Organizational Communication COM 3120
University of Central Florida
Popular in Course
Popular in Communication
This 3 page Class Notes was uploaded by Jerrod Walter on Thursday October 22, 2015. The Class Notes belongs to COM 3120 at University of Central Florida taught by John Morrison in Fall. Since its upload, it has received 13 views. For similar materials see /class/227521/com-3120-university-of-central-florida in Communication at University of Central Florida.
Reviews for Organizational Communication
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: 10/22/15
Measurement in communication research Chapter 4 basics 0 Bad data is worse than no data at all 0 Some traits are elusive very difficult to measure cheerfulness 0 Measurement as a foundation for research 0 Increasing the changes of type two error Type 1 error occurs when you find a llsignificant relationship between 2 groups only it s really not there Type 2 error occurs when your evidence shows there is no llsignificant relationship between two groups but there really is Having poor measurement is a key factor is a type two error A tenuation of results usually causes type two errors Levels of measurement 0 Nominal level Locker 6 is not better than locker 2 o Ordinal level Just know what order they came in 1 2quotd 3 but don t know the gaps in between them 0 Interval level Equal degrees between each interval 0 Ratio level Think of a speedometer Exactly like the interval level but it has a 0 Applications of levels of measurement 0 The nominal level is used when comparing groups 0 The ordinal level allows us to compare ranked categories 0 The interval level is used to compare certain percentages of things 0 Ratio level on a behavior that has the potential of O Categorical data allows us to compare categories Continuous data allows us to express things numerically Ordinal interval and ratio levels are in this category Fallacy of misplaces precision occurs when you carry numbers out and make them more precise than the numbers that generated them Reliability llam measuring consistently Contributions to unreliability o Familiar with the test form 0 Fatigue 0 Emotional strain 0 The testing environment 0 Health of the test taker 0 Memory fluxuations 0 experience of the test taker on the skill being tested 0 knowledge gained outside the test experience Assessing reliability The reliability coefficient ranges from O to 1 1 is total reliability Typically expressed as a number with a decimal point o If the number is 90 and above you have excellent 0 80 to 89 is good reliability 0 7079 is fair reliability 0 6069 is marginal reliability 0 Less that 60 is unacceptable Forms of reliability Testretest take a test more than once and receive the same answer Alternate forms several forms of the same test Split half reliability score the 1st half of the items with the score of the 2nd half Item to total reliability compare score of one item to score of the entire test Intercoder reliability comparing the times of coding Example 2 people time how many times guy looks at girl If both people have the same time it s reliability Validity llhow accurate is my measure Something can be reliable but not accurate but it reliability alone is not enough for validity Accessing validity 0 Face validity lllooks like it measures it to me 0 Expert jury validity get a bunch of experts if they think the measurement is valid 0 Criterion validity Concurent validity compare your scale to an established instrument Predictive validity compare your scale to some other way of obsessing the criteria
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'