Quiz 5 Study Guide
Quiz 5 Study Guide PSY 302
Popular in Statistical Meth Psych
Popular in Psychlogy
This 4 page Study Guide was uploaded by Mara Anderson on Monday June 1, 2015. The Study Guide belongs to PSY 302 at University of Oregon taught by Robbie Ross in Spring 2015. Since its upload, it has received 111 views. For similar materials see Statistical Meth Psych in Psychlogy at University of Oregon.
Reviews for Quiz 5 Study Guide
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 06/01/15
Quiz 5 Study Guide PSY302 Spring 2015 What is correlation conceptually and mathematically What type of variables do we need for Pearson s r Correlation tests describe a relationship between two measured variables They provide direction and strength of the relationship Correlation asses the extent to which two variables vary together relative to how much each variable varies on its own SP shared vairabilty r 1SSxSSy independentvariability What is the symbol for correlation in the population In a sample Samples r Populations p How are linear regression and correlation related to one another Correlations describe a relationship between two measured variables Regressions predict the score of one variable Y using another variable X Regressions are a practical application of correlations and are used to predict future scores What is a sum of cross products What is this conceptually How does it relate to correlation SP 2XMxYMY SP deviations of scores from their means multiplied by deviations of other scores from their means and summed SP can be positive or negative because it involves multiplication and not squaring SP is the shared variability When would the sum of cross products be positive When would it be negative SP is positive when both XMXXYMY are negative or both are positive SP is negative when either XMX or YMY is negative while the other is positive What numbers form the bounds for correlation At what value is there no relationship between two values At what values is there a perfect relationship r l 1 1 perfect positive relationship 1 perfect negative relationship 0 no relationship What is a positive and a negative correlation How many If are there for testing the significance of a correlation What family of distributions do you use to test a correlation A positive correlation indicates that the relationship between the two variables is positive and vise versa for negative correlations dfn2 Use a tdistribution to test correlation What is a weak versus strong correlation conceptually and numerically Why does a scatterplot tell you a lot about the size and strength of a correlation Strong close to l or 1 Weak close to 0 Scatter plot tells us visually the direction and strength of the correlation 2 What is r what does it mean and is this measure part of a family of measures of what r2 coef cient of determination r2 tells us about the amount of variability in one variable that can be determinedexplained by its relationship with the other variable Why do you always have to plot your data What are some issues with correlation You need to plot your data because correlation is used only to test linear relationships You plot your data rst so that you can get a visual sense of the relationship to ensure that it is linear before performing calculations What is linear regression conceptually How does it relate to correlation Linear regressions predict the score of one variable Y using another variable X Linear regressions are the practical application of correlations and are used to predict future scores What is Yhat What do the symbols a and b mean What is the regression equa on Yhat is the predicted score a is the yintercept when x0 b is the slope of the regression line 2 Why is r important to knowing if a regression is significant r2 is the proportion of variance of one variable that can be predicted explained accounted for by another variable r2 ranges from 0 to l llOO of variance is explained What is residual What is fit of a line and lack of t Residual error amount of variability remaining in Y that is not explained by the regression equation The t of the line is how accurate the regression equation is A lack of t would indicate a low r value and a low signi cance in the variability between the variables On what distribution do you test a regression equation What are the If for a regression equation You test regression on an F distribution 0 df l n2 k nkl What is a parametric or non parametric test When would you use a non parametric test Parametric tests use data that can be treated as interval level or ratio continuous DV this is what we have seen so far and not that our IVs have typically been categorical Nonparametric tests use data that cannot be treated as intervalratio they use categorical data nominalordinal What type of variables are used in chisquare Chisquared are nonparametric tests they use categorical data Allows us to answer questions about proportions or frequencies in populations What does the chisquare formula mean conceptually and how does it accomplish this goal mathematically Chisquared formula compares observed frequency counts to the counts that are expected if the null hypothesis is true x2 2 fo fe2 f e What are f0 and fe How do you find expected frequencies for chisquare goodness of fit and independence tests f0 is the observed frequency 0 fe is the expected frequency if the null hypothesis is true fe NC Why would you use a goodness of fit test How is goodness of t similar to one way ANOVA What two hypotheses can be tested with goodness of fit tests Use goodnessof t tests if a categorical variable is distributed across cells in particular ways Similar to one way ANOVA because you have one factor with 2 or more levels 1 No preferenceequal proportions o if null is true frequencies will be evenly distributed across categories 2 No difference from comparison proportions o if null is true frequencies in one population will be the same as frequencies in another population Texas vs Oregon voters What is chisquare independence test When and how is it used How is it similar to interactions in factorial ANOVA Test for independce is used if two categorical variables are related to each other or are independent Similar to factorial ANOVA because you have 2 factors row and column each of which can have as many levels as you want How do you figure out If for different chisquare tests Goodness of t 0 dfCl of categoriescolumns 1 Independence o dfClR l columns lrowsl 0 What is the null hypotheses for chisquare independence When null is true fefo
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'