Ch3 Variables and Hypothesis Language of Research Success of Research Clear conceptualization of concepts Shared understanding of concepts What is a Variable? Difference between concepts or characteristics Relationship between concepts or characteristics Variances: Square or standard deviation Deviations: Differences between the standard deviation and the mean Variability: Extent of scores being different from one and other Operational Definitions How can we define the variable “class level of students”? Freshman Sophomore Junior Senior < 30 credit hours 30-50 credit hours 60-89 credit hours > 90 credit hours Operational definitions are definitions stated in terms of specific criteria for testing or measurement. The specifications must be so clear that any competent person using them would classify the objects in the same way. If a study of college students required classifying students by class level, a definition of each category would be necessary. Students could be grouped by class level based on self-report, number of years in school, or number of credit hours completed. Credit hours is the most precise measure. A Variable Is the Property Being Studied Act Event Variable Characteristic Trait Attribute In practice, the term variable is used as a synonym for the property being studied. In this context, a variable is a symbol of an event, act, characteristic, trait, or attribute that can be measured and to which we assign categorical values. The different types of variables are presented on the following slides. Types of Variables Dichotomous Male/Female Employed/ Unemployed Discrete Ethnic background Educational level Religious affiliation Continuous Income Temperature Age For the purposes of data entry and analysis, we assign numerical values to a variable based on that variable’s properties. Dichotomous variables have only two values that reflect the absence or presence of a property. Variables also take on values representing added categories such as demographic variables. All such variables are said to be discrete since only certain values are possible. Continuous variables take on values within a given range or, in some cases, an infinite set. Types of Variables Quantitative: Numerical degree of difference Qualitative (categorical): Difference or relationship between experiments, treatments, or methods Independent: Influence or affect on other variables (treatments or experiments) Dependent: Affected or expected to be affected by the independent variable (the criterion or outcome variables Manipulated: Treatments or experiments Types of Variables (continued) Select: Variables that already exits that the researcher may want to use in their study Extraneous: Variables that occur without control Types of variables Forms: continuous variable & categorical variable Sources: active variable & attribute variable Relationships: Independent variable、dependent variable 、moderator variable 、control variable 、confounding variable & intervening variable Independent and Dependent Variable Synonyms Independent Variable (IV) Dependent Variable (DV) Predictor Criterion Presumed cause Presumed effect Stimulus Response Predicted from… Predicted to…. Antecedent Consequence Manipulated Measured outcome Exhibit 3-2 Exhibit 3-2 presents the commonly used synonyms for independent and dependent variables. An independent variable is the variable manipulated by the researcher to cause an effect on the dependent variable. The dependent variable is the variable expected to be affected by the manipulation of an independent variable. The Relationship between Independent and Dependent Variables Independent Variables Dependent Variable (s) (presumed or possible cause) (presumed Results) Relationships Among Variable Types Relationships Among Variable Types Relationships Among Variable Types Moderating Variables (MV) The introduction of a four-day week (IV) will lead to higher productivity (DV), especially among younger workers (MV) The switch to commission from a salary compensation system (IV) will lead to increased sales (DV) per worker, especially more experienced workers (MV). The loss of mining jobs (IV) leads to acceptance of higher-risk behaviors to earn a familysupporting income (DV) – particularly among those with a limited education (MV). Moderating variables are variables that are believed to have a significant contributory or contingent effect on the originally stated IVDV relationship. Whether a variable is treated as an independent or as a moderating variable depends on the hypothesis. Examples of moderating variables are shown in the slide. Extraneous Variables (EV) With new customers (EV-control), a switch to commission from a salary compensation system (IV) will lead to increased sales productivity (DV) per worker, especially among younger workers (MV). Among residents with less than a high school education (EV-control), the loss of jobs (IV) leads to high-risk behaviors (DV), especially due to the proximity of the firing range (MV). Extraneous variables are variables that could conceivably affect a given relationship. Some can be treated as independent or moderating variables or assumed or excluded from the study. If an extraneous variable might confound the study, the extraneous variable may be introduced as a control variable to help interpret the relationship between variables. Examples are given in the slide. Intervening Variables (IVV) The switch to a commission compensation system (IV) will lead to higher sales (DV) by increasing overall compensation (IVV). A promotion campaign (IV) will increase savings activity (DV), especially when free prizes are offered (MV), but chiefly among smaller savers (EV-control). The results come from enhancing the motivation to save (IVV). An intervening variable (IVV) is a factor that affects the observed phenomenon but cannot be measured or manipulated. It is a conceptual mechanism through which the IV and MV might affect the DV Research Hypothesis Definition -- A predication regarding a possible outcome -- A declarative sentence that conjectures a relationship between two or more variables (statement) -- Well stated hypotheses are derived from the research question or problem -- You need a rationale for making predictions or a hypotheses 1. The review of the literature 2. Theory Research Hypothesis (continued) -- Differences between directional and non-directional hypotheses 1. A directional hypothesis show a significant difference between two or more variables and usually uses inferential statistics in its analysis 2. A non-directional hypothesis shows that there is a difference or a relationship between two or more variables and usually uses descriptive statistics or qualitative research to analyze the data Propositions and Hypotheses Brand Manager Jones (case) has a higherthan-average achievement motivation (variable). Generalization Brand managers in Company Z (cases) have a higher-than-average achievement motivation (variable). A proposition is a statement about observable phenomena that may be judged as true or false. A hypothesis is a proposition formulated for empirical testing. A case is the entity or thing the hypothesis talks about. When the hypothesis is based on more than one case, it would be a generalization. Examples are provided in the slide. Hypothesis Formats Descriptive Hypothesis In Detroit, our potato chip market share stands at 13.7%. American cities are experiencing budget difficulties. Research Question What is the market share for our potato chips in Detroit? Are American cities experiencing budget difficulties? A descriptive hypothesis is a statement about the existence, size, form, or distribution of a variable. Researchers often use a research question rather than a descriptive hypothesis. Examples are provided in the slide. Either format is acceptable, but the descriptive hypothesis has three advantages over the research question. Descriptive hypotheses encourage researchers to crystallize their thinking about the likely relationships. Descriptive hypotheses encourage researchers to think about the implications of a supported or rejected finding. Descriptive hypotheses are useful for testing statistical significance. Relational Hypotheses Correlational Young women (under 35) purchase fewer units of our product than women who are older than 35. Causal The number of suits sold varies directly with the level of the business cycle. An increase in family income leads to an increase in the percentage of income saved. Loyalty to a grocery store increases the probability of purchasing that store’s private brand products. A relational hypothesis is a statement about the relationship between two variables with respect to some case. Relational hypotheses may be correlational or explanatory (causal). A correlational hypothesis is a statement indicating that variables occur together in some specified manner without implying that one causes the other. A causal hypothesis is a statement that describes a relationship between two variables in which one variable leads to a specified effect on the other variable. The Role of Hypotheses Guide the direction of the study Identify relevant facts Suggest most appropriate research design Provide framework for organizing resulting conclusions Characteristics of Strong Hypotheses Adequate A Strong Hypothesis Is Testable Better than rivals Theory within Research Exhibit 3-5 What is the difference between theories and hypotheses? Theories tend to be complex, abstract, and involve multiple variables. Hypotheses tend to be simple, limited-variable statements involving concrete instances. A theory is a set of systematically interrelated concepts, definitions, and propositions that are advanced to explain or predict phenomena. To the degree that our theories are sound and fit the situation, we are successful in our explanations and predictions. The product life cycle, shown in Exhibit 3-5, is an example of a theory. The Role of Reasoning Exhibit 3-7: Business models are developed through the use of inductive and deductive reasoning. As illustrated in Exhibit 3-7, a business model may originate from empirical observations about market behavior based on researched facts and relationships among variables. Inductive reasoning allows the modeler to draw conclusions from the facts or evidence in planning the dynamics of the model. The modeler may also use existing theory, managerial experience or judgment, or facts. The Scientific Method Direct observation Clearly defined variables Clearly defined methods Empirically testable Elimination of alternatives Statistical justification Self-correcting process Good business research is based on sound reasoning because reasoning is essential for producing scientific results. This slide introduces the scientific method and its essential tenets. The scientific method guides our approach to problem-solving. An important term in the list is empirical. Empirical testing denotes observations and propositions based on sensory experiences and/or derived from such experience by methods of inductive logic, including mathematics and statistics. Researchers using this approach attempt to describe, explain, and make predictions by relying on information gained through observation. The scientific method is described as a puzzle-solving activity. Researchers Encounter problems State problems Propose hypotheses Deduce outcomes Formulate rival hypotheses Devise and conduct empirical tests Draw conclusions Sound Reasoning Types of Discourse Exposition Deduction Argument Induction Exposition consists of statements that describe without attempting to explain. Argument allows us to explain, interpret, defend, challenge, and explore meaning. There are two types of argument: deduction and induction. Deduction is a form of reasoning in which the conclusion must necessarily follow from the premises given. The next slide provides an example of a deductive argument. Induction is a form of reasoning that draws a conclusion from one or more particular facts or pieces of evidence. Slide 2-8 illustrates an inductive argument. Deductive Reasoning Inner-city household interviewing is especially difficult and expensive This survey involves substantial inner-city household interviewing The interviewing in this survey will be especially difficult and expensive © 2002 McGraw-Hill Companies, Inc., McGraw-Hill/Irwin Inductive Reasoning Why didn’t sales increase during our promotional event? Regional retailers did not have sufficient stock to fill customer requests during the promotional period A strike by employees prevented stock from arriving in time for promotion to be effective A hurricane closed retail outlets in the region for 10 days during the promotion Why Didn’t Sales Increase? Exhibit 3-8 Induction and deduction can be used together in research reasoning. Induction occurs when we observe a fact and ask, “Why is this?” In answer to this question, we advance a tentative explanation or hypothesis. The hypothesis is plausible if it explains the event or condition (fact) that prompted the question. Deduction is the process by which we test whether the hypothesis is capable of explaining the fact. Exhibit 3-8 illustrates this process. Tracy’s Performance Advantages of using a Hypothesis Helps the researcher think more clearly and careful about what it is you are investigating (keeps you focused) Helps the researcher think more deeply and specifically about the possible outcomes (critically evaluating what you are doing and how you are doing it, emphasizing the precise nature of the study) It makes for specific predictions based on prior evidence or theory arguments. Helps the researcher to see or not to see the relationships or differences between variables Disadvantages of using a Hypothesis In qualitative research stating the hypothesis would unnecessary before the research begins because it is difficult to predict what the findings might be It creates a bias by helping the researcher to arrange procedures and/or manipulate the data to bring about a desired outcome. The hypothesis may take the attention away from noticing other things that might develop through the research. Hypothesis Check List Do your hypotheses suggest the relationship between two or more variables? Do your hypotheses specify the nature of the relationship? Do the hypotheses imply the research design to be used ton study the relationships? (differences relationships, significance)? Are the hypotheses free of mentioning specific measures? Are the hypotheses free of unnecessary methodological detail? Have you kept your hypotheses to manageable number? (five or fewer)