1Scientific Methods II:Scientific Methods II:CorrelationalCorrelationalResearchResearchEXAMPLESEXAMPLES"MARRIAGE SLOWS CANCER DEATHS“"MARRIAGE SLOWS CANCER DEATHS“Evidence that married people have a better Evidence that married people have a better chance of surviving cancer than do singles chance of surviving cancer than do singles means that the unmarried might be good means that the unmarried might be good targets for cancertargets for cancer--prevention programs. prevention programs. Married people with cancer had a 23% Married people with cancer had a 23% higher overall survival rate than the higher overall survival rate than the unmarried.unmarried.Example 2Example 2Isolation increases with Internet useIsolation increases with Internet usePsychologist Robert Kraut and his Psychologist Robert Kraut and his colleagues report that greater use of the colleagues report that greater use of the Internet leads to shrinking social support Internet leads to shrinking social support and happiness, and increases in and happiness, and increases in depressiondepressionand loneliness…And the and loneliness…And the findings were unexpected, Kraut says, findings were unexpected, Kraut says, given that most people use the Internet for given that most people use the Internet for chat lines and echat lines and e--mail, not just to isolate mail, not just to isolate themselves in mounds of electronic themselves in mounds of electronic information. information. Example 3Example 3““Revenge of the Beaker Revenge of the Beaker Bunch”..ResearchersBunch”..ResearchersFind that Find that Scientists Live LongerScientists Live LongerIf it were a movie, it would probably be called "If it were a movie, it would probably be called "Nerds:TheNerds:TheUltimate Revenge.“ A study spanning nearly 70 yearsUltimate Revenge.“ A study spanning nearly 70 yearssuggests that, all else being equal, scientists live longersuggests that, all else being equal, scientists live longerthan nonthan non--scientists… According to Friedman's study,scientists… According to Friedman's study,nonscientists are 26 percent more likely to die at any givennonscientists are 26 percent more likely to die at any givenage than scientists. In a sample of 600 men born aroundage than scientists. In a sample of 600 men born around1912, Friedman's group found that only 67% of non1912, Friedman's group found that only 67% of nonscientists were still alive by age 70, compared to 72% of scientists were still alive by age 70, compared to 72% of the scientists...” the scientists...”2CorrelationalCorrelationalResearchResearchCorrelationalCorrelationalresearch examines whether 2 research examines whether 2 factors are naturally associated. [Cofactors are naturally associated. [Co--relation: the relation: the degree to which one variable is related to degree to which one variable is related to another.]another.]Examples focus on naturally occurring Examples focus on naturally occurring relationships relationships marriage & cancer recoverymarriage & cancer recoveryInternet use & depressionInternet use & depressionoccupation & longevityoccupation & longevityCorrelations: The BasicsCorrelations: The BasicsNumerical range: Numerical range: --1.00 to +1.001.00 to +1.00The Correlational MethodCorrelation CoefficientPositive correlations indicate that an increase in one variable is associated with an increase in the other.Negative correlations indicate that an increase in one variable is associated with a decrease in the other.3The Correlational MethodThe Correlational MethodSurveysThe correlational method often relies on surveys, as well as on observational data. Surveys are used when the variable of interest is not easily observable.How do we evaluate How do we evaluate correlationalcorrelationalfindings?findings?Amount use Internet is associated with Amount use Internet is associated with greater depression. Why?greater depression. Why?3 possible explanations3 possible explanationsUsing Internet Using Internet ÆÆdepression depression Depression Depression ÆÆgreater Internet use (cannot greater Internet use (cannot determine direction of causality)determine direction of causality)A 3A 3rdrdvariable might be related to both variable might be related to both using the Internet and becoming using the Internet and becoming depresseddepressed433rdrdVariablesVariablesPeople….People….People….People….Evaluating Evaluating CorrelationalCorrelationalResearchResearchCorrelationalCorrelationalresearch cannot determine research cannot determine causality.causality.Problems knowing direction of causalityProblems knowing direction of causalityProblems knowing whether some 3Problems knowing whether some 3rdrdvariable (confounding variable) might variable (confounding variable) might explain the observed correlationexplain the observed correlationHow do we evaluate How do we evaluate correlationalcorrelationalfindings?findings?Consider in context of research on TV Consider in context of research on TV exposure and aggressionexposure and aggressionStart w/theoretical idea and to test specific Start w/theoretical idea and to test specific hypotheses. hypotheses. Hypothesis: Children who watch more Hypothesis: Children who watch more violent television shows behave more violent television shows behave more aggressively.aggressively.5TV & Violent ContentTV & Violent Content8 out of 10 Sat. morning programs contain 8 out of 10 Sat. morning programs contain violenceviolenceSat. morning children’s shows: 20 violent Sat. morning children’s shows: 20 violent acts per houracts per hourAverage American watches 4 hrs of TV Average American watches 4 hrs of TV per day, or over 1000 hrs. per year.per day, or over 1000 hrs. per year.What is relationship between watching TV What is relationship between watching TV and children’s aggressive behavior?and children’s aggressive behavior?TV and AggressionTV and AggressionMany studiesMany studiesSample Sample correlationalcorrelationalparadigm:paradigm:Parents record how much TV their kids watchParents record how much TV their kids watchTeachers record aggressive behaviors Teachers record aggressive behaviors (hitting, pushing, shoving, insulting, etc.)(hitting, pushing, shoving, insulting, etc.)IV AND
View Full Document