Psych 301 Exam 2 Review Final PDF

Preview

Summary

Quiz...

Description

Prof. Saponjic Psych 301 Exam 2 Review

Spring 2020

1. Your friend Dominic is complaining about having to take the Graduate Record Examination (GRE), a test that is required to go to graduate school and is similar to the ACT and SAT. He complains, “Tests like the GRE don’t really measure how well people actually do in graduate school.” Dominic is questioning the ___________of the test. a. discriminant validity b. content validity c. convergent validity d. criterion validity 2. Dr. Smith, a developmental psychologist, is planning on conducting a study that involves watching children play together to determine how sharing behavior occurs in same-sex friend pairs compared to opposite-sex friend pairs. Dr. Smith decides to collect his data at a neighborhood park. He has his two research assistants pose as a married couple having a picnic. While having their picnic, they take detailed records of the sharing behavior of the children and note whether the pairs are same sex or opposite sex. Given his use of two research assistants, he must establish the ___________ of their measures. a. face validity b. convergent validity c. interrater reliability d. test-retest reliability 3. Studies that use nonprobability samples have _______ external validity. a. zero b. unknown c. guaranteed d. enhanced 4. Why do studies that use probability samples have excellent external validity? a. They also ensure excellent internal validity. b. They study every member of the population of interest. c. They use a larger number of measures. d. All members of the population are equally likely to be represented in the sample. 5. Dr. Chandler is a personality psychologist who is interested in studying the characteristics of people who report being abducted by UFOs. She finds several people in an online support group for UFO abductees to participate and asks them if they can provide the names and contact information of other people who have also been abducted. Upon contacting these new participants, she asks them to refer her to even more people they may know who have been abducted. This is an example of what kind of sampling? a. Purposive sampling b. Snowball sampling c. Convenience sampling

d. Self-selection sampling 6. If researchers measure every tenth member of a population, they have: a. conducted a census. b. collected a sample. c. increased internal validity. d. biased the study. 7. What is an advantage of open-ended questions? What is a disadvantage? An advantage of open-ended questions is the vast amount of information the researcher gathers that provides detailed responses from the respondents- they can express themselves freely in answering the questions. The disadvantage is time consuming- it takes time to process the data because researcher have to read and analyze the answers and put them into categories. And there is a possibility of researcher bias because he/she analyzes the data subjectively. 8. List, describe, and give an example of one type of reliability. Test-retest (.70) – refers to the extent to which a test administered at one time is correlated with the same test administered to the same person at another time. It is the most common measure of reliability. In order to measure the test-retest reliability, we have to give the same test to the same person on two separate occasions. For example, Me taking and exam. The first time I took the exam, I refer it as exam #1 and the second time as Exam 2. The scores on the two occasions are then correlated. The closer my scores are on Exam 1 and Exam 2, the test measure is more reliable. A test-retest coefficient of 1 indicates that each of my exam scores are perfectly correlated. For a coefficient of .70 = It’s either acceptable or questionable reliability (I’m not sure): (Between .7 and .8 = acceptable and between .6 and .7 = questionable reliability) Research Methods Exam 2 Review Key MC #1 Criterion validity – if a test has this type of validity it is useful for predicting performance or behavior in another situation

MC #2 Interrater reliability – two research assistants are independently observing behavior to see if their observations are consistent MC #3 Unknown – when using a nonprobability sample we can’t estimate how much our sample matches our population – chances are the external validity will be low but we do not know MC #4 All members are equally likely to be represented in the sample – probability samples ensure that every member of the population has an equal chance of being selected for the study so the sample matches the population MC #5 Snowball sampling – existing study subjects are recruiting future subjects from among their acquaintances MC #6 Collected a sample – this would be a probability sample since every 10th person is selected versus a census in which all of the population is part of the study SA #7 open ended – advantage – rich source of information; respondents can answer as they like – Disadvantage – time consuming; trained researches needed; typically obtain qualitative data so it needs to be coded SA #8 Test-retest – participant takes a test at time 1 (e.g., IQ test and scores 100) then take the test at time 2 (a month later and scores 103). Compare scores to see if they consistent – need the scores to correlate .70 to be considered to have test-retest reliability Interrater reliability – two observers independently observe the same behavior (children’s aggressive behavior on a playground). They record their observations independently. If the behavior is recorded quantitatively (# of aggressive acts in 10 minutes) then their scores need to correlate .70. If the behavior is calculated as a percent agreement – observers watch 100 cars come to a stop sign and each time record whether they came to a complete or incomplete stop.). Then they calculate how any times the two observers agreed (independently – they are not interacting). They must agree at least 85% to have interrater reliability Internal reliability – also called internal consistency – are the items on the measure (e.g., self esteem) correlated – do they all seem to me measuring self esteem. For example – if a respondent expressed agreement with the statements “I like to ride bicycles” and “I’ve enjoyed riding bicycles in the past” and disagreement with the statement “I hate bicycles” this would be indicative of good internal consistency of the test. You would calculate cronbach’s alpha to determine this (needs to be at least .7)

A p-value less than 0.05 (typically ≤ 0.05) is statistically significant. It indicates strong evidence against the null hypothesis, as there is less than a 5% probability the null is

correct (and the results are random). Therefore, we reject the null hypothesis, and accept the alternative hypothesis. There is no rule for determining what size of correlation is considered strong, moderate or weak. ... For this kind of data, we generally consider correlations above 0.4 to be relatively strong; correlations between 0.2 and 0.4 are moderate, and those below 0.2 are considered weak.

Francisco is conducting an international study about a new website that is preparing to launch worldwide. He wants to see if men or women are more likely to be interested in the new website so he can know which demographic to market it to. After he collects his data, Francisco discovers that whether the country he surveyed was collectivist or individualist changed how men and women responded to the website. Men from collectivist countries were the most interested, whereas women from individualist countries were the least interested. dependent variable: interest independent variable: gender moderator: type of culture Note: Predictor is IV- Gender Cause and effect The gender cause the interest (effect)...