New version page

A-State PSY 2013 - Correlation vs Causation

This preview shows page 1 out of 3 pages.

View Full Document
View Full Document

End of preview. Want to read all 3 pages?

Upload your study docs or become a GradeBuddy member to access this document.

View Full Document
Unformatted text preview:

PSY 2013 1st Edition Lecture 3 Outline of Last Lecture II. What is Psychology?a. “The Big Debate”b. Definition of PsychologyIII. Research in Psychologya. Scientific Methodb. Observation Methodsc. ExperimentOutline of Current Lecture I. Correlation v. CausationII. Statistical ReasoningIII. Research EthicsCurrent LectureI. Correlation v. Causation- Correlation: a relationship between two variables exists to some extent- Causation: a trend of one variable was the cause for a trend in another variableExample: A study showed that as ice cream consumption increased in a certain city, the violent crime rate increased also. It was concluded that eating ice cream causes people to be hostile. After further review, it was decided that this is false. In reality, it was due to the weather. (More people eat ice cream in the warmer months, and no one wants to murder someone in a blizzard.) There was a correlation between the two variables, but one was not caused by the other.o Causal statements can only be made when variables are manipulated (an experiment.)- Correlation coefficient (r) o Direction  Positive/negative o Strength Number (0-1, where absolute values closer to 1 are stronger)These notes represent a detailed interpretation of the professor’s lecture. GradeBuddy is best used as a supplement to your own notes, not as a substitute.o Direction and strength are independent of each otherExample: +0.3 is a weaker correlation than -0.6.II. Statistical Reasoning- Central tendency (Where is the center of the data?)o Mean – all the data added divided by the number of samples addedo Median – the middle number when the data is arranged from lowest to highest valueso Mode – the number that appears the most- Measures of variationo Range – highest value minus lowest valueo Standard deviation – average spread of numbers around the meano Bell curve “Normal” when mean, median, and mode are all equal 2 standard deviations on both sides of the center = 95% of population Skew – caused by outliersExample: Say the average house value in an area is $150,000 and the distribution is normal. One day Oprah moves to town and builds a $10,000,000 house. Now the average house value is $1,000,000 (ignore the math here, it’s just an example). Has the value of the existing houseschanged? (No.) Oprah’s Designer Outlier created a positive skew.- Making Inferenceso Representative Z-scores (Skimmed over in class, but http://stattrek.com/statistics/dictionary.aspx?definition=z_score explains this really well.)o Statistical significance/significant differences Variability and number tested affects this Testing more subjects is not more reliable.Example: Say an experimenter tests 50 people and 3 show what the experimenter is looking for. He tests 50 more people and gets about the same number. Eventually, he is going to have a “significant” number of people if he keeps testing.III. Research Ethics- Consento Deception may be used here.o Observing natural occurrences in public places does not require consent.- Protectiono Harm may not occur to the participant.- Confidentialityo Names and data are separated.- Debriefingo Deception is revealed at the end of an experiment. (aka “dehoaxing”)- Ethical Dilemmaso <Search for videos of Milgram’s experiment. This was shown in class and we discussed briefly whether or not we believed it to be


View Full Document
Loading Unlocking...
Login

Join to view Correlation vs Causation 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 vs Causation 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?