# Case Study 3

## Contents

## Case study 3: Beef self-sufficiency (based on slaughter statistics)

### Introduction to case study

The number, type and date of livestock slaughtered at abattoirs in Indonesia are recorded in iSIKHNAS. We will examine the cattle records.

We will determine whether there are changes in the number of different classes (e.g. female productive versus Australian imported cattle) of cattle slaughtered over the collection period of iSIKHNAS. We can make tentative conclusions about Indonesiaâ€™s quest for beef self-sufficiency based on changes in the slaughter of different categories of cattle.

It is important to note that the data used in this training course was downloaded in early 2014. This data was collected when iSIKHNAS had been operating for approximately a year in a limited area of Indonesia. The incomplete nature of our data means that no real conclusions can be made about the results of data-analyses conducted in this course. However, over time more complete data will be available for Indonesians to conduct better analyses.

### Skills to be developed during this case study

- Data management
- Summarise data with plots
- Understanding of null and alternative hypotheses
- Hypothesis testing using a statistical test

### List of files for case study

**Data**

**Videos**

**Notes: Key concepts for hypothesis testing and Case Study 3**

### Steps in analysis of Case study 3 (exercises)

#### Step 1: Objective

**Exercise 15:**

Break into small groups and discuss the objective of the case study. Do the hypotheses support the objective of the analyses?

Report back to the group with your conclusions.

**Hint:**

The broader focus of the analysis is to address an issue of concern for Indonesia, namely achievement of self-sufficiency in beef production. One way to understand whether self-sufficiency is increasing is to examine slaughter statistics.

Hypotheses are:

Null hypothesis: Month and slaughter categories are independent. That is, there is no effect of month on total slaughter numbers in different categories of slaughtered cattle.

Alternative hypothesis = Month and slaughter categories are dependant. That is, there is an effect of month on total slaughter numbers in different categories of slaughtered cattle.

Are these hypotheses adequate?

**Exercise 15: Do the hypotheses support the objective of the analyses?**

Write brief notes on group discussions of this topic.

#### Step 2: Data management

Back up your data before you alter it!

**Exercise 16: Question (create a pivot table of cattle slaughter statistics by month). **

**Hint:**

Select all the cattle data from the Excel worksheet titled *Abattoir 2014.xls* and save in a fresh work sheet. Open cattle slaughter data, error check and create a contingency table (pivot table in Excel).

**Watch video now.** Note you have already done some of this in previous exercises.

**Exercise 16: Answer (create a pivot table of cattle slaughter statistics by month). **

Include the pivot table you created below.

#### Step 3: Description of data

**Exercise 17: Question (summary plots)**

Do some summary plots for the contingency table. The aim is to understand the data before hypothesis testing.

**Hint: Watch the video for assistance.**

**Exercise 17: Answer (summary plots)**

Include the summary plots you created below.

#### Step 4: Statistical hypothesis testing

**Exercise 18: Question (chi-squared analysis of slaughter data)**

Conduct a chi-squared statistical test on the pivot table.

**Hint:** **Watch this video now.**

**Exercise 18: Answer (chi-squared analysis of slaughter data)**

Include your chi-squared test results below.

**Exercise 19: Question (inference)**

Break into your groups and discuss the findings of the significant chi-squared test. What does it mean? That is, make some inferences.

**Hint:**

Look at the result of the statistical test. Look at the summary plots from exercise 17 and look at the expected verse observed values from exercise 18. Where are the major differences between expected and observed values that are most contributing to the size of the chi-squared statistic? These are the areas where the effect is largest.

**Exercise 19: Answer (inference)**

Write brief notes on group discussions on inference about the significant chi-squared test result for the slaughter data.

#### Summary of case study 3

In this case study you were first presented with information on the basic statistical hypothesis testing approach. This can be complex, but is a consistent approach used in many studies. Then you again conducted several important steps in data analysis:

- The hypotheses were checked to see that they supported the objective
- Managed data (by backing up your original data, examining the data for errors and creating new data)
- Described data with contingency tables and plots
- Conducted hypothesis testing

This time you conducted hypothesis testing with a formal statistical approach using a chi-squared test. The major steps in the hypothesis testing approach can be used for most datasets. You now have the general skills to do this. With time and experience you will improve your knowledge of which statistical test to use and how to apply them.

**This ends case study 3. **