Lecture 4 measure something Methods Operationalization Getting at the real life tangible when you Conceptual variable that exists Correlational design v experimental design correlational measure one conceptual variable and then measure the other conceptual design need two conceptual variables o EX Theory is that happiness goes together with love If its correlation then you measure happiness and you measure love As you measure one then the other one will go up or will go down so as love goes up happiness goes up Positive and negatively correlated Positive correlation The number of firefighters that show up is positively correlated to the amount of damage to the house Firefighters do not cause damage to the house CAN YOU PREDIT THE AMOUNT OF DAMAGE TO THE HOUSE BASED ON THE NUMBER OF FIREFIGHTERS THAT SHOW UP YES Correlations use scatter plots for predictions Use the line of best fit to make predictions Straight line means there is no correlation no relationship between them 0 correlation 0 positive correlation numbers between 0 negative correlation numbers between 1 ARE THINGS THAT CAUSE EACH OTHER CORRELATED yes It s really the third variable that is causing for the two variables to increase and 1 and 0 Spurious Correlation in which two events or variables have no direct causal connection yet it may be wrongly inferred that they do due to either coincidence or the presence of a certain third unseen factor Spurious not true People assume causation when they see correlation When two things that are correlated they do not cause each other As ice cream sales increase then drowning deaths increase third variable that is causing it Black people do bad on the SAT o You measure their blackness and you measure the SAT scores Smoking and death o Measure smoking and measure death so you assume that smoking causes death o Need to run an experiment to see if it causes death experimental design if you manipulate then measure o shows that one causes the other o need to assume a direction o when you change the variable and then measures its affect on a different variable EX how you measure happiness and love Need to give 100 dollars and give 0 dollars to the people have to assign the people to be in the conditions being assigned to the conditions in the experiment random assignment Random assignment like flip a coin and that s why you are in a certain group only the manipulation should be different o NOT ALL EXPERIMENTS PROVE CAUSATION this is because all experiments are not always effective
View Full Document
Unlocking...