Study your flashcards anywhere!
Download the official Cram app for free >
 Shuffle
Toggle OnToggle Off
 Alphabetize
Toggle OnToggle Off
 Front First
Toggle OnToggle Off
 Both Sides
Toggle OnToggle Off
 Read
Toggle OnToggle Off
How to study your flashcards.
Right/Left arrow keys: Navigate between flashcards.right arrow keyleft arrow key
Up/Down arrow keys: Flip the card between the front and back.down keyup key
H key: Show hint (3rd side).h key
A key: Read text to speech.a key
7 Cards in this Set
 Front
 Back
WHat are the sources of variance that go into the numerator and the denominator of the fstat?

F = treatment effects + individual differences + experimental error
individual differences + experimental error the only difference between the numerator and the denominator is the presence of treatment effects in the numerator 

F stat equation

• So, the only difference between the numerator and the denominator is the presence of treatment effects in the numerator
• If the treatment effect is large, F will be large. • If there is no treatment effect (treatment effect = 0) the Fratio will be close to 1.0 • The denominator of the Fratio only has unsystematic sources of variation, and is therefore often referred to as the error term • If the null hypothesis is true, then both the numerator and denominator measure the same thing – unsystematic error due to sampling error 

What does the fdistribution look like? What should the value of F be if the null hypothesis is true?

• Because the Fratio is the ratio of two variance (and variance is always positive), the Fratio will always be positive.
• Under the null hypothesis, the Fratio should be close to 1. • The Fdistribution is always greater than 0, and has a mode at 1. • The exact shape of F depends on the df. df for the numerator of the Fratio = dfB dffor the denominator of the Fratio = dfW • The critical value for F can be found in the F table (to be discussed in class) 

Regression Equation and what it tells you:

• Linear Relationships
• Can be expressed by Y = bX +a • “a” is the intercept – the point at which the lines hits the Yaxis on a graph. o When X=0, Y=a or when x=0, y = the intercept. • “b” is the slope – the steepness of the line. Tells you how much Y will change when X increases by 1 unit • The equation for a line, however, does not address the data scattered around the line. Regression, allows us to draw the best fitting line through the data keeping that “error” in mind. 

•Four types of scales

•Nominal  includes labels or categories; no size or magnitude information
•Ordinal  includes ranking information; ordered by magnitude •Interval  equal intervals between numbers reflect equal differences in magnitude; no absolute zero •Ratio  like interval scales, but there IS an absolute zero. 

•Discrete vs. Continuous Variables

•Discrete  implies that the numbers are separate, individual, indivisible categories.
•Continuous  continuous scales are not limited to a fixed set of categories. **Real Limits for continuous variables: for a continuous variable, each score really corresponds to an interval on a scale. The boundaries that separate the intervals are called the real limits. The real limits are located exactly halfway between the scores. The upper real limit is half way above the score, and the lower real limit is half way below the score. 

oSkewness
oKurtosis 
oSkewness – the degree to which the distribution departs from being symmetrical
Positively skewed – tail extends in the positive direction Negatively skewed—tail extends in the negative direction Kurtosis – the degree to which a distribution is pointy or flat and spread out. Leptokurtic pointy Platykurtic – flat and spread out 