Practice question - DO NOT FORGET TO GRAPH on Page 2 and also a bell curve graph for Step TWO on Page 4
REFER TO THIS EXAMPLE HERE - https://drive.google.com/file/d/1IWEsuGLkNmXh6w8FislwThJm1j4SfwxC/view?usp=sharing
Pearson r Correlation Coefficient and Regression Measure the relationship between public school poverty rates and percentage of students that passed the college readiness benchmark by 1) creating a scatter plot, 2) conducting a Pearson / Test and appropriate post-hoc test(s), and 3) finding and reporting regression equation and standard error of the estimate (if applicable). Provide an interpretation of all of your results. Variable ONE (X) Variable TWO (Y) POVERTY COLLEGE READINESS Case X Y Y2 XY 73.49 23.11 72.85 12.31 56.26 71.21 49.36 47.62 48.07 88.4 47.66 89.51 46.57 71.5 45.19 80.6 43.22 82.2 38.25 56.74 37.34 56.3 33.33 50.97 29.58 77.05 24.22 100 22.71 100 15.79 100 11.18 100 EX= [X2= EY= [Y2= [XY= (EX) 2= ([Y) 2=\fHigh School Poverty Level Poverty rate Keystone- College readiness Overall Category Math benchmark Academic score (Created) (based on SAT) Allentown 73.49 33.75 23.11 47.8 Dieruff 72.85 55 36.86 12.31 Liberty 56.26 71.21 74.9 53.89 HIGH Catasauqua 49.36 47.62 59.7 73.83 Whitehall 48.07 88.4 85 73.54 Northwest 47.66 31.03 89.51 72.6 Easton 46.57 71.5 71.54 62.86 Freedom 45.19 80.6 69.5 54.35 Wilson 43.22 82.2 93.6 74.34 MEDIUM Northern Lehigh 38.25 56.74 74.1 67.2 Bangor 37.34 56.3 82.1 68.92 Pen Argyl 33.33 50.97 70.3 68.85 Salisbury 29.58 188.1 74.26 77.05 Emmaus 24.22 100 84.8 80.5 Parkland LOW 22.71 100 75.6 80.79 Nazareth 15.79 100 98.8 86.67 Southern Lehigh 11.18 74.25 100 81.1FOUR STEP FRAMEWORK Pearson r Correlation Coefficient STEP ONE HYPOTHESIS Two-Tailed One-Tailed Predicting a positive Predicting a negative correlation correlation Ha:p=0 Ho:p>0 Ha:p='05 Measure Effect Size (If significant) The Proportion of Variance Accounted For: r2 Report Result Linear Regression (Usually used when you are experimentally manipulating one variable) Compute \"r" and determine that it is significant. Proceed only if r is signicant. Determine your predictor (independent) variable (X) Determine your criterion (dependent) variable (Y) Compute the Linear Regression Equation: 1\": bx + a (Enables us to find the value ofa particular Y when we know b (the slope) and a (where Y intercepts)) Slope of the regression line (b) The Y intercept (a) [FW a=17'-(b)()?) NERD-(EXP Compute the Standard Error of the Estimate: (Sy'l (Determines the amount of error we expect to have when we use a relationship to predict Y scores) 5],! = (5V) (J1 r2) Report and Interpret the Regression Eguation
