1. Team Bivariate Chris Bulock Chris Bulock Michael Mackavoy Michael Mackavoy Jennifer Masunaga Jennifer Masunaga Ann Pan Ann Pan Joe Pozdol Joe Pozdol

2. Independent vs. Dependent Independent: The variable manipulated or presumed to affect a dependent variable. Independent: The variable manipulated or presumed to affect a dependent variable. -Alternatively known as a predictor or experimental variable. Dependent: The variable that changes in response to the independent variable. Dependent: The variable that changes in response to the independent variable. –Also known as outcome or subject variable.

3. Example Hypothesis: The more library instruction a college student receives, the more he or she will use the library. Hypothesis: The more library instruction a college student receives, the more he or she will use the library. –Independent Variable: Quantity of Instruction –Dependent Variable: Usage of the library

4. Hypothesis Testing Null Hypothesis (Ho): A hypothesis set up to be nullified or refuted in order to support an alternative hypothesis. Null Hypothesis (Ho): A hypothesis set up to be nullified or refuted in order to support an alternative hypothesis. Alternative Hypothesis (HA or H1): The hypothesis supported if the null is rejected Alternative Hypothesis (HA or H1): The hypothesis supported if the null is rejected Alpha Level (α) and P-Values Alpha Level (α) and P-Values

5. Hypothesis: The more library instruction a college student receives, the more he or she will use the library. What is the Null Hypothesis? What is the Null Hypothesis? What is the Alternative Hypothesis? What is the Alternative Hypothesis? If p is smaller than the α level, then the data is said to be “statistically significant.” If p is smaller than the α level, then the data is said to be “statistically significant.”

6. Kurtosis, Skewness (and other weird sounding words) Kurtosis refers to the peakedness or flatness of a frequency distribution. Kurtosis refers to the peakedness or flatness of a frequency distribution.

7. Skewness Skewness describes data as symmetrical or asymmetrical about a central point. Skewness describes data as symmetrical or asymmetrical about a central point.

8. Linear Regression Analysis technique which predicts one variable from another, with the regression line being the best fit straight line drawn through paired points Analysis technique which predicts one variable from another, with the regression line being the best fit straight line drawn through paired points Independent (X-axis) and dependent (Y-axis) variables Independent (X-axis) and dependent (Y-axis) variables Slope may be negative, positive, or 0 Slope may be negative, positive, or 0

9. Samples of Scatter Diagrams and Variable Relationships:

10. Correlation How strongly one variable predicts another How strongly one variable predicts another Numerous methods for calculation of correlation coefficient Numerous methods for calculation of correlation coefficient Relationship can be direct or inverse Relationship can be direct or inverse Correlation coefficient holds a value of Correlation coefficient holds a value of r = -1.00 to r = +1.00 r = -1.00 to r = +1.00

11. Measurement of Correlation Coefficients Parametric (used in interval/ratio data measurement) Parametric (used in interval/ratio data measurement) Nonparametric (for ordinal or nominal data measurement) Nonparametric (for ordinal or nominal data measurement) Usage of parametric tests requires satisfaction of certain conditions Usage of parametric tests requires satisfaction of certain conditions

12. Pearson Correlation Parametric method for calculation of coefficient of correlation (requires interval or ratio data) Parametric method for calculation of coefficient of correlation (requires interval or ratio data) r= n∑XY-∑X∑Y_________ r= n∑XY-∑X∑Y_________ √{[n∑X 2 – (∑X) 2 ] [n∑Y 2 – (∑Y) 2 ]} √{[n∑X 2 – (∑X) 2 ] [n∑Y 2 – (∑Y) 2 ]} From r can calculate r 2, which is the coefficient of determination, in order to determine proportion of variation in the dependent variable explained by variation in the independent variable

13. Pearson Correlation Important to remember Pearson coefficient(r) or Pearson coefficient of determination (r 2 ) does not indicate causation. Instead, provides statistical evidence for a relationship between the variables. Important to remember Pearson coefficient(r) or Pearson coefficient of determination (r 2 ) does not indicate causation. Instead, provides statistical evidence for a relationship between the variables.

14. Nonparametric methods Used for data expressed in ordinal or nominal scale measurements Used for data expressed in ordinal or nominal scale measurements Spearman rank order correlation coefficient, r s (uses ordinal scale data and assumes n ranked pairs) Spearman rank order correlation coefficient, r s (uses ordinal scale data and assumes n ranked pairs) r s tells the strength of the relationship between two variables that are measured on ordinal scales r s tells the strength of the relationship between two variables that are measured on ordinal scales

15. Chi-squared (X^2) Test Nonparametric test (or parametric if normal distribution) Used for 2 nominal or ordinal variables (or continuous) Used for small samples, but minimum size required Tests if relationship between 2 variables Column percents show nature of relationship

16. Research question Does gender influence library type preference? Gender: male or female Library type: academic, corporate, public Independent variable? Dependent variable? Null hypothesis? Alternative hypothesis?

17. Collect data and construct table Poll class Make contingency table Calculate row and column marginals Calculate expected frequencies

18. Calculate X^2 Check that expected frequencies are >5 (Modify if necessary to illustrate) X^2 = Σ (O-E)^2 / E

19. Determine degrees of freedom For X^2, degrees of freedom = (#rows - 1) (#columns - 1)

20. Are variables related? Compare calculated X^2 to critical value in table 0.100.050.0250.010.005 12.7063.8415.0246.6357.879 24.6055.9917.3789.21010.597 36.2517.8159.34811.34512.838 47.7799.48811.14313.27714.860 59.23611.07012.83315.08616.750 p-value d.f.

21. “Online Workplace Training in Libraries” By Connie K Haley Focused on the preference for online training versus traditional face-to-face training Purpose of the study is to reveal the relationships between variables and preference for online or traditional face-to-face training

22. “Online Workplace Training in Libraries” Aims to reveal the relationship between preference for training and variables such as: Gender, age, education level, years of experience, training locations, training providers, and professional development policies

23. Methodology The study took pace over a twenty-day period from April 10 to April 30 of 2006. Library employees were sent online survey questionnaires The surveys were anonymous and confidential Consisted of three parts: demographic variables, Likert-scale assessment of training preferences, and open-ended questions

24. Assumptions Expectations included: Younger employees would prefer online training, while older ones would prefer face-to-face training; Highly educated employees would prefer online training, while less educated employees with fewer skills would prefer face-to-face training; Employees with more library training would prefer online training while those with less experience would prefer face-to-face training

25. Findings Preference for online training shows a correlation to training providers and training locations The preference for online training was not associated with ethnicity, gender, age, education, or library experience Training budgets and professional development policies were not related to the preference for online training correlation to training providers and training locations

26. Advantages of bivariate models Quantitative goals: Quantitative goals: –Relationships –Prediction –Causality Simplification Simplification –Core Relationship –Parsimony

27. Disadvantages of bivariate models Over-simplification Over-simplification –Many related variables –Picking the right pair False relationships False relationships –May overlook the true relationship Poor definitions Poor definitions

28. Bivariate models: when to use Simple situations Simple situations Interested in single relationship Interested in single relationship –or Get a handle on complex situation Get a handle on complex situation Initial study Initial study