- Information
- AI Chat
Lecture Notes Exam 2
Abnormal Psychology (PSYC 3303)
University of Colorado Boulder
Preview text
CH 8
Sampling Distribution - Gives all possible values that statistics can take - Probability of getting each value of the statistic if it resulted by chance alone
How to Analyze Statistics 1. Calculate the appropriate statistic 2. Evaluate that statistic based on its sampling distribution *if the probability of getting that obtained statistic, or a more extreme value of that statistic, is less than or equal to alpha, then you reject the null hypothesis Hypotheses Alternative Hypothesis (H1) (what you want) - There is a relationship between variables - Directional (wearing glasses makes you hot) - Nondirectional (wearing glasses effects your hotness) Null Hypothesis (H0) (opposite of alternative, doesn’t work) - No true relationship between variables (or opposite direction) Is based on the probability of chance, we either - Reject H0 (if P>A, P is comparing if the null is true aka no correlation, statistic calculated far from 0 to reject) - Fail to reject H0 (accept)
Errors Type 1 (false-positive) occurs if an investigator rejects a null hypothesis that is actually true in the population
Statistics
𝐀
- The probability level you will accept (the chance you are willing to take) of making a Type 1 error - Alpha never calculated, just chosen (0 standard) 𝐀 value
- The probability of getting a statistic if there is no relationship in the population (getting your statistic by chance) (0 for binomials)
Type II
(false negative)error that occurs when one fails to reject a null hypothesis that is actually false 𝐀 - The probability level you will accept (the chance you are willing to take) of making a Type II error - Effect size - how big is the effect
= mean of all the sample means = mean
Null Hypothesis Population - Actual or theoretical set of population scores that would result if the experiment were done on the entire population and the IV had no effect Sampling Distribution - All the values that a statistic can take along w their probabilities, if sampling is random from a null hypothesis population (null is true) - Probability of _ happening if null is true is really small - Ex. binomial table, z score table
Two Tailed Test: - Could go both ways - Add 0 and N on opposite sides of table, added together until just less an alpha, those X values reject the null
We want Z score to be far away from 0(middle of normal distribution) because the z score of 0 is when the null is true, we want to reject the null
The critical value is the value of the statistic that has the same P value as Alpha - Critical Value of a Z score for a 1 tailed test is 1. - Critical value of a Z score for a 2 tailed test is 1 (-1) To find on table n-2, then match up w .05, see if less than .05, reject or don’t
CH 9 Correlation Rules Two continuous variables, linear relationship only
T test formula: find probability of getting r when no relationship
- Farther away from 0, the more they effect each other, 0 means no effect
- We want t to be less than alpha
- Then find out what the value of t is at alpha aka critical value Once t is found, go to t table, and compare ur t to the critical value, is its more than it then it reject null CH 10 Linear regression: 2 Continuous Variables, unstandardized, exact amount X given, prediction for exact amount of Y
Y hat means predicted value of Y, a= y value, b= slope
Slope:
S2 = variance of x A: Y intercept Mean of Y- slope (mean of X)
Mean of Y - b * mean of X
CH 11
Multiple regression: More than one predictor variable, one outcome variable- continuous R: effect of all predictor variables on the outcome variable and 𝐀: effect of each individual predictor variable on the outcome without the influence of any other predictor variables (no overlap)
Lecture Notes Exam 2
Course: Abnormal Psychology (PSYC 3303)
University: University of Colorado Boulder
