Mean = 7.695 



Standard Deviation = 1.876 



Figure 15. 



10 12 



Diameter (in) 



Frequency and probability distribution — 

 Warren Lobster House. 



Using the equations presented in the STATISTICAL SAMPLING THEORY 

 section for sampling by variables, a small sample (11 piles) was randomly 

 selected from the total data set for each pier. As the samples were 

 acquired, the sample size was recalculated using the mean and standard 

 deviation of the sample data. If required, additional samples were then 

 randomly selected from the remaining data until the calculated sample 

 size was less than the number of samples selected. 



Based on the analysis conducted during this study, it was found 

 that the required sample size varied from a minimum of 5 piles to a 

 maximum of 37 piles depending on the degree of deterioration found in 

 the pier. The mean diameter calculated for each sample was within 

 0.5 inch of the mean diameter calculated for the entire population for 

 each pier. This was well within the 10-percent accuracy and 90-percent 

 confidence level used to determine the required sample sizes. 



Another objective of this study was to determine if the magnitude 

 of the required maintenance could be determined from the data sample. 

 To demonstrate the suitability of making these predictions based on 

 sample probability distributions, an effective diameter of 7 inches was 

 selected as the critical diameter for replacement. The actual percentage 

 of pilings having a minimum effective diameter less than 7 inches was 

 compared to the predicted percentage of pilings with diameters less than 

 7 inches obtained from random samples from each pier. Results of this 

 analysis are presented in Table 1. From these data, it can be seen that 



18 



