Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
PDAM #6
| Question | Answer |
|---|---|
| What is Factorial ANOVA (2) | 1, it involves two or more independent variables 2, it is good to see if whenever one independent variable depend on anothe independent variable INTERACTION EFFECT |
| What are assumptions for Factorial ANOVA (2) | 1, independent measures 2, independent & normally distributed error/ residual (again robust for homogeneity) |
| In calculation of Factorial ANOVA what is different (2) | 1, SSm is splitted into multiple categories for each group and group interaction 2, that leds to multiple F-test and ost-hoc outputs |
| What is Covariance (2) | 1, Cov(x,y) = ∑(x-x̄)(y-ȳ) / n-1 2, shows how scores on two variables differ from their means, on average |
| What is standartized covariance | Correlation coefficient r= Cov(x,y,) / Sx*Sy |
| What is "phylosifically" our goal when comparing F models | if F models are more reliable methods that just mean |
| What is R² (3) | 1, shared variance 2, coefficient of determination 3, Correlation squared 2 |
| What are 3 methods to calculated correlation if there is no normality | 1, Bootstrap CI 2,Spearman r 3,Kendall´s tau |
| How does Kendall´s tau works (3) | 1, check concordant and discordant pairs 2, how often higher (or lower) x correspond to higher (or lower) y 3, values from -1=perfect negative 0= no effect 1= higher possible effect |
| How does Spearman works (4) | 1, rank x and y 2, check how different the rank positions are 3, values -1 to 1 where 0= no relation 4, sensitive to outliers and errors |
| What is idea between partial correlation (2) | 1, there may be another variables affecting the relationship investigated 2, with partial correlation the correlation is adjusted for that effect |
| What is standartized beta in simple regression | it is the same as r (unsquared explanatory level) >> β = r |
| What is important to check before using model for validity & generalizability (2) | 1, are the 4 assumption for linear regression met 2, would change excluding certain cases result in different regression coefficient |
| What 3 types of methods of including multiple predictors in regression are there | 1, Enter / forced entry 2, Hierarchial / blockwise 3, Stepwise methods |
| What is 1, Enter / forces entry method 2, Hierarchial / blockwise method | 1, Enter / forces entry method >>> all predictors are entered simultaneously 2, Hierarchial / blockwise method >>> researcher decides the order in which variables are entered into the model |
| Which 3 stepwise methods of including multiple predictors in regression are there | 1, Forward 2, Stepwise 3,Backward |
| How do following stepwise methods work 1, Forward 2, Stepwise 3,Backward | 1,Forward >adding predictors one by one starting with the one with strongest significance 2,Stepwise >adding the best predictor and add another if it improve the model 3,Backward >starting with all predictors and one by one exclude the weakest |
| What happens if we violate assumptions of regression model | we decrease confidence of the validity and the generalizability |
Created by:
semester1.IBWL