Behavior & Statisitcs 4
Behavior & Statisitcs 4 Psychology 211
Popular in Behavioral Statistics
Popular in Psychlogy
verified elite notetaker
This 3 page Class Notes was uploaded by Alexis Notetaker on Monday February 29, 2016. The Class Notes belongs to Psychology 211 at Southern Illinois University Carbondale taught by Zachary Pilot in Spring 2016. Since its upload, it has received 8 views. For similar materials see Behavioral Statistics in Psychlogy at Southern Illinois University Carbondale.
Reviews for Behavior & Statisitcs 4
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: 02/29/16
Psy Notes 4 Wednesday, February 17, 2016 10:44 AM How to measure behavior • Scales of measurement ○ Ratio Interval □ Ordinal Nominal • Nominal ○ Numbers are assigned as labels for characteristics or behavior ○ Provides the least amount of information Ex. Race, Countries • Ordinal ○ The ran ordering of peoples behaviors or characteristics ○ Does not tell us the distance between participants on the variables being measured Ex. From small to big • Interval ○ Equal differences between the numbers reflect equal difference between participants ○ No true zero point Ex. Temperature • Ratio ○ Contains a true zero point ○ Provides the greatest amount of information ○ Should be used when possible Ex. Distance Central Tendency(chapter 3) • A descriptive measure which represents the entire distribution of scores ○ Mean : Interval and Ratio ○ Median: Interval, Ratio and Ordinal ○ Mode: All of them • You con condense a large set of data into a value • Compare 2 + sets of data by comparing the central tendency for one set vs another set The mean (or average) • Most common used measure of central tendency ○ Interval or Ratio scales ○ How to compute Compute the sum of all scores ( E) Divide the sum by the number of score ○ In manuscripts, the sample mean is identified as "M" How to measure behavior(leary3) • Measurement error ○ Variability in scores due to factors that distort the true score Can be measured • True score ○ The score a participant would obtain if a measure were perfect and we could measure without error Can't be measured Can't be measured Sources of measurement • Transient states ○ Temporary Something that changes on a day to day ○ Stable attributes Lasting □ Something that is about someone ex. Depression ○ Situational factors Research setting □ Something in the environment that could change the participants performance ○ Characteristics of the measure To long ○ Mistakes in recording Incorrect data □ A person with hearing lost Reliability • Consistency/dependability of the measuring technique • Reliability has an inverse relationship with measurement error • If observed scores are close to true scores the measure has high reliability ○ Measured over time Assessing reliability • Researchers determine if two or more measurements of the same behavior • Estimated using a correlation coefficient Test-Retest Reliability • Consistency of participates' Reponses on a measure over time ○ Use the same measure twice ○ Examine the correlation between the two ○ Correlation > .70 is considered acceptable ○ Useful only if dat being measured should not change over time Interrater Reliability • The consistency among researchers who observe and record behavior Interitem Reliability • Consistency between the items on a scale • Tells us whether all items on a scale are measuring the same thing ○ If not, measurement error increases and reliability decreases Indices of Interitem Reliability • Item-total correlation ○ The correlation between one item and the sum of all the other items on scale • Split-half reliability ○ Divide the items on a scale into two sets and examine the correlation between the sets • Cronbach's alpha coefficient (*alpha sign*) ○ The average of all possible split-half reliabilities Most frequently *Alpha sign* >.70 is considered acceptable Increasing Reliability • Standardize administration of the measure • Clarify instructions and questions • Train observers • Minimize error in coding data Validity Validity • Actually measures what it is intended to measure • Do differences in score reflect difference in what we are trying to measure? ○ I am I actually measuring what I am actually measuring? Face, Construct, Convergent, Discriminant Forms of Validity • Face Validity ○ Appears to measure what it's supposed to measure Just because something has a face validity doesn't mean that it is valid Some measures are designed to lack face validity to disguise their true purpose □ Does not actually impact true validity • Construct Validity ○ Measure of hypothetical constructs relates a it should to other measures ○ Hypothetical constructs Something that can not be directly observed but is inferred based on experience ○ Convergent validity Correlates with measures it should correlate with ○ Discriminant validity Does not correlate with other measures that it should not correlate with Fairness and Bias • Test bias occurs when a particular measure is not equally validity for everyone ○ The question is not whether various groups score different on the test ○ When the validity of measure is lower for some groups than for others
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'