1 / 33

Chapter Eleven

Chapter Eleven. Performing the One-Sample t-Test and Testing Correlation. More Statistical Notation. Recall the formula for the estimated population standard deviation. Chapter 11 - 2. Use the z -test when is known Use the t -test when is estimated by calculating .

harsha
Télécharger la présentation

Chapter Eleven

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Chapter Eleven Performing the One-Sample t-Test and Testing Correlation

  2. More Statistical Notation Recall the formula for the estimated population standard deviation Chapter 11 - 2

  3. Use the z-test when is known Use the t-test when is estimated by calculating Using the t-Test Chapter 11 - 3

  4. Performing the One-Sample t-Test Chapter 11 - 4

  5. Setting Up the Statistical Test Set up the statistical hypotheses (H0 and Ha). These are done in precisely the same fashion as in the z-test. Select alpha Check the assumptions for a t-test Chapter 11 - 5

  6. You have one random sample of interval or ratio scores The raw score population forms a normal distribution The standard deviation of the raw score population is estimated by computing Assumptions for a t-Test Chapter 11 - 6

  7. Computational Formula for the t-Test First, compute the estimated standard error of the mean Chapter 11 - 7

  8. Computational Formula for the t-Test Then, compute the one-sample t statistic: Chapter 11 - 8

  9. The t-Distribution The t-distribution is the distribution of all possible values of t computed for random sample means selected from the raw score population described by H0 Chapter 11 - 9

  10. Comparison of Two t-distributions Based on Different Sample Ns Chapter 11 - 10

  11. The quantity N - 1 is called the degrees of freedom We obtain the appropriate value of tcritfrom the t-tables using both the appropriate a and df Degrees of Freedom Chapter 11 - 11

  12. Two-Tailed t-Distribution Chapter 11 - 12

  13. Estimating the Population Mean by Computing a Confidence Interval Chapter 11 - 13

  14. Estimating m There are two ways to estimate the population mean m Point estimation in which we describe a point on the variable at which the m is expected to fall Interval estimation in which we specify an interval (or range of values) within which we expect the m to fall Chapter 11 - 14

  15. Confidence Intervals We perform interval estimation by creating a confidence interval The confidence interval for a single m describes an interval containing values of m Chapter 11 - 15

  16. Significance Tests for Correlation Coefficients Chapter 11 - 16

  17. The Pearson Correlation Coefficient The Pearson correlation coefficient (r) is used to describe the relationship in a sample Ultimately we want to describe the relationship in the population For any correlation coefficient you compute, you must decide if it is significant Chapter 11 - 17

  18. The Pearson Correlation Coefficient The symbol for the Person correlation coefficient in the population is r Chapter 11 - 18

  19. Hypotheses Two-tailed test H0: r = 0 Ha: r ≠ 0 One-tailed test Predicting positive − Predicting negative correlation correlation H0: r ≤ 0 H0: r ≥ 0 Ha: r > 0 Ha: r< 0 Chapter 11 - 19

  20. Scatterplot of a Population for Which r = 0 Chapter 11 - 20

  21. Assumptions for the Pearson r There is a random sample of X and Y pairs and each variable is an interval or ratio variable. The X scores and Y the scores each represent a normal distribution. Further, they represent a bivariate normal distribution. The null hypothesis is there is zero correlation in the population. Chapter 11 - 21

  22. Sampling Distribution The sampling distribution of ris a frequency distribution showing all possible values of r that can occur when samples of size N are drawn from a population where r is zero. Chapter 11 - 22

  23. Degrees of Freedom The degrees of freedom for the significance test of a Pearson correlation coefficient are N - 2 N is the number of pairs of scores Chapter 11 - 23

  24. Interpreting the Results • If the Pearson r is significant, compute • the regression equation and • the proportion of variance accounted for (r2) • It is the r2 (not the test of significance) that indicates the importance of the relationship Chapter 11 - 24

  25. Testing the Spearman rs Testing the Spearman rs requires a random sample of pairs of ranked (ordinal) scores Use the critical values of the Spearman rank-order correlation coefficient for either a one-tailed or a two-tailed test The critical value is obtained using N, the number of pairs of scores in the sample Chapter 11 - 25

  26. Maximizing the Power of a Statistical Test Chapter 11 - 26

  27. Maximizing the Power of the t-Test Larger differences produced by changing the independent variable increase power Smaller variability in the raw scores increases power A larger N increases power Chapter 11 - 27

  28. Maximizing the Power of aCorrelation Coefficient Avoiding a restricted range increases power Minimizing the variability of the Y scores at each X increases power Increasing N increases power Chapter 11 - 28

  29. Example 1 Use the following data set and conduct a two-tailed t-test to determine if m = 12 Chapter 11 - 29

  30. Example 1 H0: m = 12; Ha: m ≠ 12 Choose a = 0.05 Reject H0 if tobt > +2.110 or if tobt < -2.110 Chapter 11 - 30

  31. Example 2 For the following data set, determine if the Pearson correlation coefficient is significant. Chapter 11 - 31

  32. Example 2 From chapter 7, we know that r = -0.88 Using a = 0.05 and a two-tailed test, rcrit = 0.811. Therefore, we will reject H0 if robt > 0.811 or if robt < -0.811 Since robt = -0.88, we reject H0 We conclude this correlation coefficient is significantly different from 0 Chapter 11 - 32

  33. Key Terms • point estimation • sampling distribution of r • sampling distribution of rs • t-distribution confidence interval for a single m estimated standard error of the mean interval estimation margin of error one-sample t-test Chapter 11 - 33

More Related