Please enable JavaScript.

Coggle requires JavaScript to display documents.

Correlation (2) 7. (Regression (Linear Regression (Definition (Formal…

- - - - Formal
        
        Regression uses 1 Independent Variable to Explain or Predict the Outcome of the Dependent Variable Y
        
        a Statistical Analysis that uses 1 Indipendent Variable to Predict values of Y
        
        Ex. Given IQ scores (X),
        want to Predict University Grades (Y)
        
        2 sources of Variance
        
        Not Predicted by X
        (Explained by smth Else)
        
        1 more item...
        
        Predicted by X
        (/Explained)
        
        1 more item...
        
        Regression Line
        
        Line that best Minimizes the Sum of the Squared Distances Between Each point and the Regression Line
        
        1 more item...
    - - Predict the Value of a Variable
        by using the Value of Another
        
        Predictor Variable
        
        the Variable we Use to Predict
        (Indipendent Variable X)
        
        Criterion Variable
        
        the Variable we Want to Predict
        (Dependent Variable Y)
    - - Y-hat: Predicted Score
        
        X: the Score we Use to Predict
        
        b: Regression Coefficient (Slope)
        
        a: Regression Constant (Y-Intercept, Cross Value on Y axis)
        
        how to Calculate
        
        b
        
        SP: Sum of Products (of X and Y) /
        SS: Sum of Squares (of X)
        
        a
  - - - More Indipendent Variables
        used to Predict Y
    - - Indipendent Variables are
        Minimally Correlated w each other
    - - Hierarchical Multiple Regression
        
        we Assume some Variables
        have More Predictive Power
        
        we Make and Use a Theoretical Model
        that describes the DIff. Predicitve powers of Diff. Variables
      - Normal Multiple Regression
        
        All Varaibles involved
        are Considered Equal
  - - - if we have Included All Extraneous Variables, or
        
        that we have Measured the Confounding Variables in Correct way
        
        Confounding Variable
        
        an Extraneous Variable that
        Influences both the Dependent and Independent Variable
        
        Extraneous Variable
        
        a Variable that we have Not Considered
        
        any Variable Other than
        the Indipendent , Dependent and Control Variables
        
        is Extraneous to our Test/Experiment
- - - - Not w Curvilinear
    - - Interval or Ratio Scales
        
        No Nominal nor Ordinal Scales
  - - - Procedure
        
        put Observation Values in a Crescent Order
        
        Assign to the Lowest X Value the value of 1,
        to the Second-Lowest assign 2, and so on
        
        Same Procedure for Y Observation Values
        
        Calculate Normal Pearson Correlation (r) w new X and Y Values
        
        w Equal Scores (ex.):
        7th=15
        8th=15 ->
        (7th + 8th) / 2 = 15
        7.5th = 15
- - - - Inter-Reater Reliability
        
        More Observers
        used to
        Minimize Subjective Bias
        
        Calculate the Correlation
        btw Scores by Diff. Observers
        
        Percentage of Agreement
        
        Disadvantage
        
        Does Not Consider
        Casual Consensus
        
        1 more item...
        
        Sources of Measurement Error
        
        Reactivity
        
        testing Humans, the Observer can Influence
        the Participants and hence the Measurements
        
        the Participants Reacts (Modify their Behavior due)
        to the Observer
        
        Expectation Effect &
        Observer Bias
        
        Expectation and Bias
        are Systematic Errors
        
        Bias
        
        ex. Observer knows the Hypotheses being tested,
        Measures or Manipulates Data (even Unconsciously) in a Particular Direction
        
        1 more item...