management Journal, 27(1), 95--112. Lachman, L. & Aranya, N. (1986) Evaluation of alternative models of commitments and job attitudes of professionals. Journal of Occupational Behavior, 7, 227--243. Meyer, J. & Allen, N. (1997) Commitment in the workplace: Theory, research and application. Thousand Oaks: Sage. Meyer, J., Stanley, D., Herscovitch, L. & Topolnytsky, L. (2002) Affective, continuance and normative commitment: a meta-analysis of antecedents, correlates and consequences. Journal of Vocational Behavior, 63, 20--52. 4. **Research Design**: The blueprint for fulfilling research objectives; expressing the **structure of the research** and the plan for carrying out the investigation empirically. The various issues involved in the research design and discussed in this chapter are shown comprehensively in the next figure. As may be seen, issues relating to decisions regarding the research strategy (for instance, experiments, surveys, case studies), the extent to which the study is manipulated and controlled by the researcher (extent of researcher interference), location (i.e., the study setting), the level at which the data will be analyzed (unit of analysis), and temporal aspects (the time horizon) are integral to research design. **Elements of Research design:**  Research Format **Type of Investigation** - Exploratory Study: Explore/Observe constructs - Descriptive Study: Describe or measure a construct - Comparative Study: Differentiate two or more constructs - Casual Study: Establish causality among constructs - Correlation Study: Establish correlations among constructs **Extent of Interference** - **Minimal Interference** - Research conducted in normal flow of work. - **Moderate Interference** - Researchers manipulate the work environment to control some variables under study. - **Excessive Interference** - Research conducted in an artificial (laboratory) setting. **Research Setting:** **Contrived Studies** - the studies carried out under [artificial settings], that do not simulate actual environmental conditions, for example: lab experiments. ***Non-contrived Studies*** - *studies in which the researcher inspects the activities of a subject without* *attempting to change its [natural environment].* **Time Horizon:** **Cross Sectional Studies** - a study in which various segments of a population are sampled and data are collected at a [single moment in time]. **Longitudinal Studies** - a survey of respondents [at different times], thus allowing analysis of changes over time **Unit of Analysis** The unit of analysis for a study indicates what or who should provide the data and at what level of aggregation ( a collection, or the gathering of things together) : - **Individuals (such as customers, employees, and owners)** - **Households (families, extended families, and so forth)** - **Organizations (businesses and business units)** - **Departments (sales, finance, and so forth)** - **Geographical areas** - **Objects (products, advertisements, and so forth).** **Multi-level analysis studies variables -** A problem may be investigated at more than one level of analysis. **Sample Design** - **Target Population** - Includes everyone that is eligible to participate in the study. - **Sample Size** - The number of people who will actually become part of the study - **Sampling Procedure** - The way each sampling unit would be selected to become part of the study **Data Sources** **Secondary Data** - existing data, taken through review of books, journal articles, and professional literature that relate to the management dilemma. - [Sources:] encyclopedia, articles, newspapers, websites, company records, etc. **Primary Data** - original works of research or raw data that is collected particularly for a given study. - [Sources:] Survey, Observations, Experiments, Focus groups, etc. **Research Instrument** **The instrument is the main mode of data or tool used for data collection** - Common research instruments include: - Self-Administered Questionnaires - Interview Guide **Analysis Technique** **Quantitative Studies** - a statistical study, which involves the precise count of some behavior, opinion or attitude. **Qualitative Studies** - a study that emphasizes contextual analysis of a few events or conditions and their interrelations **Chapter 7: Primary & Secondary Research Designs** **Secondary Research**: summary, collation and/or synthesis of existing research **Sources of Secondary Data -- Examples** **Internal Sources** - Accounting information - Customer complaints, warranty card returns, and other records. - Intranets: is a private, secure network used within an organization to share information, tools, and resources among its members. **External Sources** - **Libraries** - **Internet** **Publishers** **[A literature review]** is "the selection of available documents (both published and unpublished) on the topic, which contain information, ideas, data and evidence written from a particular standpoint to fulfill certain aims or express certain views on the nature of the topic and how it is to be investigated, and the effective evaluation of these documents in relation to the research being proposed" (Hart, 1998, p. 13). **The functions of a literature review in research** - **Builds on existing knowledge**: It adds to what is already known rather than starting from scratch. - **Avoids duplication**: You don\'t repeat work already done by others (no \"reinventing the wheel\"). - **Focuses on specifics**: It examines a problem from a unique angle or perspective. - **Identifies important variables**: It helps determine the factors you need to study in your research. - **Defines key terms**: Introduces and explains important terminology used in the field. - **Establishes relationships**: Explains how different variables or factors are connected. - **Improves testability and reliability**: Makes your research easier to test and replicate by being clear and thorough. - **Relates findings**: Links your study\'s results to what others have already discovered. **Reasons for reviewing the literature** - To conduct a 'preliminary' search of existing material: meaning to explore what has already been studied and find useful information related to your topic. - To organise valuable ideas and findings: It allows you to structure important concepts and results effectively. - To identify other research that may be in progress: This ensures you are aware of ongoing studies in the field. - To generate research ideas: Reviewing the literature can inspire new questions or topics for exploration. - To develop a critical perspective: It helps you evaluate existing work and form your own informed views. **Different uses for the Literature Review- Approaches used** **Deductive Approach:** - Start by reading the literature to build a framework or idea. - Then test this framework using the data you collect. **Inductive Approach:** - Begin by analyzing the data to identify patterns or ideas. - Then compare these findings with the existing literature to develop or refine theories. **Adopting a critical perspective** **Most important skills:** 1. **Evaluate what you read:** - Assess whether the information is reliable, logical, and well-supported. 2. **Connect it to other information:** - Relate what you're reading to other knowledge or ideas you already know. **Questions to ask yourself** - Why am I reading this? - What is the author trying to do in writing this? - How convincing is this? - What use can I make of this reading? The **literature search strategy** refers to a plan or method for finding relevant academic articles, books, studies, and other scholarly works related to a specific research topic. - **Parameters of your search:** Guidelines you set to focus your research, like the topic, scope, and time period. - **Keywords and search terms to be used:** Important words or phrases that describe your topic to help find relevant research. - **Databases and search engines to be used:** Online platforms or tools where you search for academic articles and studies. - **Criteria for selection of relevant and useful studies**: Rules for choosing which studies to include based on their relevance, quality, and credibility. **Four Common forms of plagiarism:** - Stealing material from another source - Submitting material written by another - Copying material without quotation marks - Paraphrasing material without documentation **Chapter 8: Survey Research** **Survey Research:** Non-experimental method used to assess attitudes, activities, opinions, or beliefs (a way to gather information by asking people about their thoughts, feelings, behaviors, or beliefs without influencing them.) **Methods:** Questionnaires- Interviews **Advantages gathering information via surveys is:** - Quick - Inexpensive - Efficient - Accurate **Interviews:** - A survey method where the researcher verbally asks the questions to the participant and then records the responses. - **Unstructured interviews:** the interviewer does not enter the interview setting with a planned sequence of questions. - **Structured interviews:** the interviewer has a list of predetermined questions to be asked of the respondents. **Questionnaires:** - A pre-formulated, written set of questions to which the respondent records his answers. - When the data needs to be collected from a [large audience], over a [wide geographical area], questionnaires are usually the cheapest option. **Questionnaires can be collected** - In person - Through mail - Online (e-mail & web-based) Errors in Survey Research **Random Sampling Error** - A statistical fluctuation that occurs **because of chance** variation in the elements selected for a sample. **Systematic Error** - Error resulting from imperfections in **research design or its execution,** resulting in: - *Respondent Error: non-response, self-selection, etc.* - *Administrative Error: data processing error, sample selection error, etc.* - **Respondent Error**: Mistakes or biases that happen because some people don\'t respond, or they choose to participate based on personal preference. - **Administrative Error**: Mistakes made during the process of organizing or handling the survey, like errors in data entry or choosing the wrong group of people to survey. Observation Research: The systematic process of recording actual behavioral patterns of people, objects, and events as they happen. Observation Studies: **Visible Observation** - Observation in which the observer's presence is known to the subject. **Hidden Observation** - Observation in which the subject is unaware that observation is taking place. What Can Be Observed? - Physical actions - Verbal behavior - Expressive behavior - Temporal patterns - Physical objects - Verbal and pictorial records What Cannot Be Observed? - Observation can describe the event that occurred but cannot explain **why the event occurred**. - **Long processes** are difficult to observe, as observation over long periods is expensive or even impossible. Advantages of Observation Studies - Data are free from distortions, inaccuracies, or other response biases. - Data are recorded when actual and nonverbal behavior takes place (Observations capture real-time actions and behaviors, including body language or facial expressions, which can\'t be faked.) When is Observational Research appropriate? - Commonly performed **in public** where others can observe the behavior. - The behavior is performed in a setting that **assures the anonymity** of the person being observed. - The observed person has **agreed to be observed**. **Chapter 9: Sampling** **Sampling:** the selection of a subset of individuals from within a population **Census**: An investigation of all individual elements that make up a population. A **census in research** is the process of collecting data from every single member of a population, rather than just a sample. It\'s a complete survey of everyone in the group you\'re studying. **Why a sample:** **Pragmatic Reasons** (practical considerations or real-world limitations that influence a decision. In research, it means choosing a course of action that is realistic, feasible, and efficient given factors like time, budget, and access to resources.) - Budget and time constraints - Limited access to total population **Accurate and Reliable Results** - Can yield reasonably accurate information - More reliable than the population due to fewer chances of errors **Destruction of Test Units** - Necessary if there are limited number of units to study (If there are limited test units and using them would destroy or deplete them, researchers may choose to study a smaller sample instead of the entire group. This approach helps preserve the remaining units while still providing useful data.) A diagram of a diagram of a group of people Description automatically generated **Results obtained from a sample are expected to be true for the rest of the population** **Sampling Process** - Target population - Sampling frame - Sample size - Sampling techniques **Definition the target population** - Universe of elements relevant to the research (refers to the entire group or population that is relevant to the research and from which the sample will be drawn. It includes all individuals, items, or units that could potentially be part of the study) - Includes everyone that can participate in the study. **Sampling Frame:** a [list of elements] from which a sample may be drawn; also called working population Population: The entire group you\'re interested in studying. Sampling Frame: A list of individuals or items from the population that you can actually access and use to select your sample. It\'s like a practical version of the population. Sample: A smaller group taken from the sampling frame, which you actually study. It's a subset of the sampling frame, chosen to represent the larger population. **Sample Size** - The number of people who will actually become part of the study. - **Sample size depends on:** - Available Resources (time and money) - Required Response Rate - Population Heterogeneity (refers to the diversity or differences within a population) - Type of Analysis **Sampling Technique** - Method for choosing sample units - Researchers choose between **Probability and Non-Probability** Techniques  **Probability** 1. **Simple Random Sampling** - Where each element in the population has an equal chance of being included in the sample. 2. **Systematic Sampling** - A starting point is selected by a random process and then every nth number on the list is selected (for example, every 5th person). It's a way to choose a sample in an orderly, spaced-out manner. 3. **Stratified Sampling** - Divides the population into separate groups, **called strata,** then randomly selects the final subjects **proportionally** from the different strata. - **Stratified sampling** means you first divide the population into different groups based on certain traits (like age or gender), then randomly pick people from each group, making sure each group is represented fairly. 4. **Cluster Sampling** - The total population is divided into groups (or clusters) and a simple random sample of the groups is selected. - Each cluster is considered a sampling unit. - It is the most time-efficient and cost-efficient probability design for large geographical areas A table with black text Description automatically generated **Non-probability sampling** 1. **Convenience Sampling** - Obtaining those people or units that are most conveniently available. - means selecting people or items that are easiest to reach or access, like choosing people who are nearby or readily available, rather than randomly selecting from the entire population. 2. **Quota Sampling** - A **form of stratified sampling** where predetermined proportion of people are sampled from different groups but on a convenience basis. - a type of sampling where you divide the population into groups (like age or gender) and then select a certain number of people from each group. However, instead of randomly picking them, you choose people who are easiest to access. 3. **Judgment (Purposive) Sampling** - An experienced individual selects the sample based on personal judgment when the information needed can only be gained from specific people. - is when an expert or researcher picks the sample based on their knowledge, choosing specific people who are believed to have the most relevant information for the study. 4. **Snowball Sampling** - A sampling procedure based on **chain referrals.** - Initial respondents are selected by the researcher, and additional respondents are obtained from information provided by the initial respondents. - is when the researcher starts with a few people, and then those people refer others who fit the study criteria. This continues, creating a \"chain\" of referrals to find more participants.  The **appropriate sample design** depends on several factors: - **Degree of accuracy**: How precise the results need to be. - **Resources**: The amount of money, tools, and support available for the study. - **Time**: How much time you have to complete the research. - **Advanced knowledge of the population**: How well you understand the group you\'re studying. - **National versus local project**: Whether the study is on a national or local scale, which affects how you select the sample. **Chapter 14: Validity and Reliability** **Goodness of measures:** A test of quality that ensures that the instrument we use to measure a particular construct is in fact - Measuring the variable accurately, and - Targeting precisely the variable that we intend to measure. It helps ensure that we have not overlooked some important dimensions and elements or included some irrelevant ones. A diagram of a company Description automatically generated **Reliability:** - The extent to which the measure is without bias (error free). - It ensures **consistent results** over time and across the various items in the instrument.  **Reliability -- Stability** **Stability** indicates that when a scale is administered multiple times, it yields similar results. It can be assessed using: - ***[Test--Retest Reliability]*:** repetition of the same measure at a different time and comparing results. A person with a clipboard and a question mark Description automatically generated - ***[Parallel-Form Reliability]**:* comparing results of two similar sets of measures tapping the same construct.  **Test--Retest Reliability**: This is when you take the same test at two different times and check if the results are consistent. **Parallel-Form Reliability**: This involves comparing results from two different versions of a test that measure the same thing. It checks if the measures are similar and consistent. **Reliability -- Consistency** **Consistency** indicates the [similarity between the items] used to measures the given construct. It can be assessed using: - [Inter-Item Reliability]: check whether responses to all items measuring a single construct are similar. - [Split-Half Reliability]: comparing responses between two halves of an instrument. ( the test is divided into two halves, and the results from each half are compared to check consistency.) split-half looks at one test divided, while parallel-form compares two separate tests. - The extent to which we are sure that we are measuring what we wanted to measure. - The degree to which the **correct construct** is being studied. **Content Validity:** ensures that the construct is being measured adequately (completely). - It is an assessment of the dimensions and elements. - It is commonly assessed using: ***[Face validity]*** refers to how much a test or survey appears to measure what it's supposed to, just by looking at the questions or items. If it looks like it's measuring the right thing at first glance, it has face validity. **Criterion Validity:** is the ability of a measure to differentiate individuals based on the criteria it measures/predicts. **An instrument with high criterion validity would** - Identify [current differences] between people who are actually different. - Predict [future difference] between people who are actually different.  A close-up of a person Description automatically generated **Construct validity:** is an assessment of how well you translated the construct into dimensions and elements. - *Constructs which are [theoretically related], should get highly correlated results.* - *Construct which are [theoretically unrelated], should get results that uncorrelated.*  **Goodness of measures:** **Reliability -** how consistently an instrument measures whatever concept it is measuring. **Validity -** how well an instrument measures the intended concept. Together, reliability and validity of the measure attest to the [scientific rigor] that has gone into the research study. Scientific rigor refers to the strictness and accuracy with which research is conducted. It ensures that the methods, procedures, and analysis are thorough, reliable, and unbiased, leading to valid and trustworthy results. A diagram of a target Description automatically generated  **Questionnaire design** - A questionnaire (survey) is only as good as the questions it asks---ask a bad question, get bad results. - Composing a good questionnaire appears easy, but it is usually the result of long, painstaking work. - The questions must meet the basic criteria of relevance and accuracy. **Decisions in Questionnaire Design** - *What should be asked?* - *How should questions be phrased?* - *How should the questions be arranged?* - *What questionnaire layout to use?* - *How should the questionnaire be pretested?* - *Does the questionnaire need to be revised?* **Guidelines for Constructing Questions** - Avoid complexity: Use simple, conversational language. - Avoid leading and loaded questions. - Avoid ambiguity: Be as specific as possible. - Avoid double-barreled items. - Avoid making assumptions. - Avoid burdensome questions that may tax the respondent's memory. - Make certain questions generate variance. **Common Rating Scales**