ISDS702 - Week 2 - Hypothesis Testing Notes.docx - ISDS702 Week 2 Hypothesis Testing Notes Overview Good Morning This week we will talk about the

ISDS702 - Week 2 - Hypothesis Testing Notes.docx - ISDS702...

This preview shows page 1 - 2 out of 23 pages.

ISDS702 - Week 2 - Hypothesis Testing Notes Overview Good Morning, This week we will talk about the concept of hypothesis testing and conduct z and t tests to practice this concept. There are some theory and definitions this week. Please make sure you understand these theories and definitions before you take the quiz. If you have any questions ask me or your class mates. I am planning to hold another meeting this Thursday at 5 pm (central time) for your questions. I will send you a meeting invitation in an email. Apart from the quiz, please do not forget to complete the Excel assignment. Best of luck! Dr. Koksal Week 1 Quiz Overview Dear Students, Due to school’s no return policy, quizzes in this course are not open to review after they are graded. However, I will provide general feedback for each quiz so that you can refer back to the material accordingly. Please find below an overview of Week 1 quiz. The average grade for Week 1 quiz was 52.67 out of 60. This is almost 88%, congratulations! I went through the quiz to identify the questions with which students struggled the most. According to the results, one of the concepts students struggled with is discrete/continuous random variables. Please refer to the course video to review these concepts. Just as a summary, continuous random variables can take any value within an interval. Discrete random variables on the other hand can only take certain values. For example, say a scientist is studying wolves. Weight is an example of a continuous random variable, because the weight of a wolf can take any value between, let’s say 50 and 180 pounds. So a wolf can weigh 120 pounds, or 120.2 pounds, or 120.22 pounds, etc. On the other hand, size of a wolf pack is a discrete variable. For example we can talk about a pack of 9 wolves, but it makes little sense to talk about a pack of 9.2 wolves. This is because 9.2 is not a value the size variable can take. I also noticed that the z score is a concept some students struggled with. The z score is a measure of the distance in standard deviations between any given value and the mean of the sample/population from which the value is drawn. For example, if the z score of a variable X is 2, we say that X is 2 standard deviations above the mean. If the z score is -2, we say that X is 2 standard deviations below the mean. z = (x - µ)/σ Looking at the formula above, we can say that one is more likely to find a larger z score when the standard deviation is small (when the denominator is small). Similarly, a large numerator (a greater difference between a given X value and its mean) will also lead to a larger z score. Keep in mind that the probability of an event and the probability of the complement of that event add up to 1. For instance, let's say we have an event X. Assume that event Y is the complement of event X. Than P(X) + P(Y) = 1.
Image of page 1
Image of page 2

You've reached the end of your free preview.

Want to read all 23 pages?

  • Fall '15
  • Null hypothesis, Statistical hypothesis testing

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture