DOC PREVIEW
Pitt PSY 0010 - Correlation
Type Lecture Note
Pages 7

This preview shows page 1-2 out of 7 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 7 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 7 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 7 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

CorrelationExamine relation between variablesLiterally means “co-relation”Sometimes between 2 variablesMost often between more than 2 variablesEX: time spent studying and grade on into to psych examCorrelation CoefficientRepresented by lower case “r”Can be positive or negativeEX: r = +0.37The +/- indicates the direction of the relationshipCould be positive or negativeCould be anything between a completely positive +1.00 and complete negative -1.00The number indicates the strength of the correlationThe bigger the number, the stronger the relationship between the variablesPositive Correlation (+)As one variable increases, so does the other OR as one variable decreases, so does the otherEX: exercise and fitness, weight and height, study time and high gradesNegative Correlation (-)As one variable increases, the other decreasesEX: more partying = lower grades, less sleep = less attention spanZero CorrelationWhen there is no relationship/affect between two variablesEX: color of hair and house you grow up inCorrelation does NOT prove Causation!Correlation and Causation(1) Low self-esteem could cause depression OR (2) Depression could cause low self-esteem OR (3) Distressing events or biological predisposition could cause depression AND/OR low self-esteemExperimentEnables isolation of cause and effectBecause they can manipulate factor(s) of interestCan keep other factors under controlIndependent Variable (I.V.)Factor that is manipulated by the experimenterBecause of this the researchers are able to look at cause and effectThe effect of the independent variable is the focus of the studyEX: when examining the effects of a medication on depression, the medication is the independent variableDependent Variable (D.V.)A factor that may change in response to an independent variableEX: in our study on the effect of the medication on depression, depression is the dependent variableIn an experiment:1. Experimental Conditionsubjects receive treatment (independent variable)those exposed to I.V.2. Control Conditionsubjects do not receive treatment (independent variable)not exposed to I.V.Random AssignmentAssign subjects of an experiment to groups by chanceWe want to make sure we have a mix of different type of people in each groupMinimizes existing differencesOther pre-existing differences could be attributable to the cause of responses between variablesExperimental DesignRandom assignment1.Experimental Conditiona) I.V. – Medicationb) D.V. – level of depression2. Control Conditiona) I.V. – no medicationmust give them a placebo (most likely a sugar pill) or the subjects would know they are in the control group and would know not to expect any responseb) D.V. – level of depressionExperimenter EffectSubject’s response is influenced by experimenter’s behaviorThis is not ideal; we don’t want this to happenExperimenter’s behavior must not influence the subjects behaviorShould not give anything awaySingle Blind ProcedureParticipants do not know if they are in the Experimental group (receive IV) or Control group (don’t receive IV)If they know which group they are in, it can influence how they feel/the perceived results and affectsDouble Blind ProcedureNeither experimenter or subject know who is in experimental groups or control groupsWho is receiving the IV and who is notPlacebo EffectChange due to belief that one is receiving a treatmentEX: somebody who believes they are given alcohol (when they were not) starts to act intoxicatedStatisticsA tool that psychologists use to:1. Organize2. Summarize3. Make inferencesOrganizing Data:Frequency DistributionsA simple way to organize dataProvides a visual formEX: Histogram (bar graph), Polygon (line graph)Rank OrderingWould help to know what the highest and lowest possibly scores areRecording scoresMeasures of Central TendencyWhat is their tendency in terms of being in the middleMode:The most frequently occurring scoreit tells us what was most frequentMedian:The middle score in a rank-ordered distributionMean:The arithmetic average of scores in a distributionAdd up all of the scores and divide the sum by the number of scores totalSkewed DistributionWhen there are clear outliers, it can affect the vales of the meanThe average is greatly affected by the outliersVariabilityRangeDifference between the highest and lower scoresGives you a sense of how spread out the scores areStandard DeviationA measure of how much the scores vary around the meanSolve for this by taking the (mean-every score)^2 then take the square root of that resultInferential StatisticsProbability theoryRe: chance vs. true differencesThere is always the likelihood that the results happened by chanceThis must be taken into accountIf this chance is low, we are in a better position to infer from a small group to the larger population“infer” from group studied to larger groupcan results be generalized?Generalizing from SamplesWhen we plan on doing this we want to make sure we have a representative sampleLess variable observationsThe less the results vary, the more confidence we can have when inferring to larger samplesMore cases (data)The larger the sample size, the more confident we can be in the results when inferring to a larger populationStatistical SignificanceDifference observed probably was not due to chance variation between groupsPreferably <.05%Research EthicsInformed consentIf there is no informed consent, the test should not happen and the results can not be usedRiskDeceptionSometimes can be used, but only if it is justifiedMust be told as soon as possibly why they were deceivedDebriefingConfidentialityYour name is not associated with the studyCodes can be usedAnimalsRules/guidelines do existFederal Animal Welfare ActNational Academy of ScienceAversive techniques are rareMay be the only alternative to testing on humansPSY 0010 1nd Edition Lecture 3 Outline of Last Lecture I. Applied “Clinical” ProfessionalsII. ResearchIII. Psychology is a Natural Science Outline of Current Lecture II. CorrelationA. Correlation CoefficientB. Correlation and Causation III. ExperimentsIV. ProceduresV. RegulationsVI. EthicsCurrent Lecture Correlation- Examine relation between variables- Literally means “co-relation”o Sometimes between 2 variableso Most often between more than 2 variables- EX: time spent studying and grade on into to psych exam Correlation Coefficient- Represented by lower case “r”o Can be positive or negative- EX: r = +0.37o The +/-


View Full Document
Download Correlation
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 Correlation 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 Correlation 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?