By the end of this chapter, you will be able to: - identify the right hypothesis test for your organization's objectives with confidence - determine hypothesis errors accurately based on the goals of your organization - find and mark critical and acceptance regions correctly using the data provided - carry out Z-tests and T-tests correctly and efficiently with real-world data
Mastering these skills will help you make informed decisions and add value to your workplace through reliable data analysis.
Testing hypothesis is a fundamental quantitative technique used by accountancy professionals in Kenya to make informed decisions based on sample data. It provides a structured framework for evaluating assumptions about financial data, audit results, or economic indicators, which is crucial in environments with incomplete information. This chapter introduces the key terms used in hypothesis testing, laying the groundwork for applying these concepts to accounting problems such as financial statement analysis, fraud detection, and budgeting.
In hypothesis testing, the null hypothesis (\(H_0\)) is the default assumption that there is no effect or no difference in the population parameter. The alternative hypothesis (\(H_a\)) represents a statement that contradicts \(H_0\), indicating the presence of an effect or difference. Formally, the hypotheses are stated as:
$$ H_0: \theta = \theta_0 $$
$$ H_a: \theta \neq \theta_0 \quad \text{or} \quad H_a: \theta > \theta_0 \quad \text{or} \quad H_a: \theta < \theta_0 $$
where \(\theta\) is the population parameter under consideration (e.g., mean, proportion).
Example 1: A bank claims the average processing time of loan applications is 5 days. Test whether the average processing time differs from 5 days.
Given: \(H_0: \mu = 5\) days, \(H_a: \mu \neq 5\) days
Example 2: A SACCO estimates the average loan default rate is less than 2%. Formulate the hypotheses.
Given: \(H_0: p = 0.02\), \(H_a: p < 0.02\)
Example 3: A retail business wants to test if the average monthly sales exceed Ksh 1,000,000.
Given: \(H_0: \mu = 1,000,000\) Ksh, \(H_a: \mu > 1,000,000\) Ksh
The significance level (\(\alpha\)) is the probability threshold for rejecting the null hypothesis when it is actually true (Type I error). Common values are 0.05 or 0.01 in accounting studies. The critical region is the set of values of the test statistic that leads to rejection of \(H_0\).
$$ P(\text{reject } H_0 | H_0 \text{ true}) = \alpha $$
The critical values define the boundaries of the critical region.
Example 1: For \(\alpha = 0.05\), determine the critical values for a two-tailed test with a normal distribution.
Given: \(\alpha = 0.05\), two-tailed test
Example 2: A county government auditor sets \(\alpha = 0.01\) for testing if expenditure exceeds budget. Find the critical value for a right-tailed z-test.
Given: \(\alpha = 0.01\), right-tailed test
Example 3: For \(\alpha = 0.10\), find the critical region for a left-tailed test on monthly revenue.
Given: \(\alpha = 0.10\), left-tailed test
Type I error occurs when \(H_0\) is rejected although it is true. The probability of this error is the significance level \(\alpha\). Type II error happens when \(H_0\) is not rejected although it is false, with probability \(\beta\). Minimizing both errors is crucial in financial decision-making to avoid false audit conclusions or wrong investment decisions.
$$ \text{Type I error probability} = \alpha $$
$$ \text{Type II error probability} = \beta $$
Example 1: If \(\alpha = 0.05\), calculate the probability of Type I error.
Given: \(\alpha = 0.05\)
Example 2: A SACCO tests if default rate is 3%, with \(\beta = 0.10\). What is the probability of Type II error?
Given: \(\beta = 0.10\)
Example 3: Explain the trade-off between \(\alpha\) and \(\beta\) when auditing financial statements.
Given: \(\alpha = 0.01\), \(\beta = 0.20\)
The test statistic is a standardized value computed from sample data used to decide whether to reject \(H_0\). The p-value is the probability of observing a test statistic as extreme as the one obtained, assuming \(H_0\) is true. Hypothesis rejection occurs if the p-value is less than \(\alpha\).
$$ \text{p-value} = P(\text{Test statistic} \geq \text{observed value} | H_0) $$
Example 1: Given a sample mean and standard deviation, calculate the z-test statistic for testing a mean.
Given: Sample mean = 105, population mean = 100, standard deviation = 15, sample size = 30
Example 2: Calculate the p-value for a test statistic \(z = 2.33\) in a right-tailed test.
Given: \(z = 2.33\)
Example 3: In an audit, a test statistic \(t = -1.8\) with 20 degrees of freedom is observed. Find the p-value for a two-tailed test.
Given: \(t = -1.8\), df = 20
Create a free account to open more of this chapter.
Free: practical guides, quick cards, workplace scenarios and more.
Create a free accountThis chapter introduces the fundamental terms used in hypothesis testing, providing a clear understanding of concepts such as null and alternative hypotheses. It then explores the different types of hypotheses, distinguishing between simple and composite forms. The discussion advances to the errors encountered during testing, specifically Type 1 and Type 2 errors, explaining their significance and consequences. Students learn about critical and acceptance regions, which are essential for decision-making in hypothesis testing. The chapter also covers the application of Z-tests and T-tests, detailing when and how each test is used depending on sample size and population variance knowledge. Finally, it highlights emerging issues reports that address current challenges and developments in hypothesis testing methods. This comprehensive overview equips students with the necessary skills to conduct and interpret hypothesis tests confidently.
A company claims that the average monthly salary of its accountants is Ksh 80,000. A sample of 40 accountants has a mean salary of Ksh 78,500 with a population standard deviation of Ksh 5,000. Test the claim at 5% significance level using a Z-test. (3 marks)
A sample of 25 auditors showed a mean working experience of 6.2 years with a sample standard deviation of 1.5 years. The national average is 5.8 years. Test whether the auditors in the sample have significantly different experience from the national average at 5% significance level using a T-test. (4 marks)
At the start of this chapter we promised you would be able to:
Tick each one you can genuinely do.
So, are you there yet?
You're competent when you can confidently do 50% or more of what this chapter promised.
Sign in to record how you're doing.