SW 594 B

• - Independent variables
• - Influence (influences another)
• - Cause / Predictor
• - Can be manipulated
• - Its's value does not depend on another variable - The value that is manipulated - For example: - Does "GENDER" have an influnce on depression? "Gender"= IV

• - Dependent variable
• - Outcome / Effect

• - The value depends of the cause (independent variable)
• - The variable that is measured

• - Categorical
• - Mutually Exclusive
• - Not ranked in order

• Examples:
• MEAL PREFERENCE: Breakfast, Lunch, Dinner
• RELIGIOUS PREFERENCE: 1 = Buddhist, 2 = Muslim, 3 = Christian, 4 = Jewish, 5 = Other
• 1 = male, 2 = female.

• - Categorical
• - Mutually Exclusive
• - Ranked in order

• Examples:
• RANK: 1st place, 2nd place,. last place
• LEVEL OF AGREEMENT: No, Maybe, Yes

• - Continuous
• - Scale
• - No absolute zero
• - Scale responses- NO true meaning between scores

• Examples: TIME OF DAY on a 12-hour clock -
• What is your bed time? 8-9; 9-10; 10-11; 11-12

• - Continuous
• - Scale
• - Absolute zero
• - Scale responses: "HAVE" true meaning between scores

• Examples: INCOME: money earned last year
• NUMBER of children
• GPA: grade point average

- Are you serious about attending a post crisis workshop? Yes/No

- Do you believe in the death penalty? Yes/No

- What is your favorite color? Blue/ Green/Red


Nominal

- How serious are you about attending a post crisis workshop? Extremely serious/very serious/somewhat serious/ not serious

- How satisfied are you with the MSW program at CSULB? Very satisfied, Somewhat satisfied, Not satisfied

Ordinal

On a scale from 1-10, respond to how serious you are about attending a post crisis workshop? 1=not at all; 10=extremely serious

- The death penalty is justified in certain cases? 5:Strongly agree; 4:Agree; 3: Neutral; 2:Disagree; 1: Strongly disgree


Interval

- How many clients have you had in the last six months?

- How many days would you attend a 20 day post crisis workshop if offered?

Ratio

• - Univariate Analyses
• - Descriptive Statistics (describes something about your populations)

• - Mode = Most frequent score
• - Median = Mid point (n+1/2), # line
• - Mean = Averge (add scores togther divide by x)

• - Univariate Analyses
• - Descriptive Statistics (describes something about your populations)

• - Range + Interquarrite Range (mid 50%) difference between the largest and smallest values (Take the largest score and subtracts from the smallest score)
• - Standard Diviation = Square root of s^{2 =} +/- SD
• - Variance (s²)=
• 

• -H_o
• - If significance is found reject the Null (H_o)

- H_o = pre means + post means

• -H_a-
• If significance is found you fail to reject the Alternative (H_a) (accept H_a)

- H_a = pre means ≠ means

- H_o --> r = 0

- H_a --> r ≠ 0

• -"p" value -
• -> Less than 0.05=Significance
• -> Greater than 0.05- NO Significance

- Phi, pb (Point Biserial), Cramer's V

• - Significance
• - How much possible evidence do we have aginst the null

"p" value:

• -> Less than 0.05 or equal to =Significance
• -> Greater than 0.05 or equal to- NO Significance

• - Bivariate Analyses (2 variables)
• - Includes 2 catergorical variables

- Table to display cell count (2x2; 3x2)(define rows (R) and column (C))

• - Bivariate Analyses (2 variables)
• - Includes 2 catergorical variables

- Test of ASSOCIATION (difference) between 2 catergorical variables

- Phi (Correlation) 2 + variables

- Univariate Analysis

- Bivariate Analysis

- Datad ananylses, results, findings, conclusions

- The use of surveys, scales, instruments, charts

- Bivariate Analyses

• - Catergorical IV (2 independent grps)
• - Categorical DV (mean scores (differnce))

- Test of ASSOCIATION (difference)

H_o --> Mean score (boys) = Mean score (girls)

• Independent t -test-->
• - X (pre mean) ≠ X (post mean) (independent of each other)

• Dependent t -test--> PAIRED
• - X (pre mean) WITH X (post mean) (paired together)

• ANOVA--> one IV (3 means)
• - X _boys (pre mean) ≠ X _girls ≠ X_trans

• - pb - Point Biseral Correlation
• -->1 catergorical IV; 1 continuous DV

• -ETA (NOT ON TEST)
• -->2 catergoriacl IV's; 1 continuous DV

Chi Square X²:

• H_o : Odds = 1
• H_a : Odds ≠ 1

• ANOVA: Association
• Example: Depression vs girls vs boys vs transgender

H_o: X_boys = X_girls = X_transgender

H_a: X_{boys ≠} X_{girls ≠} Xtransgender

• Independent t -test-->
• H_o: X_{girls =} X_boys
• H_a: X _girls≠ X_boys

• Dependent t -test-->
• H_o: X_{pre mean} = X_{post mean}
• H_a: X_{pre mean} ≠ X_{post mean}