Study Guide for Exam 2
Study Guide for Exam 2 COMSTRAT309
Popular in Qualitative Research Methods
verified elite notetaker
PSYC 3310 Industrial-Organizational Psychology
verified elite notetaker
Popular in Communication Studies
This 4 page Study Guide was uploaded by Linda Prado on Tuesday March 10, 2015. The Study Guide belongs to COMSTRAT309 at WSU, Washington taught by Jay Hmielowski in Fall. Since its upload, it has received 245 views. For similar materials see Qualitative Research Methods in Communication Studies at WSU, Washington.
Reviews for Study Guide for Exam 2
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: 03/10/15
Study Guide for ComStrat 309 393 Definitions gt Conceptual Constitutive Definition Dictionary definition using words to describe the concept gt Operational Definition Procedures to measure a concept I Example operational definition of artichoke go to your local grocery store and look at the produce until you find a sign that says artichoke The produce there is what an artichoke is gt Conceptual fit You want to have your Operational Definition match the Conceptual Definition Valid Measure When you are sure you are measuring what you think you are measuring gt Analogy Hitting the bullseye on a target Reliable Measure When your measurements are consistent gt Analogy Not always hitting the bullseye but hitting the same spot consistently Five Assessments of Validity gt Face Validity The measure seems to look good on the face of it it appears to relate to your research question gt Content Validity The measure captures the full range of meaning dimensions of the O 06 O 09 O 90 concept ALL aspects of the concept I A scale measuring depression should include both psychological and behavioral measures gt Criterion Predictive Validitv The measure is shown to predict scores on some other relevant future measure I IQ can predict college GPA gt Concurrent Validitv The measure differentiates between known different groups I Tests for athleticism separates those who exercise and those who don t gt Construct Validitv The measure is shown to be related to other concepts that should be related and not to ones that shouldn t I Grit should be related to effort grades determination etc not to anger shyness etc I Does not predict future events 393 Ways to Test Reliability gt Stability Consistency of measure at different points in time I T estretest measure the same thing on the same people at different intervals of time I Measures with a stronger relationship are more reliable gt Internal Consistencv measure assigns similar values I Spilthalf when the first five questions of a survey get similar scores as the second set of five questions I Cronbach s Alpha Stats that assess whether items get at the same concept gt Equivalencv Cross Test I Develop two versions of a scale different measures I Intercoder reliabilitygsee if results can be reproduced by others used a lot in content analysis 3 Independent Variable the cause and predictor 393 Dependent Variable the effect and outcome Usually reliant on the Independent Variable 39339 Levels of Measurement 9 09 O O 00 09 gt Nominal When the variable is measured with categories Numbers here are meaningless Categories must be mutually exclusive no overlap and exhaustive everything must fit into a category Measurement does not have subparts 12 46 etc This is the weakest form of measurement I Example separating silverware in a drawer Ordinal Measured with rankorder categories This tells you placement but not how far apart the rankings are I Example Rank form of entertainment from favorite 4 to least favorite 1 Interval Measurement points with equal distance between them But there is NO true zero Can have subparts I Example Temperature RLio Measurement points with equal distances between them There is a true and meaningful zero I Example How many hours of TV do you watch daily 01 12 23 etc Different Rating Scales gt Likert Scale I Measure by agreement strongly agree to strongly disagree I Measure by Frequency never to always I Measure Satisfaction completely satisfied to completely dissatisfied gt Semantic Differential Scale polar opposite scale I Good Bad I Democrat Republican Ismorphism Whether the measurement corresponds with an actual number in reality attitude or belief doesn t line up well with reality gt Example Temperature means something Control Variable Variables that are used to ensure that the results of the study are due to the independent variables not to another source Noise Variables that may create spurious or misleading results Idea Behind Measurement A researcher assigns numerals to objects events or properties according to certain rules gt Numerical Has no implicit quantitative meaning When given quantitative meaning it becomes a number and can be used in mathematical and statistical computations Assignment the designation of numerals or numbers to certain objects or events Rules specify the way that numerals or numbers are to be assigned Dummy Variable A variable measured at the nominal level that may be used in higher VVV order statistics best to worst when the numbers are not meant to rank them just name them with a number O 09 O 09 O 06 o 9 O O 06 09 I Example Democrat 1 Republican 2 Independent 3 Other 4 When selecting the type of scalel3 15 110 you want for your study consider these three things gt A scale With more points rather than fewer points allows for greater differentiation on the item or items being rated Males and females of all age groups races and nationalities like to use a 110 scale When using simple rating scales it is best to tell respondents the higher the number the gt gt more you agree Sire a composite measure of a variable Sampling Describes how you select your subjects gt Representative Probability Sampling Used to generalize to a larger population gt Nonrepresentative Nonprobability Sampling Used When you are looking for a specific characteristic can t generalized to larger population Population The entire group of people you are interested in learning about It is important to clearly define this gt Example All people living in the US over 18 years old Census When the entire population is measured This is very rare to get Types of Probability Samples gt Simple Random Sampling Obtain a list of all population members assign numbers to all members randomly select numbers until desired sample size is reached gt Systematic Random Sampling Obtain a list of all population members assign numbers to all members randomly select a start position in the list I Example select every 10th person on the list I Random Digit Dialing Start with a given area code eg 509 obtain all the given exchanges in the area code start With a number and add a predetermined mumber to generate a sample keep doing this until sample size is reached gt Stratified Random Sampling Used to get representation from a certain group Strata are variables characteristics of a group that are important to your sample I Choose strata groups your research Will focus on then randomly sample from each group until you reach your desired sample I This gets tougher the more specific you get With your groups gt Multistage Cluster Sampling Like Stratified Random Sample except you do this When you don t have a list of people I Procedure Randomly select clusters can be based off of something like zip code randomly select participants from Within the clusters Margin of Error Statistical estimate of What the population looks like how close your results are to the actual population Confidence Level How certain you are that the results fall in a given margin of error Four Issues you Should Consider When Deciding to use Probability or NonProbability Sampling gt Purpose of the study gt Cost versus value gt Time constraints gt Amount of acceptable error 3 Ungualified Volunteer Sample There are no qualifications or restrictions or restrictions related to Who gets into a sample Anyone can participate 393 Qualified Volunteer Sample volunteer sample is selected using probability sampling the type of person permitted to participate is controlled and limited 3 Sampling Frame The complete list of members in the population 39339 Seven Factors that Determine the Sample Size Required for a Study gt The research Method gt The base gure used to back in to a total sample size gt Cost and time considerations gtMultivariate studies require larger samples than do univariate studies because they involve analyzing multiple response data gtResearchers should always select a larger sample than is actually required gt Use information available in published research gt Generally speaking the lager the sample the better 339 Weighting Sample Balancing When the ideal sample size is not reached the responses of the subjects that are available are multiplied weighted to allow for the shortfall
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'