T-test PDF

Parametric tests Introduction to T-test Biostatistics for Pharmaceutical Sciences - PHRM 103 – Practical 2 Department of Pharmacy Practice, College of Pharmacy, Taibah University 2024-1446...

Parametric tests Introduction to T-test Biostatistics for Pharmaceutical Sciences - PHRM 103 – Practical 2 Department of Pharmacy Practice, College of Pharmacy, Taibah University 2024-1446 1  Learning Objectives By the end of this presentation, students will be able to: 1) Understand the basic concept and purpose of a t-test. 2) Differentiate between independent t-tests and paired t-tests. 3) Identify when it is appropriate to use a t-test in pharmacy practice. 4) Interpret the t-value and p-value results to assess the significance of differences. 5) Apply t-tests to compare the effectiveness of drugs or treatments using real-world clinical examples. 6) Recognize the assumptions underlying t-tests and common pitfalls to avoid. 2 What is a T-Test? A t-test is a statistical test used to compare the means (averages) of two groups. Goal: To determine if the difference between the two group means is statistically significant (i.e., unlikely to have happened by chance). Importance: Frequently used in clinical trials, research studies, and drug comparisons. 3  Why Should we Learn T-Tests? Clinical Application: Helps in comparing the effectiveness of two drugs, or a treatment before and after administration. Interpreting Research: T-tests are commonly used in research studies published in medical and pharmaceutical journals. Decision-Making: Provides evidence for choosing between different treatment options based on patient data. 4 When Do We Use a T-Test? Two groups only: T-tests are used when comparing exactly two groups or conditions. Example: Drug A vs. Drug B, or pre-treatment vs. post-treatment results. Continuous data: The data being compared should be numerical and continuous, such as blood pressure, glucose levels, or cholesterol. Normally distributed data: The data should follow a normal distribution (bell-shaped curve), which means most of the data points cluster around the mean. 5  Types of T-Tests There are two main types of t-tests: 1.Independent T-Test (also called two-sample t-test) 1.Used to compare the means of two different groups. 2.Example: Comparing the effects of Drug A on one group of patients and Drug B on another. 2.Paired T-Test (also called dependent t-test) 1.Used to compare the means of the same group at two different times. 2.Example: Comparing a patient’s blood pressure before and after taking a drug. 6  Independent T-Test Scenario: You want to compare the effect of two cholesterol- lowering drugs, Drug A and Drug B, in two different groups of patients. Hypotheses: Null hypothesis (H₀): There is no difference in cholesterol reduction between Drug A and Drug B. Alternative hypothesis (H₁): There is a difference in cholesterol reduction between Drug A and Drug B. 7  Paired T-Test Scenario: You are studying whether Drug X lowers blood pressure in a group of 50 patients. You measure each patient’s blood pressure before and after 6 weeks of taking Drug X. Hypotheses: Null hypothesis (H₀): There is no difference in blood pressure before and after taking Drug X. Alternative hypothesis (H₁): There is a difference in blood pressure before and after taking Drug X. 8 Key Concepts: Null and Alternative Hypotheses Null Hypothesis (H₀): Assumes that there is no significant difference between the two group means (e.g., both drugs have the same effect). Alternative Hypothesis (H₁): Assumes that there is a significant difference between the two group means (e.g., one drug is more effective than the other). 9  Steps in a T-Test State the Hypotheses: Define the null and alternative hypotheses. Collect Data: Gather the data for both groups (e.g., blood pressure readings). Perform the T-Test: Calculate the t-value to compare the two group means. Check the p-value: Compare the p-value to a significance level (usually 0.05) to determine if the result is statistically significant. 10  Understanding the t-Value The t-value represents how different the two groups are relative to the variability within the groups. A larger t-value suggests a greater difference between the two groups. The t-value formula depends on the difference in the means of the groups, the sample size, and the variability (standard deviation) within the groups. 11  Understanding the p-Value The p-value tells us the probability that the observed difference happened by chance. p < 0.05: The difference is statistically significant. This means there’s less than a 5% chance that the observed difference is due to random variation. p > 0.05: The difference is not statistically significant, meaning it could be due to chance. 12  Paired T-Test Example Scenario: You want to see if Drug X significantly reduces blood pressure in a group of 50 patients. Mean blood pressure before treatment: 150 mmHg. Mean blood pressure after treatment: 140 mmHg. Paired data: Since you are measuring the same patients before and after treatment, you would use a paired t-test. 13  T-Test Assumptions Before performing a t-test, the following assumptions must be met: 1.Data is normally distributed: The outcome (e.g., blood pressure, cholesterol levels) should follow a normal distribution. 2.Equal variances: The variability in both groups should be similar (for independent t-tests). 3.Independence of observations: Each data point in the groups should be independent of the others (for independent t-tests). 14  Common Mistakes to Avoid Not checking for normality: The data must be approximately normally distributed for a valid t-test. Using a t-test for more than two groups: T-tests are only used for two groups. For more groups, use an ANOVA. Ignoring outliers: Outliers can skew the results, leading to incorrect conclusions. 15  Summary and Takeaways T-tests are a simple, yet powerful tool to compare two groups and determine if the differences are statistically significant. T-tests are essential in clinical trials, research, and making evidence-based decisions in pharmacy practice. Key concepts: Understanding the null hypothesis, p-values, and assumptions ensures the correct application of t-tests. Practical importance: Mastering t-tests allows you to critically analyze studies and make informed decisions in healthcare. 16