DOC PREVIEW
TAMU PSYC 203 - Monty Hall

This preview shows page 1 out of 4 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 4 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 4 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

PSYC 203 1st Edition Lecture 11Outline of Last Lecture I. Review II. Alpha III. Test- Retest Reliability IV. Parallel Forms V. Inter-Rater Reliability VI. Validity Outline of Current Lecture I. Monty Hall Problem II. Construct validity III. Reliability and Validity IV. Hypothesis Current LectureI. Monty Hall Problem a. You are on a game show. You have a choice of three doors: Behind one door is a car whereas behind the other two are goats. You pick Door No. 1.The host, who knows what's behind the doors, opens Door No. 3 to show you a Goat. He then says to you, "Do you want to pick door No. 2 or stay with No. 1?" Is it to youradvantage to switch your choice?b. http://www.stat.sc.edu/~west/javahtml/LetsMakeaDeal.htmlc. click on above link to see for yourself and we will talk about it next class. II. Construct validity a. Focus on the Construct (i.e., the idea) and NOT the properties of a single instrumenti. Construct is the hypothetical idea, like extraversion, happiness, depression, etcThese notes represent a detailed interpretation of the professor’s lecture. GradeBuddy is best used as a supplement to your own notes, not as a substitute.b. Can we get convergence across different measures of the SAME construct? c. Can we get expected divergence?i. Are measures of different constructs unrelated? d. How does this construct fit into a nomological network (a lawful network of expected relations)? e. All of these are important questions when measuring constructs III. Reliability and Validity a. Convergent Validity: Associations Between Different Methods of Assessing the Same Construct. Confirmation of the Measurement of the Construct using Multiple Methods.i. Different methods of assessing the constructs should correlate (yield the same info)b. Discriminant Validity: Distinctiveness of Constructs. This is indicated by a lack of association between measures of different constructs.i. Can you differentiate from anxiety and depression?c. Something can be reliable, but not valid. d. For example: shoe size can be a reliable measure of intelligence because both your shoe size and IQ remain fairly constant but this isn’t a valid measurement because the two have nothing to do with each other e. Phrenology is another example IV. Hypothesis a. Research in psychology often involves hypothesis testing: – Does therapy X reduce depression compared to a Placebo? – Do kids exhibit more aggressive behavior after playing Aggressive Video Games versus Non-Violent Games? b. Hypothesis testing determines whether one should conclude that a specifictreatment has a statistically detectable impact or whether there is a statistical association between two variables. i. Is the detected difference greater than the difference we would’ve expected from chance factors alone?c. The statistical objective is determine the likelihood that random chance (sampling error) is a plausible explanation for the results of a study.V. NHST (NULL HYPOTHESIS SIGNIFICANCE TESTING)a. A statistical technique that uses data from SAMPLES to make inferences about the POPULATIONb. First specify a Null Hypothesis and 1 or more Alternatives (Research Hypotheses). c. Then decide if the sample data are convincing enough to REJECT the Null Hypothesis d. Embodies the idea of no association e. The research hypothesis is the alternative f. Is the difference between treatment and control big enough to reject the null hypothesis?g. You need to be able to reject or fail to reject the null hypothesis h. The null states that there will be no difference between your groups or no association between your variablesi. Examples1. There is No effect of Pill X on depression 2. There is No difference between men and women in aggression 3. There is No association between SAT scores and college GPA i. Conservative approach i. You assume the NULL applies until the evidence suggests otherwise1. NHST: Assume null is correct until your data suggest otherwise2. We have agreed upon benchmarks to determine whether to reject the NULL3. NHST: Reject the Null when you are confident any observeddifferences/associations are not better explained by chance/random factorsj. Statistically significant means…i. The observed result (e.g., the observed mean difference) is unlikely to occur if the NULL hypothesis was TRUE.ii. Aka: statistically improbable iii. There is a statistically significant difference between the two groupsiv. We need to avoid sampling error to be able to generalize our resultsfrom our samples to our population v. The Null is framed as a statement about the population (not a sample) H0 1. No difference between men and women in math skill. 2.H0 : the population mean of a equals the population mean of B 3. Not usually stated in journal articles—only


View Full Document

TAMU PSYC 203 - Monty Hall

Download Monty Hall
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Monty Hall and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Monty Hall 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?