Exam 1 Notes
Exam 1 Notes Comm 304
Popular in Mass Communications Research
Popular in Communication
verified elite notetaker
verified elite notetaker
verified elite notetaker
verified elite notetaker
verified elite notetaker
verified elite notetaker
This 25 page Study Guide was uploaded by Dara Smith on Wednesday October 14, 2015. The Study Guide belongs to Comm 304 at Pennsylvania State University taught by Sushma Kumble in Fall 2015. Since its upload, it has received 37 views. For similar materials see Mass Communications Research in Communication at Pennsylvania State University.
Reviews for Exam 1 Notes
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 10/14/15
Ch 1 Pg 216 Intro to Research Process 09022015 Mass Communication 0 Any form of communication transmitted through a medium channel that simultaneously reaches a large number of people TRADITIONAL DEFINITION Any communication channel used to simultaneously reach a large number of people including radio TV newspapers magazines billboards lms recordings books the internet and smart media REVISED DEFINITION Mass Media 0 The channels that carry mass communication Smart mass media 0 Smartphones smart TVs tablets Research 0 An attempt to discover something 0 Can be formal or informal Two basic questions a beginning researcher must learn to answer 0 1 how to use research methods and statistical procedures 0 2 when to use research methods and statistical procedures Applied data analyst researcher not the statistician 0 Does not concentrate the role of the statistician because the quotreal worldquot of mass media research usually does not require an extensive knowledge of statistics 0 Instead the real world requires an understanding of what the statistics produce how to interpret results and how to use the results in decision making 0 Learning WHAT to do with the research methods not HOW they work The Development of Mass Media Research Phase 1 The medium itself Phase 2 Uses and users of the medium Phase 3 Effects of the medium Phase 4 How the medium can be improved Scienti c Research 0 An organized objective controlled qualitative or quantitative empirical analysis of one or more variables The Methods of Knowing 0 Method of Tenacity o Follows the logic that something is true because it has always been true oThe idea is that nothing changes what was good bad or successful before will continue to be so in the future 0 Method of Intuition o A person assumes that something is true because it is quotself evidentquot or quotstands to reasonquot oTo these people scienti c research is a waste of time and their advertising effectiveness usually suffers as a consequence 0 Method of Authoritv o Promotes a belief in something because a trusted source such as a parent a news correspondent or a teacher says it is true o The emphasis is on the source not on the methods the source may have used to gain the information 0 Method of Science oThe scienti c method approaches learning as a series of small steps and unlike the other methods of knowing it has several de nable characteristics 0 Method of SelfDiscovery o Refers to things we learn and know without intervention from an outside source 0 Selfdiscovery involves using one or more of the other methods of knowing but the difference is that the discovery was made alone 0 Similar to the scienti c method without the characteristic of being public and it may be considered a subset of the method of authority where a person becomes his or her own authority based on knowledge gained from personal experience Characteristics of the Scienti c Method 0 Scienti c Research is Public 0 Science is Objective 0 Science is Empirical Science is Svstematic and Cumulative Science is Predictive Science is SelfCorrecting Concept 0 A term that expresses an abstract idea formed by generalizing from particulars and summarizing related observations 0 Typical concepts in mass media research include terms such as advertising effectiveness message length media usage and readability Concepts are important for 2 reasons 0 1 they simplify the research process by combining particular characteristics objects or people into general categories o 2 they simplify communication among those who have a shared understanding of them researchers use concepts to organize their observations into meaningful summaries and to transmit this information to others Construct o A concept that has three distinct characteristics 0 1 it is an abstract idea that is usually broken down into dimensions represented by lowerlevel concepts a construct is a combination of concepts 0 2 because of its abstraction a construct usually cannot be observed directly 0 3 a construct is usually designed for a speci c research purpose so that its exact meaning relates only to the context in which it is found Authoritarianism represents a construct de ned to describe a certain type of personality it involves nine different concepts including conventionalism submission superstition and cynicism o Authoritarianism itself cannot be seen so some type of questionnaire or standardized test is used to determine its presence Variables The empirical counterpart of a construct or concept 0 Variables link the empirical world with the theoretical they are the phenomena and events that are measured or manipulated in research Marker Variables 0 After suitable analysis the most important variables are kept and the others are discarded 0 They tend to de ne or highlight the construct under study Independent Variables Systematically varied by the researcher Dependent Variables Are observed and their values are presumed to depend on the effects in uence of the independent variables 0 DV is what the researcher wishes to explain Multivariate Analysis 0 Multiple dependent variables are measured in a single study Discrete Variable Includes only a nite set of values it cannot be divided into subpa s Continuous Variable Can take on any value including fractions and can be meaningfully broken into smaller subsections PredictorAntecedent Variable in nonexperimental research 0 The variable that is used for predictions or is assumed to be causal analogous to the independent variable Criterion Variable in nonexperimental research 0 The variable that is predicted or assumed to be affected analogous to the dependent variable Control Variable 0 Used to ensure that the results of the study are due to the independent variables not to another source De ning Variables Operationally Measurement 0 A researcher assigns numerals to objects events or properties according to certain rules 0 A Numeral has no implicit quantitative meaning it becomes a number and can be used in mathematical and statistical computations 0 Assignment is the designation of numerals or numbers to certain objects or events 0 Ex assigning the numeral 1 to the people who obtain most of their news from TV the numeral 2 to those who get most of their news from a paper 3 to other 0 Rules specify the way that numerals or numbers are to be assigned 0 They are the heart of any measurement system if they are faulty the system will be awed Measurement systems strive to be isomorphic to society lsomorphism 0 Identity or similarity of form or structure Levels of Measurement Nominal Level 0 The weakest form of measurement Numerals or other symbols are used to classify people objects or characteristics 0 Properties of the nominal level 0 Equivalence if an object is placed in category 1 it is considered equal to all other objects in that category 0 All categories are exhaustive and mutually exclusive each measure accounts for every possible options and that each measurement is appropriate for that category Ordinal Level Objects are usually ranked along some dimension such as from smallest to largest 0 Properties of the ordinal level Equivalence Interval Level When a scale has all the properties of an ordinal scale and the intervals between adjacent points on the scale are of equal value 0 Disadvantage of interval level it lacks a true zero point ex it is difficult to conceive a person having zero intelligence or zero personality Ratio Level Have all the properties of interval scales plus one more 0 The existence of a true zero point Measurement Scales A scale represents a composite measure of a variable It is based on more than one item Scales are usually used with complex variables that do not easily lend themselves to singleitem or singleindicator measurements Rating scales are common in mass media research 0 0 Researchers often ask people to rate a list of items Factor Fusion arti cially restricting the range of ratings It means that opinions perceptions and feelings are squeezed into a smaller space It is better for the respondents and the researcher to have more rating points than fewer rating points Transforming scales 0 On occasion a researcher will conduct a study using one scale and then later want to compare those data to other data using a different rating scale The procedure is always the same divide the smaller rating scale into the larger to produce a multiplier to transform the scale 0 Example to transform a 17 scale to a 1100 scale rst divide 100 by 7 which is 142857 and then multiply this number times each of the 17 elements to compute the converted 1 100 scale numbers Specialized Rating Scales Thurstone Scales Are also called Edual Appearing Interval Scales because of the technique used to develop them and are typically used to measure the attitude toward a given concept or construct Guttman Scaling Also called Scalogram Analysis is based on an ides that items can be arranged along a continuum in such a way that a person who agrees with an item or nds an item acceptable will also agree with or nd acceptable all other items expressing a less extreme position Likert Scales The most commonly used scale in mass media research Also called the Summated Rating Approach a number of statements are developed with respect to a topic and respondents can strongly agree agree be neutral disagree or strongly disagree with the statements 0 Each response option is weighted and each subjects responses are added to produce a single score on the topic Semantic Differential Scales Used to measure the meaning an item has for the individual Three general factors activity potency and evaluation were measured by this scale 0 Uses factor analysis an advanced multivariate statistical procedure 0 Reliability and Validity 0 Using any scale without preliminary testing is poor research At least one pilot study should be conducted for any newly developed scale to ensure its reliability and validity Reliability 0 A measure is reliable if it consistently gives the same answer 0 Reliability in measurement is the same as reliability in any other context 0 Ex a reliable person is one who is dependable stable and consistent over time oln understand measurement reliability there are two components a The rst represents the individual 5 quottruequot score on the measuring instrument 0 The second represents random error and does not provide an accurate assessment of What is being measured a A completely unreliable measurements measures nothing at all Reliability consists of 3 different components stability internal consistency and equivalency 0 Stability o The consistency of a result or of a measure at different points in time 0 One commonly used statistic for assessing reliability is the correlation coefficient denoted as rxx One method that uses correlation coefficients to compute reliability is the testretest method This procedure measures the stability component of reliability 0 Internal Consistency o lnvolves examining the consistency of performance among the items that compose a scale 0 If separate items on a scale assign the same values to the concept being measured the scale possesses internal consistency o For example suppose a researcher designs a 20iten scale to measure attitudes toward newspaper reading For the scale to be internally consistent the total score on the rst half of the test should correlate highly with the score on the second half of the test this method of determining reliability is called the splithalf technique Another common reliability coefficient is alpha which is sometimes referred to as Cronbach39s alpha Uses the analysis of variance approach to assess the internal consistency of a measure 0 Equivalency 0 Sometimes referred to as crosstest reliability 0 Assesses the relative correlation between two parallel forms of a test 0 Two instruments that use different scale items or different measurement techniques are developed to measure the same concept The two versions are then administered to the same group of people during a single time period and the correlation between the score on the two forms of the test is taken as a measure of the reliability 0 The less parallel the two forms the lower the reliability 0 lntercoder reliability ls used to assess the degree to which a result can be achieved or reproduced by other observers Validity 0 A measurement must have validity if it is to be of use in studying variables A valid measuring device measures what it is supposed to measure 0 Or in other words determining validity requires an evaluation of the congruence between the operational de nition of a variable and its conceptual or constitutive de nition Validity consists of 4 major components and each has a corresponding technique for evaluating the measurement method face validity predictive validity concurred validity and construct validity Face Validity o Is achieved by examining the measurement device to see whether on the face of it it measures what it appears to measure For example a test designed to measure proofreading ability could include accounting problems but this measure would lack face validity A test that asks people to read and correct certain paragraphs has more face validity as a measure of proofreading skill Predictive Validity 0 Checking a measurement instrument against some future outcome For example scores on a test to predict whether a person will vote in an upcoming election can be checked against actual voting behavior If the test scores allow the researcher to predict with a high degree of accuracy which people will actually vote and which will not then the test has predictive validity o The sole factor in determining validity in the predictive method is the measurement s ability to forecast future behavior or events correctly the concern is not with what is being measured but with whether the measurement instrument can predict something 0 Concurred Validity O Closely related to predictive validity in this method however the measuring instrument is checked against some present criterion For example it is possible to validate a test of proofreading ability by administering the test to a group of professional proofreaders and to a group of nonproofreaders If the test discriminates well between the two groups it can be said to have concurrent validity Another example a test of aggression might discriminate between one group of children who are frequently detained after school for ghting and another group the members of which have never been reprimanded for antisocial behavior 0 Construct Validity o The most complex 0 lnvolves relating a measuring instrument to some overall theoretic framework to ensure that the measurement is logically related to other concepts in the framework Ideally a researcher should be able to suggest various relationships between the property being measured and the other variables For construct validity to exist the researcher must show that these relationships are in fact present For example an investigator might expect the frequency with which a person views a particular television newscast to be in uenced by his or her attitude toward that program If the measure of attitudes correlates highly with the frequency of viewing there is some evidence for the validity of the attitude measure Therefore if an investigator nds a relationship between a measure and other variables that is predicted by a theory and fails to nd other relationships that are not predicted by a theory there is evidence for construct validity Face validity Judgmentbased Predictive validity and Concurrent validity Criterionbased Construct validity Theorybased Population and Sample The goal of scienti c research is to describe the nature of a population Population 0 A group or class of subjects variables concepts or phenomena Census 0 The process of examining every member in a population Sample 0 A subset of the population that is representative of the entire population Research Error There are two broad types of error presented in all research sampling error amp nonsampling error Sampling Error 0 Error related to selecting a sample from a population Nonsampling Error 0 Error created by every other aspect of a research study such as measurement errors data analysis errors the in uence of the research situation itself or even error from an unknown source that can never be identi ed and controlled or eliminated 0 Measurement Error a form of nonsampling error 2 ctgs 0 Random Error Relates to problems where measurements and analyses vary inconsistently from one study to another the results may lean in one direction in one study but then lean in the opposite direction when the study is repeated at a later time 0 Systematic Error Consistently produces incorrect invalid results in the same direction or same context and is therefore predictable Unlike random error researchers may be able to identify the cause of systematic errors and eliminate their in uence Types of Sampling Procedures Probability and Nonprobability Sampling 0 Probability sampling uses mathematical guidelines whereby each unit s chance for selection is know 0 Nonprobability sampling does not follow the guidelines of mathematical probability 0 The most signi cant characteristic distinguishing the two is that probability sampling aows researchers to calculate the amount of sampling error present in a research study nonprobability sampling does not 4 Issues to consider when deciding Whether to use Probability or Nonprobability Sampling 0 Purpose of the study 0 Nonprobability sampling is appropriate in research studies that are not designed to generalize the results to the population but rather to investigate the variable relationships or collect exploratory data to designs questionnaires or measurement instruments 0 Cost versus value 0 If the cost of probability sampling is to high in relation to the type and quality of info collected or the purpose of the study then nonprobability sampling is usually satisfactory 0 Time constraints 0 Probability sampling is often more time consuming than nonprobability sampling 0 Amount of acceptable error 0 In preliminary studies or pilot studies where error control is not a prime concern a nonprobability sample is usually adequate Research Volunteers Unquali ed volunteer sample 0 A type of sample is a totally selfselected nonprobability sample 0 Researchers have no control over the respondents or subjects who participate in a research study virtually anyone can participate 0 has become common in mass media research due mostly to the increased use of the internet as a data collection tool by trained researchers and people who have no research expedence Quali ed volunteer sample 0 Probability sampling is followed and the sample consists of systematically selected respondents whose names were chosen using some probability method 0 These people must qualify pass on one or more questions such as age sex use of the media etc 0 The controls which constitute a sampling frame help eliminate spurious results from respondents who should not be involved in the study Types of Nonprobability Sampling Convenience sampling 0 A collection of readily accessible subjects elements or events for study such as a group of students enrolled in a class or shoppers in a mall o Generalizability to population is low Quota sampling 0 Subjects are selected to meet a predetermined or known percentage 0 Similarly a purposive sample incudes respondents subjects or elements selected for speci c characteristic or qualities and eliminates those who fail to meet these criteria obviously not representative of the population Snowball sampling 0 A researcher randomly contacts a few quali ed respondents and then asks these people for the names of friends relatives or acquaintances they know who may also qualify for the research study TVpes of Probabilitv Samplinq Simple Random Sampling 0 Each subject element event or unit in the population has an equal chance of being selected 0 Steps 0 1 List all members of the population 0 2 Assign a number to each individual 0 3 Use a random process to select individuals from the list 0 If a subject or unit is drawn from the population and removed from subsequent selections the procedure is known as random sampling without replacement the most widely used random sampling method 0 Random sample with replacement involves returning the subject element or unit to the population so that is has a chance of being chosen another time used often in more complicated research studies such as nationwide surveys Systematic Random Sampling Begins by listing all the individuals in the population then randomly picking a starting point on the list After the rst person is selected then a researcher systematically selects every nth name on the list from that starting point Every nth subject unit or element is selected from a population Strati ed Random Sampling The approach used to get adequate representation of a subsample The characteristics of the subsample strata or segment may include almost any variable age gender religion income level etc Begin by identifying a set of subgroups or segments in the population then determine what proportion of the population corresponds to each subgroup eg a population 75 females 25 males a sample 75 females 25 males 0 Commonly used for political polls and other major public opinion surveys Can be applied in 2 different ways Proportionate strati ed sampling a nd cluster sampling Proportionate strati ed sampling includes strata with sizes based on their proportions in the population if 30 of the population is adults ages 1824 then 30 of the total sample wll be subjects in that age group 0 Disproportionate strati ed sample is considered important for marketing oversampling and over representing a particular stratum targeting Cluster sampling select the sample in groups or categories state can be divided into districts counties or ZIP code areas and groups of people can be selected from each area Advantages and disadvantages with Simple Random Sampling and Systematic Random Sampling Simple Random Sampling Advantages o 1 Detailed knowledge of the population is not required 0 2 External validity may be statistically inferred o 3 A representative group is easily inferred o 4 The possibility of classi cation error is eliminated Disadvantages o 1 A list of the population must be compiled o 2 A representative sample may not result in all cases 0 3 The procedure can be more expensive than other methods Systematic Random Sampling 0 Advantages o 1 Selection is easy 0 2 Selection can be more accurate than in a simple random sample 0 3 The procedure is generally inexpensive Disadvantages o 1 A complete list of the population must be obtained 0 2 Periodicity arrangement or order of list may bias the process Samplind Error vs Standard Error Sampling Error 0 Provides an indication of how close the data from a sample are to the population mean 0 A low sampling error indicates that there is less variability or range in the sample distribution 0 Computing sampling error is appropriate only with probability samples 0 Sampling error cannot be computed with research that uses nonprobability samples because not everyone has an equal chance of being selected 0 Based on the concept of the central limit theorem the sum of a large number of independent and identically distributed random variables or sampling distributions has an approximate normal distribution Standard Error Relates to the population and how samples relate to that population 0 If a large number of samples are selected from a population the data or statistical information from those samples will fall into some type of pattern The standard error of a statistic is the standard deviation avg difference of scores from the population mean of the sampling distribution of that statistic Standard error is closely related to sample size as sample size increases the standard error decreases Advantages of Laboratory Experiments The Experimental Method Evidenc 0 Control 0 Cost e of causality The experiment is the best social science research method for establishing causality The researcher controls the time order of the presentation of two variables and thus makes sure that the cause actually precedes the effect Researchers have control over the environment the variables and the subjects Laboratory research allows researchers to isolate a testing situation from the competing in uences of normal activity Laboratory studies also allow researchers to control the numbers and types of independent and dependent variables selected and the way these variables are manipulated The cost of an experiment can be low when compared to other research methods Replication Typically the conditions of the study are clearly spelled out in the description of an experiment which makes it easier for others to replicate Disadvantages of Laboratory Experiments The Experimental Method Arti ciality Much behavior of interest to mass media researchers is altered when studied out of its natural environment Critics claim that the sterile and unnatural conditions created in the laboratory produce results that have little direct application to real world settings where subjects are continually exposed to competing stimuli Researcher Experimenter Bias Researchers who were told what ndings to expect had results more in line with the research hypothesis than researchers who were not told what to expect 0 To counteract this problem researchers can use the doubleblind technique 0 Neither subjects nor researchers know whether a given subject belongs to the control group or the experimental group Limited Scope Many of the more interesting research topics in mass media are concerned with the collective behavior of perhaps millions of people 0 Experiments on this scale are too massive to consoluct Conducting Experimental Research Select the setting Many experiments are best conducted in a laboratory or in another environments under the direct control of the researcher oOthers are conducted in more natural surroundings where the researcher has little if any control over the experimental situation Select the experimental design Depends on the nature of the hypothesisresearch question types of variables to be manipulated or measured availability of subjects and amount of resources available Operationalize the variables In the experimental approach independent variables are usually operationalized in terms of the manipulation done to create them dependent variables are operationalized by constructing scales or rules for categorizing observations or behavior Decide how to manipulate the independent variable A set of speci c instructions events or stimuli is developed for presentation to the experimental subjects o2 types of manipulations Straightforward Manipulation and Staged Manipulation o Straightforward Manipulation written materials verbal instructions or other stimuli are presented to the subjects Staged Manipulation researchers construct events and circumstances that enable them to manipulate the independent variable Select and assign subjects to experimental conditions 0 To ensure external validity experimental subjects should be selected randomly from the population under investigation Conduct a pilot study 0 Manipulation Check a test to determine whether the manipulation of the independent variable actually has the intended effect Administer the experiment The dependent variable is measured and the subjects are debriefed Analyze and interpret the data 0 The subjects scores on the dependent variabes are tabulated and the data are analyzed Control of Confounding Variables Confounding variables extraneous variables oThese variables can be controlled through the environment experimental manipulations experimental design or assignment of subjects This section concentrates on techniques used to ensure that the groups in an experiment are comparable before the experimental treatment is administered Randomization Randomy assigning subjects to various treatment groups each subject has an equal chance of being assigned to each treatment group The variables to be controlled are distributed in approximately the same way in all groups Matching Match subjects on characteristics that may relate to the dependent variable 0 Matching by Constancy makes a variable uniform for all of the experimental groups 0 Matching by Pairing subjects are paired on a similar value of a relevant variable before being assigned to different groups Including the Confounding Variable in the Design 0 A bene t of this design is that it can provide information about the interaction the combined effects of the confounding variable and independent variable of interest Experimental Design The word design can have two different meanings o It can refer to the statistical procedures used to analyze the date and it is common to hear about an analysis of variance design or a repeated measures ttest design 0 It can refer to the total experimental plan or structure of the research it means selecting and planning the entire experimental approach to a research problem 0 Pretest gt Experimental treatment gt Posttest R represents a random sample or random assignment 0 X represents a treatment or manipulation of the independent variables so that the effects of these variables on the dependent variables can be measured 0 0 refers to a process of observation or measurement it is usually followed by a numerical subscript indicating the number of the observation 01 Observation 1 Basic Experimental Designs 0 PretestPosttest Control Group 0 O O 0 Subjects are randomly selected or assigned and each group is given a pretest However only the rst group receives the experimental treatment The difference between 01 and 02 for Group 1 is compared to the difference between 01 and 02 for Group 2 If a signi cant statistical difference is found it is assumed that the experimental treatment was the primary cause 0 PosttestOnly Control Group 0 When researchers are hesitant to use a pretest because of the possibility of subject sensitization to the posttest 0 Neither group has a pretest but Group 1 is exposed to the treatment variable followed by a posttest Solomon FourGroup Design 0 Combines the rst 2 designs and is useful if pretesting is considered to be a negative factor 0 Each alternative for pretesting and posttesting is accounted for in the design which makes it attractive to researchers Factorial Studies Factorial Designs 0 Research studies involving the simultaneous analysis of two or more independent variables each independent variable is called a factor 0 The approach saves time money and resources and allows researchers to investigate the interaction between the variables 0 Twofactor design indicates that two independent variables are manipulated o Threefactor design indicates that three independent variables are manipulatedetc Other Experimental Designs RepeatedMeasures Design o If information about the effects of multiple manipulations is desired this design is appropriate several measurements of the same subject 0 Instead of assigning different people to different manipulations the researcher exposes the same subjects to multiple manipulations o The effects of various manipulations appear as variations within the same person s performance rather than as differences between groups of people 0 Carryover effects the effects of one manipulation may still be present when the next manipulation is presented a Latin Square Design o If the researcher thinks that the order of presentation of the independent variables in a repeatedmeasures design will be a problem this design is approprate Descriptive and Analvtical Survevs Descriptive Survey 0 Attempts to describe or document current conditions or attitudes that is to explain what exists at the moment 0 The interest is in discovering the current situation in the area under study Analytical Survey Attempts to describe and explain Why situations exist Two or more variables are usually examined to investigate research questions or test research hypothesis The results allow researchers to examine the interrelationships among variables and to develop explanatory inferences Advantages and Disadvantages of Survey Research Advantages They can be used to investigate problems in realistic settings The cost of surveys is reasonable when one considers the amount of info gathered A large amount of data can be collected with relative ease from a variety of people Surveys are not constrained by geographic boundaries they can be conducted almost anywhere Data that are helpful to survey research already exist Disadvantages Independent variables cannot be manipulated the way they are in laboratory experiments Inappropriate wording or placement of questions within a questionnaire can bias results The wrong respondents may be included in survey research Some survey research is becoming difficult to conduct because response rates continue to decline Constructing Questions Five basic rules of questionnaire design Understand the goals of the project so that only relevant questions are included Questions should be clear and ambiguous 0 Questions must accurately communicate what is required from the respondents 0 Don t assume respondents understand the questions they are asked 0 Follow Ockham s Razor in question development and order Types of Questions Openended questions 0 Requires respondents to generate their own answers 0 Allow respondents freedom in answering and an opportunity to provide indepth responses Closedended questions 0 Respondents select an answer from a list provided by the researcher 0 These questions are popular because they provide greater uniformity in responses and the answers are easy to quantify General Guidelines Make questions clear Keep questions short Remember the purposes of the research Do not ask doublebarreed questions 0 Doublebarreled questions are ones that ask two or more questions in the same sentence 0 Avoid biased words or terms 0 Avoid leading questions 0 A leading question suggests a certain response or contains a hidden premise o Doubleblind question regardless of how the respondent answers an af rmative response to the hidden premise is implied ex quotdo you still use marijuanaquot Do not use questions that ask for highly detailed info 0 Avoid potentialy embarrassing questions unless they are absolutely necessary Mutually exclusive 0 There should be only one response option per question for each respondent Rating scales 0 Widely used in mass media research strongly agree 5 agree 4 etc Semantic differential scales 0 Used to rate persons concepts or objects 0 These scales use bipolar adjectives with seven scale points Rankordering 0 Used in situations where there is an interest in the relative perception of several concepts or items Checklist question 0 Often used in pilot studies to re ne questions for the nal project Forcedchoice questions 0 Frequently used in media studies designed to gather information about lifestyles and they are always listed in pairs Response rate 0 The percentage of respondents who complete the questionnaire among those who are contactedselected CATI computeraided telephone interviewing o Eliminates many problems such as skip patterns and rotation of queonns CAPI computerassisted personal interviewing o The interview is conducted in person and either the respondent or interviewer enters the info in the computer Screener questions lter questions 0 Used to eliminate unwanted respondents that is to include only respondents who have speci c characteristics or who answer questions in a speci c manner
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'