Instruction on JMP IN of Chapter 17
Example 17.1
(1). Download the dataset xm17-01.JMP from the website for this course and open it.
(2). Go to the Analyze menu and select Fit Y by X. Click on "Odometer" and then click the “X, Factor” button. Then click "Price" and then click the “Y, Response” button. Click OK.
(3). Click the red triangle next to the heading “Bivariate Fit of… ”, then select “Fit Line”.
Following is the output:
Bivariate Fit of Price By Odometer
Linear Fit
Price = 6533.383 - 0.0311577 Odometer
Summary of Fit
RSquare / 0.650132RSquare Adj / 0.646562
Root Mean Square Error / 151.5688
Mean of Response / 5411.41
Observations (or Sum Wgts) / 100
Analysis of Variance
Source / DF / Sum of Squares / Mean Square / F RatioModel / 1 / 4183527.7 / 4183528 / 182.1056
Error / 98 / 2251362.5 / 22973 / Prob > F
C. Total / 99 / 6434890.2 / <.0001
Parameter Estimates
Term / Estimate / Std Error / t Ratio / Prob>|t|Intercept / 6533.383 / 84.51232 / 77.31 / <.0001
Odometer / -0.031158 / 0.002309 / -13.49 / <.0001
Example 17.2
In the output of Example 17.1, "Root Mean Square Error" is just the standard error.
Example 17.3
See the last part of the output ("Parameter Estimates") of Example 17.1 for the test.
Example 17.4
"RSquare" in the output of Example 17.1 is the coefficient of determination.
Example 17.5
(1). Download the dataset xm17-05.JMP from the website for this course and open it.
(2). Go to the Analyze menu and select “Fit Y by X”. Click "TSE" and then click the “X, Factor” button. Then click "Nortel" and then click the “Y, Response” button. Click OK.
(3). Click the red triangle next to the heading “Bivariate Fit of… ”, then select “Fit Line”.
Following is the output:
Bivariate Fit of Nortel By TSE
Linear Fit
Nortel = 0.0128181 + 0.8876912 TSE
Summary of Fit
RSquare / 0.313688RSquare Adj / 0.301855
Root Mean Square Error / 0.063123
Mean of Response / 0.018459
Observations (or Sum Wgts) / 60
Analysis of Variance
Source / DF / Sum of Squares / Mean Square / F RatioModel / 1 / 0.10562961 / 0.105630 / 26.5097
Error / 58 / 0.23110484 / 0.003985 / Prob > F
C. Total / 59 / 0.33673445 / <.0001
Parameter Estimates
Term / Estimate / Std Error / t Ratio / Prob>|t|Intercept / 0.0128181 / 0.008223 / 1.56 / 0.1245
TSE / 0.8876912 / 0.172409 / 5.15 / <.0001
Example 17.6
At this step, you are recommended to use calculator to compute the confidence interval and predictive interval. We will show you how to use JMP IN to find these intervals in the instruction of Chapter 18.
Example 17.7
(1). Download the dataset xm17-01.JMP from the website for this course and open it.
(2).Go to the Analyze menu and select Multivariate. Double click "Odometer" and "Price". Then click OK.
(3). Click on the red triangle next to the heading “Multivariate” and select “Pairwise Correlations”.
Following is the output: (Note: The t-statistic is not given in the output.)
Multivariate
Correlations
Odometer / PriceOdometer / 1.0000 / -0.8063
Price / -0.8063 / 1.0000
Scatterplot Matrix
Pairwise Correlations
Variable / by Variable / Correlation / Count / Signif ProbPrice / Odometer / -0.8063 / 100 / 0.0000
Example 17.8
(1). Download the dataset xm17-08.JMP from the website for this course and open it.
(2).Go to the Analyze menu and select Multivariate. Double click "Aptitude" and "Performance". Then click OK.
(3). Click on the red triangle next to the heading “Multivariate” and select “Nonparametric Correlations”. Then choose "Spearman's Rho".
Following is the output:
Multivariate
Correlations
Aptitude / PerformanceAptitude / 1.0000 / 0.4541
Performance / 0.4541 / 1.0000
Scatterplot Matrix
Nonparametric: Spearman's Rho
Variable / by Variable / Spearman Rho / Prob>|Rho|Performance / Aptitude / 0.3792 / 0.0991 / ++++++++++++++++