Exam 3 Biostats

Identify the following types of data as univariate or bivariate. 

1. A demographer records the ages of residents in a village. 

univariate

Identify the following types of data as univariate or bivariate. 

1. A researcher wants to examine the relationship between systolic blood pressure and age. 

bivariate

Identify the following types of data as univariate or bivariate. 

1. An economic study wants to look at total money spent on advertising and total revenue.

bivariate

Positive Correlation - ______ relationship between two variables; as one variable increases, the other variable also increases 

direct

Negative Correlation - ______ (converse) relationship between two variables; as one variable increases, the other variable decreases

indirect

Pearson coefficient of -1 (r=-1) means…

negative correlation

Pearson coefficient of positive 1 (r=1) means….

positive correlation

Pearson coefficient of 0 (r=0) means….

no relationship

Blanched formula for finding r

raw score formula for calculating r

The thinner (skinnier) the ellipse, the _____ the correlation.

higher

what is a small effect size of r

r= 0.10 - 0.29

what is a medium effect size of r

r= 0.30 - 0.49

what is a large effect size of r

r= 0.50 and higher

what is the coefficient of determination (r²)

statistic that tells you the proportion of variance (variability) that two variables in a bivariate distribution have in common

what does a coefficient of determination of 0 (r² = 0) mean

unable to predict dependent variable

what does a coefficient of determination of 0 to 1 (r² = 0 -1) mean

partially predicts DV

what does a coefficient of determination of 1 (r² = 1) mean

perfectly predicts DV

what does the correlation coefficient (r) tell you

reliability

• how consistently devices measure what they are intended to measure

what does the correlation coefficient (r) NOT tell you

cannot tell you cause and effect

r can only be used in ____ relationships

linear

what is linear regression used for

uses linear relationship btwn 2 variables to make predictions

What method do you use to find line of best fit

least squares method (regression equation)

equation for least squares method

for positive correlations, b is _____

for negative correlations, b is ____

positive= b is positive

negative = b is negative

how to calculate regression coefficient b (slope)

how to calculate coefficient a (intercept)