Surevying Phonebooks

STA2PR

Surveying Phone Books

Abstract

It is hypothesized that 10% of residential phone numbers in the 2010>2011 Melbourne White Pages end in one. However, due to the fact that random allocation may not be in effect this may not be true. The aim of this research is to use random samples generated by Minitab to estimate if 10% of residential phone numbers end in one using a cluster sampling method.

Introduction

To complete the research the population has been selected randomly from the Melbourne White Pages. However, this may affect our final result as the residential phone numbers may not have been randomly allocated, and each column (cluster) may not contain the same number of phone numbers.

It is hypothesized that 10% of residential phone numbers in Melbourne White Pages end in one. However, the results could show that more than 10% of the residential phone numbers end in one or that less that 10% of numbers end in one.

Cluster sampling was used as the data collection method as it is the sampling method which delivers the highest precision for the least time cost.

An initial 10 clusters were chosen so that we could estimate how many additional clusters we would require for a given error. The 10 clusters were generated randomly using Minitab and the results were compiled. Then, the further results were compiled from the additional clusters, stacked with the initial clusters and then the descriptive statistics were calculated.

Sampling Design and Theory

There are a number of sampling methods that could be used to sample the data. Such sampling techniques are (but not limited to); Simple Random Sampling, Stratified Random Sampling, Systematic Sampling and Cluster Sampling.

A simple random sample is obtained by choosing elementary units in search a way that each unit in the population has an equal chance of being selected. A simple random sample is free from sampling bias. However, using a random number table to choose the elementary...