{"id":9428,"date":"2026-06-01T21:33:48","date_gmt":"2026-06-01T21:33:48","guid":{"rendered":"https:\/\/kapdec.com\/help\/?p=9428"},"modified":"2026-06-01T21:33:48","modified_gmt":"2026-06-01T21:33:48","slug":"set-up-and-conduct-the-testing","status":"publish","type":"post","link":"https:\/\/kapdec.com\/help\/set-up-and-conduct-the-testing\/","title":{"rendered":"Set-up And Conduct The Testing"},"content":{"rendered":"

Unit: <\/strong>inference for Quantitative Data: Means<\/strong><\/h2>\n

Chapter: <\/strong>Setting up and carry the testing<\/strong><\/h3>\n

Reference: – Null and alternative hypotheses, significance level, One sample z-test and t-test, Two sample tests, Type 1 and Type 2 errors, p value interpretation, Critical value and rejection Regions, chi-square test, paired t-test.<\/em><\/p>\n

After studying this chapter, you should be able to:<\/strong><\/p>\n

    \n
  • Null and alternative hypotheses.<\/li>\n
  • Two sample tests.<\/li>\n
  • Paired t-test.<\/li>\n
  • Critical value and rejection Regions.<\/li>\n<\/ul>\n

    Null and alternative hypotheses.<\/strong><\/p>\n

      \n
    • Purpose of Hypotheses: Hypotheses are statements that propose a specific claim about a population parameter, such as a mean, proportion, or difference. The null hypothesis (H0) typically represents a default or no-effect assumption, while the alternative hypothesis (Ha) represents the claim you're trying to test.<\/li>\n
    • Symbolic Representation: Null and alternative hypotheses are often written symbolically. H0 represents the null hypothesis, and Ha represents the alternative hypothesis. For example, H0: μ = μ0 (population mean is equal to a specific value) and Ha: μ ≠ μ0 (population mean is not equal to the specific value).<\/li>\n
    • Relationship Between H0 and Ha: The null and alternative hypotheses are complementary. Rejecting the null hypothesis provides evidence in favor of the alternative hypothesis, while failing to reject the null hypothesis implies that there's insufficient evidence to support the alternative claim.<\/li>\n
    • Directional vs. Non-Directional: The alternative hypothesis can be directional (one-sided) or non-directional (two-sided). A directional alternative hypothesis specifies a particular direction of effect (greater than or less than), while a non-directional alternative does not specify a direction.<\/li>\n
    • Testable Statements: Hypotheses must be testable using sample data. They should make specific claims about a population parameter that can be evaluated statistically based on the observed data.<\/li>\n
    • Type I and Type II Errors: Hypothesis testing involves the risk of making Type I errors (rejecting H0 when it's true) and Type II errors (failing to reject H0 when Ha is true). The choice of significance level (α) affects the balance between these errors.<\/li>\n
    • Research and Null Hypotheses: The research hypothesis is often derived from prior research, theory, or observations. It proposes a specific effect or difference. The null hypothesis provides a baseline against which the research hypothesis is tested.<\/li>\n
    • Testing Claims: Hypothesis testing is a formal process to evaluate the validity of a claim. It involves calculating a test statistic and comparing it to a critical value or p-value to determine whether there's enough evidence to reject the null hypothesis.<\/li>\n
    • P-Value Interpretation: The p-value is a measure of the strength of evidence against the null hypothesis. A small p-value suggests that the observed data is unlikely under the null hypothesis, leading to its rejection in favor of the alternative hypothesis.<\/li>\n
    • Level of Significance: The significance level (α) determines the threshold for considering a result statistically significant. Common choices are 0.05 or 0.01. If the p-value is less than α, the null hypothesis is rejected; otherwise, it's not rejected.<\/li>\n<\/ul>\n

      Two sample tests.<\/strong><\/p>\n

        \n
      • Comparing Two Populations: Two-sample tests are used to compare the means, proportions, or variances of two independent populations or groups. These populations could represent different treatments, groups, or conditions.<\/li>\n
      • Null and Alternative Hypotheses: In a two-sample test, the null hypothesis (H0) typically states that there is no significant difference between the two populations, while the alternative hypothesis (Ha) asserts a specific claim about the difference.<\/li>\n
      • Independent Samples: Two-sample tests assume that the samples from the two populations are independent of each other. This means that the observations in one sample are not related to or dependent on the observations in the other sample.<\/li>\n
      • Equal Variances or Unequal Variances: Depending on whether the population variances are assumed to be equal or unequal, you choose between the two-sample t-test (equal variances) or the Welch's t-test (unequal variances) for comparing means.<\/li>\n
      • Pooling of Variances: In the equal variances case, you may pool the variances of the two samples to estimate a common variance for the t-test calculation. Pooling is appropriate when there's no evidence of significant variance differences.<\/li>\n
      • Degrees of Freedom: The degrees of freedom for the t-distribution in a two-sample t-test depend on the sample sizes and whether you're assuming equal or unequal variances. Welch's t-test adjusts the degrees of freedom when variances are unequal.<\/li>\n
      • Pooled Sample Proportion: For two-sample tests involving proportions, a pooled sample proportion is used to estimate the common population proportion under the null hypothesis. This pooled proportion considers both samples.<\/li>\n
      • Paired vs. Independent Samples: In two-sample tests, samples can be either paired (dependent) or independent. Paired samples are matched pairs, such as before-and-after measurements, while independent samples have no inherent pairing.<\/li>\n
      • Test Statistic and P-Value: The test statistic is calculated based on the difference between sample statistics (means or proportions) and their standard errors. The p-value represents the probability of observing a difference as extreme as the one calculated under the null hypothesis.<\/li>\n
      • Interpretation of Results: After conducting a two-sample test, you interpret the results by comparing the p-value to the significance level (α). If the p-value is less than α, you reject the null hypothesis and conclude that there's evidence of a significant difference between the populations.<\/li>\n<\/ul>\n

        Paired t-test.<\/strong><\/p>\n

          \n
        • Dependent Samples: The paired t-test is used when dealing with dependent or paired samples. These samples involve related observations, such as before-and-after measurements on the same subjects or matched pairs.<\/li>\n
        • Purpose: The paired t-test is used to determine if there is a significant difference between the means of two related populations or treatments. It evaluates whether the observed differences are likely due to actual effects or simply due to random variability.<\/li>\n
        • Null and Alternative Hypotheses: The null hypothesis (H0) states that there is no significant difference between the paired means, while the alternative hypothesis (Ha) asserts that there is a significant difference.<\/li>\n
        • Calculating Differences: The paired t-test involves calculating the differences between paired observations (after – before). These differences represent the changes or effects of the treatment.<\/li>\n
        • Mean of Differences: The mean of the differences is calculated and serves as the point estimate for the population mean difference. This is denoted by ¯d (x-bar d).<\/li>\n
        • Standard Error: The standard error of the mean difference (SE) is calculated using the standard deviation of the differences and the square root of the sample size.<\/li>\n
        • Test Statistic and Degrees of Freedom: The test statistic (t) is calculated by dividing the mean difference by the standard error. The degrees of freedom (df) are n – 1, where n is the number of paired observations.<\/li>\n
        • P-Value and Significance Level: The p-value represents the probability of observing a test statistic as extreme as the one calculated, assuming the null hypothesis is true. It's compared to the significance level (α) to make a decision about rejecting the null hypothesis.<\/li>\n
        • Assumptions: The paired t-test assumes that the differences are approximately normally distributed and that the paired observations are dependent, random, and representative of the population.<\/li>\n
        • Interpreting Results: If the p-value is less than the chosen significance level (α), you can reject the null hypothesis and conclude that there is evidence of a significant difference between the paired means. Otherwise, you fail to reject the null hypothesis.<\/li>\n<\/ul>\n

          Critical value and rejection regions.<\/strong><\/p>\n

           <\/p>\n

            \n
          • Significance Level (α): The significance level (α) is a predetermined threshold used to determine whether to reject the null hypothesis. Common values are 0.05 or 0.01, representing the probability of making a Type I error.<\/li>\n<\/ul>\n

             <\/p>\n

              \n
            • Critical Values: Critical values are specific values from a probability distribution (such as the t-distribution or the standard normal distribution) that define the boundaries of the rejection region. They correspond to the extreme values beyond which the null hypothesis is rejected.<\/li>\n<\/ul>\n

               <\/p>\n

                \n
              • Rejection Region: The rejection region is the range of values for the test statistic that leads to the rejection of the null hypothesis. It is determined by the critical values and the chosen significance level.<\/li>\n<\/ul>\n

                 <\/p>\n

                  \n
                • One-Tailed and Two-Tailed Tests: In a one-tailed test, the rejection region is located in one tail of the distribution (either the left or the right). In a two-tailed test, the rejection region is divided into two tails, representing extreme values on both sides of the distribution.<\/li>\n<\/ul>\n

                   <\/p>\n

                    \n
                  • Critical Value Calculation: Critical values are often determined using tables, calculators, or statistical software based on the chosen significance level and the degrees of freedom for the distribution.<\/li>\n<\/ul>\n

                     <\/p>\n

                      \n
                    • Degrees of Freedom: The degrees of freedom for critical value calculation depend on the specific distribution being used (e.g., t-distribution, chi-square distribution). It reflects the variability in the sample data.<\/li>\n<\/ul>\n

                       <\/p>\n

                        \n
                      • Visualizing Critical Values: Critical values can be plotted on a probability distribution curve to visually represent the rejection region. This helps in understanding which values lead to the rejection of the null hypothesis.<\/li>\n<\/ul>\n

                         <\/p>\n

                          \n
                        • P-Value Comparison: The critical value approach is conceptually similar to comparing the calculated p-value to the significance level. If the p-value is smaller than α, the null hypothesis is rejected; if the test statistic falls in the rejection region, the null hypothesis is also rejected.<\/li>\n<\/ul>\n

                           <\/p>\n

                            \n
                          • Interpreting Results: If the test statistic falls within the rejection region (beyond the critical values), you reject the null hypothesis in favor of the alternative hypothesis. If it falls outside the rejection region, you fail to reject the null hypothesis.<\/li>\n<\/ul>\n

                             <\/p>\n

                              \n
                            • Type I Error: Rejecting the null hypothesis when it's actually true is a Type I error. The probability of making a Type I error is equal to the chosen significance level (α).<\/li>\n<\/ul>\n

                               <\/p>\n

                              Example: <\/strong>A manufacturer claims that their new smartphone model has an average battery life of at least 30 hours. To test this claim, a random sample of 50 smartphones was selected, and their battery lives were recorded. The sample mean battery life was found to be 29.5 hours, with a sample standard deviation of 3.2 hours. Use a significance level of 0.05 to test the manufacturer's claim.<\/p>\n

                              Solution<\/strong>: –<\/p>\n

                              Step 1: Setting Up Hypotheses:<\/p>\n

                              Null Hypothesis (H0): The average battery life of the new smartphone model is 30 hours or less. H0: μ ≤ 30.<\/p>\n

                              Alternative Hypothesis (Ha): The average battery life of the new smartphone model is greater than 30 hours. Ha: μ > 30.<\/p>\n

                              Step 2: Choosing the Significance Level:<\/p>\n

                               <\/p>\n

                              The significance level (α) is given as 0.05.<\/p>\n

                               <\/p>\n

                              Step 3: Calculating the Test Statistic:<\/p>\n

                               <\/p>\n

                              Given:<\/p>\n

                               <\/p>\n

                              Sample mean (x\u0304) = 29.5 hours<\/p>\n

                              Sample standard deviation (s) = 3.2 hours<\/p>\n

                              Sample size (n) = 50<\/p>\n

                              We'll use the formula for the t-test when the population standard deviation is unknown:<\/p>\n

                              t = (x\u0304 – μ) \/ (s \/ √n)<\/p>\n

                               <\/p>\n

                              Calculating the t-test statistic:<\/p>\n

                              t = (29.5 – 30) \/ (3.2 \/ √50) ≈ -1.664<\/p>\n

                               <\/p>\n

                              Step 4: Finding the Critical Value or P-Value:<\/p>\n

                               <\/p>\n

                              Since this is a one-tailed test (greater than), we need to find the critical value from the t-distribution with 49 degrees of freedom at the 0.05 significance level. Using a t-table or calculator, the critical value is approximately 1.677.<\/p>\n

                               <\/p>\n

                              Step 5: Making a Decision:<\/p>\n

                               <\/p>\n

                              Comparing the calculated t-test statistic (-1.664) with the critical value (1.677):<\/p>\n

                               <\/p>\n

                              Since -1.664 is not greater than 1.677, we fail to reject the null hypothesis.<\/p>\n

                              Step 6: Interpreting the Results:<\/p>\n

                               <\/p>\n

                              Based on the sample data and the significance level of 0.05, we do not have enough evidence to reject the manufacturer's claim that the average battery life of the new smartphone model is at least 30 hours.<\/p>\n

                              Key Points<\/strong><\/p>\n

                                \n
                              • The binomial distribution models the number of successes in a fixed number of independent trials, where each trial has the same probability of success.<\/li>\n<\/ul>\n

                                 <\/p>\n

                                  \n
                                • It deals with discrete outcomes (usually "success" and "failure") and is characterized by parameters "n" (number of trials) and "p" (probability of success).<\/li>\n<\/ul>\n

                                   <\/p>\n

                                    \n
                                  • The Probability Mass Function (PMF) gives the probability of getting exactly "k" successes in "n" trials and is calculated using the binomial coefficient: P(X = k) = C(n, k) * pk<\/sup> * (1 – p)n-k<\/sup>.<\/li>\n<\/ul>\n

                                     <\/p>\n

                                      \n
                                    • The mean (expected value) of a binomial distribution is μ = np, and the variance is σ² = np(1 – p).<\/li>\n<\/ul>\n

                                       <\/p>\n

                                        \n
                                      • Conditions for the binomial distribution include independent trials, fixed probability of success, and a fixed number of trials.<\/li>\n<\/ul>\n

                                         <\/p>\n

                                          \n
                                        • The geometric distribution models the number of trials needed to achieve the first success in a sequence of independent trials, each with a fixed probability of success.<\/li>\n<\/ul>\n

                                           <\/p>\n

                                            \n
                                          • It's a discrete distribution with a parameter "p" (probability of success on each trial).<\/li>\n<\/ul>\n

                                             <\/p>\n

                                              \n
                                            • The PMF of the geometric distribution gives the probability of needing exactly "k" trials to achieve the first success: P(X = k)<\/li>\n<\/ul>\n

                                               <\/p>\n

                                                \n
                                              • The mean of the geometric distribution is μ = 1\/p, and the variance is σ² = (1 – p) \/ p².<\/li>\n<\/ul>\n

                                                 <\/p>\n

                                                  \n
                                                • The geometric distribution exhibits the memoryless property, meaning the probability of success on the next trial is unaffected by past trials.<\/li>\n<\/ul>\n

                                                   <\/p>\n

                                                    \n
                                                  • Binomial distributions are used in scenarios with a fixed number of trials and a constant probability of success, like counting successes in manufacturing inspections.<\/li>\n<\/ul>\n

                                                     <\/p>\n

                                                      \n
                                                    • Geometric distributions model scenarios where you're interested in the number of trials required to achieve the first success, such as waiting times or attempts until a rare event occurs.<\/li>\n<\/ul>\n

                                                       <\/p>\n

                                                        \n
                                                      • The binomial distribution considers a fixed number of trials and counts the number of successes, while the geometric distribution focuses on the number of trials needed for the first success.<\/li>\n<\/ul>\n

                                                         <\/p>\n

                                                          \n
                                                        • The binomial distribution is applicable when you're interested in the number of successes out of a fixed number of trials, while the geometric distribution deals with the number of trials until a specific outcome.<\/li>\n<\/ul>\n

                                                           <\/p>\n

                                                            \n
                                                          • Calculators and statistical software are useful for computing probabilities, means, and variances in both binomial and geometric distributions.<\/li>\n<\/ul>\n

                                                             <\/p>\n","protected":false},"excerpt":{"rendered":"

                                                            Unit: inference for Quantitative Data: Means Chapter: Setting up and carry the testing Reference: – Null and alternative hypotheses, significance level, One sample z-test and t-test, Two sample tests, Type 1 and Type 2 errors, p value interpretation, Critical value and rejection Regions, chi-square test, paired t-test. After studying this chapter, you should be able […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[630],"tags":[],"class_list":["post-9428","post","type-post","status-publish","format-standard","hentry","category-ap-statistics"],"_links":{"self":[{"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/posts\/9428","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/comments?post=9428"}],"version-history":[{"count":0,"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/posts\/9428\/revisions"}],"wp:attachment":[{"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/media?parent=9428"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/categories?post=9428"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kapdec.com\/help\/wp-json\/wp\/v2\/tags?post=9428"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}