In: Statistics and Probability
Like father, like son: In 1906, the statistician Karl Pearson measured the heights of 1078 pairs of fathers and sons. The following table presents a sample of 6pairs, with height measured in inches, simulated from the distribution specified by Pearson.
| 
 Father's  | 
 Son's  | 
|||
| 
 73.6  | 
 76.5  | 
|||
| 
 69.0  | 
 69.1  | 
|||
| 
 73.6  | 
 74.9  | 
|||
| 
 66.7  | 
 68.8  | 
|||
| 
 70.1  | 
 73.3  | 
|||
| 
 72.3  | 
 71.9  | 
|||
| 
 Send data  | 
||||
The regression equation is Y = .9834x + 2.7077
Construct a 95% confidence interval for the slope. Round the answers to at least four decimal places.
_____ < B1 < _____
P-Value ______
Reject or Do not Reject
Evidence?
| ΣX | ΣY | Σ(x-x̅)² | Σ(y-ȳ)² | Σ(x-x̅)(y-ȳ) | |
| total sum | 425.30 | 434.50 | 38.43 | 47.97 | 37.79 | 
| mean | 70.88 | 72.42 | SSxx | SSyy | SSxy | 
Sample size,   n =   6  
   
here, x̅ = Σx / n=   70.883  
       
ȳ = Σy/n =   72.417      
   
SSxx =    Σ(x-x̅)² =    38.4283  
   
SSxy=   Σ(x-x̅)(y-ȳ) =   37.8  
   
          
   
estimated slope , ß1 = SSxy/SSxx =  
37.7917/38.4283=   0.9834  
  
intercept,ß0 = y̅-ß1* x̄ =   72.4167- (0.9834
)*70.8833=   2.7077      
          
   
Regression line is, Ŷ=   2.7077   +
(   0.9834   )*x
..................
SSE=   (SSxx * SSyy - SS²xy)/SSxx =
   10.8028
std error ,Se =    √(SSE/(n-2)) =   
1.6434
................
confidence interval for slope      
           
α=   0.05      
       
t critical value=   t α/2 =   
2.776   [excel function: =t.inv.2t(α/2,df) ]  
   
estimated std error of slope = Se/√Sxx =   
1.6434/√38.4283=   0.265      
   
          
       
margin of error ,E= t*std error =    2.776  
*   0.265   =   0.736040
estimated slope , ß^ =    0.9834  
           
          
       
lower confidence limit = estimated slope - margin of error
=   0.9834   -   0.736  
=   0.2474
upper confidence limit=estimated slope + margin of error
=   0.9834   +   0.736  
=   1.7195
...................
Ho:   β1=   0
H1:   β1╪   0
n=   6  
alpha =   0.05  
estimated std error of slope =Se(ß1) = Se/√Sxx =   
1.6434/√38.4283=   0.2651
t stat = estimated slope/std error =ß1 /Se(ß1) =   
(0.9834-0)/0.2651=   3.71
Degree of freedom ,df = n-2=  
4  
      
p-value =    0.0207  
decison :    p-value<α , reject Ho  
Conclusion:   Reject Ho and conclude that slope is
significantly different from zero  
.................
thanks
please upvote