What is a phi coefficient?
Download as PPTX, PDF27 likes26,948 views
A Phi coefficient is a non-parametric test used to measure the strength of association between two dichotomous (binary) variables. It analyzes the variables in a 2x2 contingency table to determine if there is a non-random pattern across the four cells. The Phi coefficient ranges in value from -1 to 1, similar to a correlation coefficient, with values closer to 1 or -1 indicating a stronger association.
What is a phi coefficient?
- 2. A Phi coefficient is a non-parametric test of relationships that operates on two dichotomous (or dichotomized) variables. It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 3. A Phi coefficient is a non-parametric test of relationships that operates on two dichotomous (or dichotomized) variables. It intersects variables across a 2x2 matrix to estimate whether there is a non-random Dichotomous pattern across means that the the four cells in the 2x2 matrix. data can take Similar on to a only two values. parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 4. A Phi coefficient is a non-parametric test of relationships that operates on two dichotomous (or dichotomized) variables. It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Like – • Male/Female • Yes/No • Opinion/Fact • Control/Treatment
- 5. It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 6. It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. What does this mean?
- 7. It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Here is an example Data Set
- 8. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 9. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Two Dichotomous Variables
- 10. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A B C D E F G H I J K L It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 11. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 B 1 C 1 D 2 E 2 F 1 G 2 H 2 I 2 J 1 K 1 L 2 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 12. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 13. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Male
- 14. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Male
- 15. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Female
- 16. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Female
- 17. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Single
- 18. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Single
- 19. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Married
- 20. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1. Married
- 21. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 22. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 23. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married Single
- 24. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married Single
- 25. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married Single
- 26. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married Single
- 27. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single
- 28. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single
- 29. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 1
- 30. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 1 2
- 31. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 1 2 3
- 32. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 1 2 3 4
- 33. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 1 2 3 4 5
- 34. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 1 2 3 4 5
- 35. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 5
- 36. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 5
- 37. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 5 1
- 38. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 5 1 2
- 39. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 5 1 2 3
- 40. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 5 1 2 3 4
- 41. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 Single 5 1 2 3 4
- 42. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 4 Single 5
- 43. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 4 Single 5
- 44. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 4 Single 5
- 45. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 4 Single 5 1
- 46. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 4 Single 5 1 2
- 47. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 4 Single 5 1 2
- 48. Subjects Gender 1= Male 2= Female Marital Status 1 = Single 2 = Married A 1 2 B 1 1 C 1 1 D 2 2 E 2 2 F 1 1 G 2 2 H 2 1 I 2 2 J 1 1 K 1 1 L 2 1 It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 4 Single 5 2
- 49. It intersects variables across a 2x2 matrix to estimate whether there is a non-random pattern across the four cells in the 2x2 matrix. Similar to a parametric correlation GENDER coefficient, the possible Male Female values of a Phi coefficient range from -1 to 0 to +1. MARITAL STATUS Married 1 4 Single 5 2
- 50. Similar to a parametric correlation coefficient, the possible values of a Phi coefficient range from -1 to 0 to +1.
- 51. A Phi coefficient of 0 would indicate that there is no systematic pattern across the 2x2 matrix. A negative Phi coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “lower’ coded values on the other variable. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable.
- 52. A Phi coefficient of 0 would indicate that there is no systematic pattern across the 2x2 matrix. A negative Phi coefficient would indicate a systematic pattern in which “higher” coded values on one variable GENDER are associated with “lower’ coded values Male on the Female other variable. A Married 3 3 positive MARITAL STATUS phi-Single coefficient 3 would 3 indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable.
- 53. A Phi coefficient of 0 would indicate that there is no systematic pattern across the 2x2 matrix. A negative Phi coefficient would indicate a systematic pattern in which or “higher” coded values on one variable are associated with “lower’ coded values on the other variable. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable.
- 54. A Phi coefficient of 0 would indicate that there is no systematic pattern across the 2x2 matrix. A negative Phi coefficient would indicate a systematic pattern in which or “higher” coded values on one variable are associated with “lower’ coded values on the GENDER other variable. A positive phi-coefficient Male would Female indicate a systematic MARITAL pattern Married in which 5 “higher” 5 coded STATUS Single 1 1 values on one variable are associated with “higher” coded values on the other variable.
- 55. A Phi coefficient of 0 would indicate that there is no systematic pattern across the 2x2 matrix. A negative Phi coefficient would indicate a systematic pattern in which or “higher” coded values on one variable are associated with “lower’ coded values on the GENDER other variable. A positive phi-coefficient Male would Female indicate a systematic MARITAL pattern Married in which 5 “higher” 5 coded STATUS Single 1 1 values on one variable are associated with “higher” coded values on the other variable. Being male or female does not make you any more likely to be married or single
- 56. A Phi coefficient of 0 would indicate that there is no systematic pattern across the 2x2 matrix. A negative Phi coefficient would indicate a systematic pattern in which or “higher” coded values on one variable are associated with “lower’ coded values on the GENDER other variable. A positive phi-coefficient Male would Female indicate a systematic MARITAL pattern Married in which 5 “higher” 5 coded STATUS Single 1 1 values on one variable are associated with “higher” coded values on the other variable. Being male or female does not make you any more likely to be married or single
- 57. A positive Phi coefficient would indicate that most of the data are in the diagonal cells.A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable.
- 58. A positive Phi coefficient would indicate that most of the data are in the diagonal cells. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable.
- 59. A positive Phi coefficient would indicate that most of the data are in the diagonal cells. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married Single
- 60. A positive Phi coefficient would indicate that most of the data are in the diagonal cells. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married Single
- 61. A positive Phi coefficient would indicate that most of the data are in the diagonal cells. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married Single For example
- 62. A positive Phi coefficient would indicate that most of the data are in the diagonal cells. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married 4 Single 5
- 63. A positive Phi coefficient would indicate that most of the data are in the diagonal cells. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married 4 1 Single 2 5
- 64. A positive Phi coefficient would indicate that most of the data are in the diagonal cells. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married 4 1 Single 2 5
- 65. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable. GENDER Male Female MARITAL STATUS Married 4 1 Single 2 5 Phi- Coefficient +.507
- 66. In terms of how to interpret this value, here is a helpful rule of thumb: A positive Phi coefficient would indicate that most of the data are in the diagonal cells. positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married 4 1 Single 2 5 +.507 Value of r Strength of relationship -1.0 to -0.5 or 1.0 to 0.5 Strong -0.5 to -0.3 or 0.3 to 0.5 Moderate -0.3 to -0.1 or 0.1 to 0.3 Weak -0.1 to 0.1 None or very weak
- 67. In terms of how to interpret this value, here is a helpful rule of thumb: positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable. Value of r Strength of relationship -1.0 to -0.5 or 1.0 to 0.5 Strong -0.5 to -0.3 or 0.3 to 0.5 Moderate -0.3 to -0.1 or 0.1 to 0.3 Weak -0.1 to 0.1 None or very weak GENDER Male Female MARITAL STATUS Married 4 1 Single 2 5 +.507 So, the interpretation would be, that there is a strong relationship between marital status and gender with being male making it more likely you are married and being female making it more likely to be single.
- 68. In terms of how to interpret this value, here is a helpful rule of thumb: positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable. Value of r Strength of relationship -1.0 to -0.5 or 1.0 to 0.5 Strong -0.5 to -0.3 or 0.3 to 0.5 Moderate -0.3 to -0.1 or 0.1 to 0.3 Weak -0.1 to 0.1 None or very weak GENDER Male Female MARITAL STATUS Married 4 1 Single 2 5 +.507 So, the interpretation would be, that there is a strong relationship between marital status and gender with being male making it more likely you are married and being female making it more likely to be single.
- 69. In terms of how to interpret this value, here is a helpful rule of thumb: positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable. Value of r Strength of relationship -1.0 to -0.5 or 1.0 to 0.5 Strong -0.5 to -0.3 or 0.3 to 0.5 Moderate -0.3 to -0.1 or 0.1 to 0.3 Weak -0.1 to 0.1 None or very weak GENDER Male Female MARITAL STATUS Married 4 1 Single 2 5 +.507 So, the interpretation would be, that there is a strong relationship between marital status and gender with being male making it more likely you are married and being female making it more likely you are single.
- 70. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on the other variable.
- 71. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married Single
- 72. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married Single
- 73. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married 1 4 Single 5 2
- 74. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Male Female MARITAL STATUS Married 1 4 Single 5 2 Phi- Coefficient -.507
- 75. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are GENDER associated with “higher” coded values on Male the other Female variable. MARITAL STATUS Married 1 4 Single 5 2 Phi- Coefficient -.507 So, the interpretation would be, that there is a strong relationship between marital status and gender with being male making it more likely that you are single and being female making it more likely you are married.
- 76. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are GENDER associated with “higher” coded values on Male the other Female variable. MARITAL STATUS Married 1 4 Single 5 2 Phi- Coefficient -.507 So, the interpretation would be, that there is a strong relationship between marital status and gender with being male making it more likely that you are single and being female making it more likely you are married.
- 77. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are GENDER associated with “higher” coded values on Male the other Female variable. MARITAL STATUS Married 1 4 Single 5 2 Phi- Coefficient -.507 So, the interpretation would be, that there is a strong relationship between marital status and gender with being male making it more likely that you are single and being female making it more likely you are married.
- 78. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are GENDER associated with “higher” coded values on Male the other Female variable. MARITAL STATUS Married 1 4 Single 5 2 Phi- Coefficient -.507 So, the interpretation would be, that there is a strong relationship between marital status and gender with being male making it more likely that you are single and being female making it more likely you are married.
- 79. A negative Phi coefficient would indicate that most of the data are in the off-diagonal cells. A positive phi-coefficient would indicate a systematic pattern in which “higher” coded values on one variable are associated with “higher” coded values on tGhENeD oERther variable. Note: the sign (+ or -) is irrelevant. The main thing to consider is the strength of the relationship between the two variables and then look at the 2x2 matrix to determine what it means. Male Female MARITAL STATUS Married 1 4 Single 5 2 Phi- Coefficient -.507
- 80. Phi Coefficient Example • A researcher wishes to determine if a significant relationship exists between the gender of the worker and if they experience pain while performing an electronics assembly task. • One question asks “Do you experience pain while performing the assembly task? Yes No” • The second question asks “What is your gender? ___ Male ___ Female”
- 81. • A researcher wishes to determine if a significant relationship exists between the gender of the worker and if they experience pain while performing an electronics assembly task. e question asks “Do you experience pain while performing the assembly task? Yes No” • The second question asks “What is your gender? ___ Male ___ Female”
- 82. • A researcher wishes to determine if a significant relationship exists between the gender of the worker and if they experience pain while performing an electronics assembly task. e question asks “Do you experience pain while performing the assembly task? Yes No” • The second question asks “What is your gender? ___ Male ___ Female”
- 83. Two survey questions are asked of the workers: • One question asks “Do you experience pain while performing the assembly task? Yes No” • The second question asks “What is your gender? ___ Male ___ Female”
- 84. Two survey questions are asked of the workers: • “Do you experience pain while performing the assembly task? Yes No” • The second question asks “What is your gender? ___ Male ___ Female”
- 85. Two survey questions are asked of the workers: • “Do you experience pain while performing the assembly task? Yes No” • “What is your gender? ___ Female ___ Male” adsfj;lakjdfs;lakjsdf;lakdsjfa
- 86. Step 1: Null and Alternative Hypotheses • Ho: There is no relationship between the gender of the worker and if they feel pain while performing the task. • H1: There is a significant relationship between the gender of the worker and if they feel pain while performing the task.
- 87. Step 1: Null and Alternative Hypotheses • Ho: There is no relationship between the gender of the worker and if they feel pain while performing the task. • H1: There is a significant relationship between the gender of the worker and if they feel pain while performing the task.
- 88. Step 1: Null and Alternative Hypotheses • Ho: There is no relationship between the gender of the worker and if they feel pain while performing the task. • H1: There is a significant relationship between the gender of the worker and if they feel pain while performing the task.
- 89. Step 2: Determine dependent and independent variables and their formats.
- 90. Step 2: Determine dependent and independent variables and their formats.
- 91. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is dichotomous, dependent
- 92. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is dichotomous, dependent An independent variable is the variable doing the causing or influencing
- 93. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is the dependent variable
- 94. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is the dependent variable
- 95. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is the dependent variable A dependent variable is the thing being caused or influenced by the independent variable
- 96. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is the dependent variable
- 97. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is the dependent variable • Gender is a dichotomous variable
- 98. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is the dependent variable • Gender is a dichotomous variable In this study it can only take on two variables: 1 = Male 2 = Female
- 99. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is the dependent variable • Gender is a dichotomous variable • Feeling pain is a dichotomous variable
- 100. Step 2: Determine dependent and independent variables and their formats. • Gender is the independent variable • Feeling pain is the dependent variable • Gender is a dichotomous variable • Feeling pain is a dichotomous variable In this study it can only take on two variables: 1 = Feel Pain 2 = Don’t Feel Pain
- 101. Step 3: Choose test statistic
- 102. Step 3: Choose test statistic • Because we are investigating the relationship between two dichotomous variables, the appropriate test statistic is the Phi Coefficient
- 103. Step 4: Run the Test – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8)
- 104. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8)
- 105. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8)
- 106. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8)
- 107. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8)
- 108. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8)
- 109. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 4 B E No C D F Total G H
- 110. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 4 6 E No C D F Total G H
- 111. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 4 6 E No 11 D F Total G H
- 112. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 4 6 E No 11 8 F Total G H
- 113. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 4 6 E No 11 8 F Total G H
- 114. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 4 6 E No 11 8 F Total 15 H
- 115. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 4 6 E No 11 8 F Total 14 H
- 116. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 4 6 E No 11 8 F Total 14 14
- 117. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 1 12 E No 13 2 F Total 14 14
- 118. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 1 12 13 No 13 2 F Total 14 14
- 119. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 1 12 13 No 13 2 F Total 12 14
- 120. Step 4: Run the Test • The Phi Coefficient should be set up as follows: – Box A contains the number of Males that said Yes to the pain item (4) – Box B contains the number of Females that said Yes to the pain item (6) – Box C contains the number of Males that said No to the pain item (11) – Box D contains the number of Females that said No to the pain item (8) Males Females Total Yes 1 12 13 No 13 2 15 Total 12 14
- 121. Phi Coefficient Test Formula
- 122. Phi Coefficient Test Formula bc ad ( ) efgh ( )
- 123. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = .788
- 124. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = ퟏퟐ∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = .788
- 125. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗ퟏퟑ −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = .788
- 126. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(ퟏ∗2) 15∗13∗14∗14 = 154.0 195.5 = .788
- 127. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗ퟐ) 15∗13∗14∗14 = 154.0 195.5 = .788
- 128. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (풆푓푔ℎ) = 12∗13 −(1∗2) ퟏퟓ∗13∗14∗14 = 154.0 195.5 = .788
- 129. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒풇푔ℎ) = 12∗13 −(1∗2) 15∗ퟏퟑ∗14∗14 = 154.0 195.5 = .788
- 130. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗ퟏퟒ∗14 = 154.0 195.5 = .788
- 131. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 13 No c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗ퟏퟒ = 154.0 195.5 = .788
- 132. Phi Coefficient Test Formula Males Females Total Yes a = 1 b = 12 e = 15 No c = 13 d = 2 f = 13 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = ퟏퟓퟒ.ퟎ ퟏퟗퟓ.ퟓ = .788
- 133. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 1 b = 12 e = 13 No - Pain c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = -.788
- 134. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 1 b = 12 e = 13 No - Pain c = 13 d = 2 f = 15 Total g = 14 h =14 Result: there is a strong relationship between gender and feeling pain with Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = -.788 females feeling more pain than males.
- 135. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 1 b = 12 e = 13 No - Pain c = 13 d = 2 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = -.788 Remember that with the Phi-coefficient the sign (-/+) is irrelevant
- 136. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 1 b = 12 e = 13 No - Pain c = 13 d = 2 f = 15 Total g = 14 h =14 We could have switched the columns and have gotten the same value but Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = -.788 with a different sign.
- 137. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 1 b = 12 e = 13 No - Pain c = 13 d = 2 f = 15 Total g = 14 h =14 We could have switched the columns and have gotten the same value but Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = -.788 with a different sign.
- 138. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 12 b = 1 e = 13 No - Pain c = 13 d = 2 f = 15 Total g = 14 h =14 We could have switched the columns and have gotten the same value but Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = -.788 with a different sign.
- 139. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 12 b = 1 e = 13 No - Pain c = 13 d = 2 f = 15 Total g = 14 h =14 We could have switched the columns and have gotten the same value but Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = -.788 with a different sign.
- 140. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 12 b = 1 e = 13 No - Pain c = 2 d = 13 f = 15 Total g = 14 h =14 We could have switched the columns and have gotten the same value but Φ = (푏푐 −푎푑) (푒푓푔ℎ) = 12∗13 −(1∗2) 15∗13∗14∗14 = 154.0 195.5 = -.788 with a different sign.
- 141. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 12 b = 1 e = 13 No - Pain c = 2 d = 13 f = 15 Total g = 14 h =14 We could have switched the columns and have gotten the same value but Φ = (푏푐 −푎푑) (푒푓푔ℎ) = ퟏퟐ∗ퟏퟑ −(ퟏ∗ퟐ) 15∗13∗14∗14 = 154.0 195.5 = -.788 with a different sign.
- 142. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 12 b = 1 e = 13 No - Pain c = 2 d = 13 f = 15 Total g = 14 h =14 We could have switched the columns and have gotten the same value but Φ = (푏푐 −푎푑) (푒푓푔ℎ) = ퟏ∗ퟐ −(ퟏퟐ∗ퟏퟑ) 15∗13∗14∗14 = 154.0 195.5 = -.788 with a different sign.
- 143. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 12 b = 1 e = 13 No - Pain c = 2 d = 13 f = 15 Total g = 14 h =14 We could have switched the columns and have gotten the same value but Φ = (푏푐 −푎푑) (푒푓푔ℎ) = ퟏ∗ퟐ −(ퟏퟐ∗ퟏퟑ) 15∗13∗14∗14 = 154.0 195.5 = +.788 with a different sign.
- 144. Phi Coefficient Test Formula Males Females Total Yes - Pain a = 12 b = 1 e = 13 No - Pain c = 2 d = 13 f = 15 Total g = 14 h =14 Φ = (푏푐 −푎푑) (푒푓푔ℎ) = ퟏ∗ퟐ −(ퟏퟐ∗ퟏퟑ) 15∗13∗14∗14 = 154.0 195.5 = +.788 The Result is the Same: there is a strong relationship between gender and feeling pain with females feeling more pain than males.
- 145. Step 5: Conclusions
- 146. Step 5: Conclusions There is a strong relationship between gender and pain • Both males and females have pain (or no pain) at equal frequencies.
- 147. Step 5: Conclusions There is a strong relationship between gender and pain with more females reporting pain than males. • Both males and females have pain (or no pain) at equal frequencies.
- 148. Step 5: Conclusions There is a strong relationship between gender and pain with more females reporting pain than males. • Both males and females have pain (or no pain) at equal frequencies. Males Females Yes - Pain 1 12 No - Pain 13 2
- 149. Step 5: Conclusions There is a strong relationship between gender and pain with more females reporting pain than males. • Both males and females have pain (or no pain) at equal frequencies. Males Females Yes - Pain 1 12 No - Pain 13 2
- 150. Step 5: Conclusions There is a strong relationship between gender and pain with more females reporting pain than males. • Both males and females have pain (or no pain) at equal frequencies. Males Females Yes - Pain 1 12 No - Pain 13 2