Chapter 11 12 13 14 and 16 Association
- Slides: 22
Chapter 11, 12, 13, 14 and 16 Association at Nominal and Ordinal Level The Procedure in Steps
The Procedure in Steps for Nominal Variables
Step 1: Make Tables o Tables must have a title. o Cells are intersections of columns and rows. o Subtotals are called marginals. o N is reported at the intersection of row and column marginals.
Step 1: Make Tables o Columns are scores of the independent variable. n There will be as many columns as there are scores on the independent variable. o Rows are scores of the dependent variable. n There will be as many rows as there are scores on the dependent variable.
Step 1: Make Tables Title Rows Columns Row 1 cell a cell b Row Marginal 1 Row 2 cell c cell d Row Marginal 2 Column Marginal 1 Column Marginal 2 N
Example of Table o The bivariate table showing the relationship between gender (columns) and party preference (rows). Female Male Labour 8 5 13 Conservatives 4 8 12 12 13 25
Example of Table o The bivariate table showing the relationship between gender (columns) and party preference (rows). Female Male Labour 66. 7% 38. 5% Conservatives 33. 3% 61. 5% 100% (N=12) 100% (N=13)
Step 2: What is the pattern/direction of the association? o See percentages in Table. o Female voters tend to have party preference for Labour and male voters have party preference for Conservatives o This relationship does have a clear pattern o But is it also significant?
Step 3: Is the Association between the Variables Significant? o Chi Square is a test of significance based on bivariate tables. o We are looking for significant differences between the actual cell frequencies in a table (fo) and those that would be expected by random chance (fe).
Example of Computation o Use Formula 11. 2 to find fe. o Multiply column and row marginals for each cell and divide by N. n For Problem above o o (13*12)/25 (13*13)/25 (12*12)/25 (12*13)/25 = = 156/25 169/25 144/25 156/25 = = 6. 24 6. 76 5. 76 6. 24
Example of Computation o Expected frequencies: Female Male Labour 6. 24 6. 76 13 Conservatives 5. 76 6. 24 12 12 13 25
Example of Computation o Divide each of the squared values by the fe for that cell. The sum of this column is chi square fo fe fo - f e (fo - fe)2 /fe 8 6. 24 1. 76 3. 10 . 50 5 6. 76 -1. 76 3. 10 . 46 4 5. 76 -1. 76 3. 10 . 54 8 6. 24 1. 76 3. 10 . 50 25 25 0 χ2 = 2. 00
Example of Computation o See Chapter 11 of Healey (pp. 286 -289) for five-step model for Chi Square Test to find out whether variables are independent/ whether the association between the variables is significant or not o χ2 (critical) = 3. 841 o χ2 (obtained) = 2. 00 o The test statistic is not in the Critical Region. Fail to reject the H 0. o There is no significant relationship between gender and party preference
Interpreting Chi Square o The chi square test tells us only if the variables are independent or not. o Like all tests of hypothesis, chi square is sensitive to sample size. n As N increases, obtained chi square increases. n With large samples, trivial relationships may be significant. o Remember: significance is not the same thing as importance
Step 4: If an Association does Exist, how Strong is it? o It is always useful to compute column percentages for bivariate tables. o But, it is also useful to have a summary measure – a single number – to indicate the strength of the relationship. o For nominal level variables, there are the following commonly used measures of association: n Phi n Cramer’s V n Lambda
Nominal Measures: Phi o See Healey, formula 13. 1, p. 342 o Phi is used for 2 x 2 tables. o The formula for Phi:
Nominal Measures: Cramer’s V o See Healey, formula 13. 2, p. 343 o Cramer’s V is used for tables larger than 2 x 2. o Formula for Cramer’s V:
Nominal Measures: Lambda o See Healey, formula 13. 3, p. 348 o When dependent and independent variables are clear o Formula for Lambda:
Step 5: Is there still an Association, if Control Variables are Added? o See Chapter 16 in Healey o See week 10 of this course
The Procedure in Steps for Ordinal Variables Steps 1 , 2, 3, 5 are similar to those for nominal variables Only step 4 is different, because you need other measures of association
Step 4: If an Association does Exist, how Strong is it? o For ordinal level variables, there are the following commonly used measures of association: n Spearman’s Rho (if there is ranking of scores, see Healey pp. 376 -382) n Gamma (Formula 14. 1, see Healey, p. 366). Is the strength of the relationship significant? Test whether gamma is significant. See Healey, pp. 380 -381
An Ordinal Measure: Gamma o interpret the strength of gamma. o e. g. gamma is 0. 61. o This is a strong association. In addition to strength, gamma also identifies the direction of the relationship. o This is a positive relationship: e. g. as education increases, income increases. o In a negative relationship, the variables would change in the different direction. o Test whether the strength of Gamma is significant Value Strength Between 0. 0 and 0. 30 Weak Between 0. 30 and 0. 60 Moderate Greater than 0. 60 Strong
- Chapter 7 scatterplots association and correlation
- Chapter 7 scatterplots association and correlation
- National association of small and medium enterprises
- Beer and diapers association rule
- International hotel and restaurant association
- Data quality standards iso
- Integrating classification and association rule mining
- Association analysis: basic concepts and algorithms
- Scatter plot and association
- Association commissural and projection fibers
- Astdd
- Air movement and control association
- Association of lunar and planetary observers
- Society and culture association
- National association of deans and directors
- Association and causation
- Example of recall bias
- American association on health and disability
- Aircollab
- Association and causation
- Association of schools and colleges of optometry
- Manitoba prospectors and developers association
- Library and information technology association