Correlational Research Correlational research: Assess relationships among naturally occurring variables. Attitudes, preferences, intelligence, personality traits, feelings, age, sex The Correlation Coefficient 22 John Wiley & Sons, Inc. Correlational Research Correlation and Causality Correlation does not imply causation. Spurious relationship 1
Cause and Effect Cigarette smoking and academic achievement. Does cigarette smoking cause poor grades? Students with poor grades are more anxious and may smoke more More sociable students may smoke more and study less Correlational Research Designs A research design is a plan for conducting a research project. 3 Types: cross-sectional successive independent samples longitudinal Cross-sectional Design A sample is selected from one or more populations at one time. 2
4 35 3 25 2 15 1 5 Externalization Internalization Depression Life Events Stress Dating Violence Males No Dating Violence Males 45 4 35 3 25 2 15 1 5 Adolescents Externalization Internalization Depression Life Events Stress Dating Violent Females No Dating Violence Females High School Students: Non Virgins Parents.21 Parental.16 Friends Friends.2.24.55 Attitudes about Premarital Sex.28 Contraceptive knowledge.25 Sexual Behavior Contraceptive Use Successive Independent Samples Design: Major goal is to describe changes in attitudes or behavior within a population over time 3
Percent Percent Percentage of High School Students Who Carried a Weapon,* 1991-23 1 8 6 4 26.1 22.1 2. 18.3 17.3 17.4 17.1 1 2 1991 1993 1995 1997 1999 21 23 * For example, a gun, knife, or club on > 1 of the 3 days preceding the survey 1 Significant linear decrease and quadratic effect, p <.5 National Youth Risk Behavior Surveys, 1991-23 Percentage of High School Students Who Ever Had Sexual Intercourse, 1991-23 1 8 6 54.1 53. 53.1 48.4 49.9 45.6 46.7 1 4 2 1991 1993 1995 1997 1999 21 23 1 Significant linear decrease, p <.5 National Youth Risk Behavior Surveys, 1991-23 Longitudinal Research Designs The same sample of individuals completes the measures at different points in time. Allows researchers to assess how individuals change over time. The sample of respondents is used to represent how individuals in the population change over time. Longitudinal Studies (same participants/different times) 4
Stability of Attachment Classifications from Infancy to Adulthood Secure Avoidant Resistant Secure Dismissing Preoccupied 2 2 3 6 8 2 3 2 4 3 Groups Secure/Insecure 64% stayed the same 72% stayed the same 72% if no significant life events 78% if no significant life events Threats to Internal Validity in Internal validity to whether it can be concluded that the independent variable produced the differences observed. History Maturation Selection Testing Statistical regression Instrumentation Mortality or attrition Threats to Internal Validity in History are differences over time due to cultural changes. The greater the period of time that elapses between measurements, the more the risk of a history effect. History is NOT a threat to cross-sectional studies which are conducted at one time point. Selection threat translates to the cohort effect. In crosssectional studies, comparing individuals who are in their 3's with individuals who are in their 7's on some task or opinions offers the risk that behavioral differences have actually nothing to do with age, rather they may be the result of differing educational, cultural and nutritional/health habits which characterized living conditions differently for each generation. 5
Cross-Sectional Designs to assess age differences: Social Network Influences on Adolescent Sexual Attitudes and Behaviors & & Attitudes about Sex & Sexual Behavior Possible confound: Cohort differences; does not get at individual change Age differences in paths of influence Parental.16** -.25**.1.1 w/ Mother.44 **.63.41 Friends Friends.18** Attitudes about Premarital Sex.7*.7.49).8*.17* Sexual Behavior The paths with significant aged differences are highlighted in yellow and have three coefficients which refer to the 9 th /1 th grade, 11/12 th grade and college age samples respectively. Threats to Internal Validity in Maturation alone may produce changes across time Testing effects consist of either reactivity as a result of testing or practice/learning from exposure to repeated testing. Statistical regression occurs where repeated measures are used and is particularly evident when participants are selected for study because they are extreme on the classification variable of interest, e.g. intelligence. Testretest scores tend to systematically drift to the mean rather than remain stable or become more extreme. Regression effects may obscure or developmental changes 6
Threats to Internal Validity in Instrumentation- measurement equivalency and cultural change Mortality or attrition of subjects is a major threat to a lengthy longitudinal study since the sample remaining at the end of the study is unlikely to be comparable to the initial sample. For example, the surviving sample is likely to be healthier, more stable in lifestyle and so forth. 7