Chapter 7 relationship between effect size sample size and significance statistical significance is related to effect size usually the stronger a correlation and the larger its effect size the more likely the correlation will be statistically significant That s because the larger an association is the less likely it could have been sampled just by chance from a population in which the association is zero But you cannot tell whether a particular correlation is statistically significant by looking at its effect size alone You will also need to look for the significance calculations the p values associated with it Statistical significance calculations depend not only on effect size but also on sample size A very small correlation say r 0 08 will be statistically significant if it is identified in a very large sample say a sample of 1 000 or more But that same small correlation of r 0 08 would not be statistically significant if the study used a small sample say a sample of 30 A small sample is more easily affected by chance events than a large sample is In other words in a population in which the association is zero studies with small samples might show weak correlations relatively frequently Therefore a weak correlation based on a small sample is more likely to be the result of chance variation and is more likely to be judged not significant in many cases people cannon be randomly assigned to a variable cannot be assigned to preferences and it is unethical to assign some people to a condition where they are forced Chapter 8 why do correlations why not just experiments use of beta to test for 3rd variable one beta variable per predictor variable positive beta positive relationship between predictor and dependent variable The higher beta is the stronger the relationship is between that predictor variable and the dependent variable The smaller beta is the weaker the relationship is Within a single regression table you can usually compare predictor variables that show larger betas to predictor variables with smaller betas the larger the beta the stronger the relationship beta changes depending on what other predictor variables are being used being controlled for in the regression the beta that is associated with a predictor variable represents the relationship between that predictor variable and the dependent variable when the other predictor variables in the table are controlled for Chapter 9 conditions needed to satisfy causality covariance related temporal precedence causal before effective internal validity alternative explanations advantages disadvantages of various experimental designs within groups more power to notice differences in conditions fewer participants D potential for order effects which threatens internal validity A ensures that participants in the two treatment groups will be equivalent treat each participant as his or her own control participant changes how they would act pretest posttest designs might give some assurance that the groups were equal but there can be costs too maturation change in behavior that happens more or less spontaneously over time history threats to internal validity that occur when a historical or external event occurs to everyone in the treatment group unclear of results Chapter 10 threats to internal validity regression attrition drop outs testing threat instrumentation threat threats table 10 1 interrogatting null effects problems and solutions problem measurement error solution reliable measurements and measure more instances precision problem 2 individual differences solution change the design and add more participants situational noise control extraneous variables control room table 10 2 Chapter 11 understanding interactions and main effects factorial design variations 2 way and 3 way interactions fig 11 24 Chapter 12 review threats to internal validity advantages disadvantages compare and contrast design types study to only one animal or one person using a single N design not represent total population Chapter 13 reviewing external validity Masuda and Nisbett s 2001 study Figs 13 8 13 10 small N design instead of gathering a little information from a larger sample they obtain a lot of information from just a few cases They may even restrict their