DATA ANALYSIS

Collecting and Using Business Data



Collecting and Using Business Data

Introduction

The statistical test to determine the significance of the difference in the observed frequencies is called Chi Square test of independence. This test can be used even with measured data on a nominal scale. The null hypothesis of the chi-square postulates a fully specified probability distribution as the mathematical model of the population that generated the sample. This test applies when we want to show independence or dependence of two criteria in an experiment (Alexeyev, 2000).

If there is perfect agreement between the observed and expected frequencies statistic takes a value of 0, on the contrary, if there is a large discrepancy between these frequencies the statistic takes a large value and, therefore, reject the null hypothesis. Thus, the critical region is located in the upper end of the Chi-square distribution with k-1 degrees of freedom (Balnaves, 2007). More samples can be classified according to a number of columns (criterion 1) and line (criterion 2). The chi-square test applies only to discrete acts , but it can be used also for samples grouped into continuous classes (Alexeyev, 2000). In this study, a survey of the workforce of 200 employees in a company is conducted by using a questionnaire. Questionnaire gathered information about following factors: gender, employment grade, distance of living place from work, use of staff social club, and the way employees travel to work.

Two different questions that can be answered by the application of the Chi-squared hypothesis test on a contingency table drawn up (for each question) from the sample are listed below.

Research Question 1

First question of the research examines the relationship between the employment grade of employees and the use of staff social club. It examines to what extent employees are more likely to sue staff social club based on their employment grade.

Research Question 2

Second research question of the study examines the relationship between the employees' grading class and mode selected for travelling to work. It examines to what extent employees mode of traveling change based on their grade level in the organization. It examines if employees are working at higher level in the organization, are they more likely to drive to work or use other travel options.

Research Hypotheses

Null and alternate hypotheses based on above research questions are listed below.

Research Question 1 Null Hypothesis

H1: Use of staff social club is independent of the employee grading level in the organization.

Research Question 1 Alternate Hypothesis

H1: Use of staff social club is dependent on the employee grading level in the organization.

Research Question 2 Null Hypothesis

H2: There is no relationship between the employees grading level in the organization and selection of travel mode to work.

Research Question 2 Alternate Hypothesis

H2: Selection of travel mode to work is dependent on the employees grading level in the organization.

It can also be stated as:

H2: Employees are working at senior management level in the organization are more likely to drive to work.

Research Hypothesis 1 Testing Results

In order to statistically test first hypothesis, Pearson chi-square test was conducted on the ...