Lecture 11_hypothesis testing

Lecture 11_hypothesis testing - 10/4/2010 Hypothesis...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
10/4/2010 1 Hypothesis Testing 1 Overview • When conducting a research study, we examine relationships among variables • In psychology, we often ask questions about whether something we do to subjects changes them – We refer to the different actions we impose as treatments and seek to understand whether a given treatment had an effect 2 Overview • As we have seen, however, when we take samples from a population results vary from sample to sample • We need a mechanism to evaluate our findings to determine whether the observed relationship implies an effect occurred or whether the relationship is the result of chance alone 3
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/4/2010 2 Overview • In order to objectively evaluate our research questions, we use a standardized set of procedures called hypothesis tests • These procedures are formalized in a set of operations called significance testing – Hypothesis testing forms the basis of all inferential statistics that address comparative and relationship research questions 4 The Goal • With comparative questions, we want to know “is there a difference?” between something and another • Because sample statistics vary due to sampling error though the question is actually, “is the difference we observe greater than what would be expected due to chance alone?” • Significance testing provides a means for us to answer that question 5 Research Scenario • To promote academic success, a university would like to implement a new “foundations” course that is designed to improve academic skills. • It is known that the mean GPA for the school is: μ = 2.9 with a standard deviation of: σ = .60 . A sample of n=200 incoming freshman is selected to participate in the new course. 6
Background image of page 2
10/4/2010 3 Research Question • The research question is : – “Is the mean GPA for students who attend the new course significantly higher than that of the mean GPA of the general population at the school?” • This is a comparative research question that examines the difference between a sample mean and a known population mean 7 Graphical Representation = 2.9 = ? Population without new course Population with new course Tx: Course Attendance 8 Two Possible Outcomes • If the “treatment” students have a similar or worse GPA than the population we would deem the course ineffective • If the “treatment” students have a mean GPA that is a lot higher than the mean GPA for the school population, we would deem the course effective – The question is, how big of a difference do we need to observe to make this judgment? 9
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
10/4/2010 4 Significance Testing Steps • All significance tests utilize a four-step procedure: 1. State hypotheses 2. State the criterion used to evaluate the hypotheses 3. (Collect data and) Compute sample statistic 4. Evaluate the hypotheses from step #1 10 Significance Testing Steps 1. State hypotheses 2. State the criterion used to evaluate the hypotheses 3. Compute sample statistic 4. Evaluate the hypotheses from step #1 11 Step 1: State Hypotheses
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/17/2011 for the course PYSC 227 taught by Professor Fairchild during the Spring '10 term at South Carolina.

Page1 / 16

Lecture 11_hypothesis testing - 10/4/2010 Hypothesis...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online