Assign #4 - Quant by Cat Flashcards
(27 cards)
3 things you can compare between a categorical and quantitative variable
- central tendencies (means or medians),
- dispersions (standard deviations or
interquartile ranges) - shapes (histograms or boxplots)
for the distributions of Y by each value of X.
provides an indication of the
strength of the association between a categorical X and quantitative Y
R2 in a regression
the test of significance for the
comparison of two or more means.
The oneway Analysis of Variance (or oneway ANOVA)
What are the hypotheses for the Oneway ANOVA test of significance?
Ho: the population means are the same
Ha: at least two of the means are different
or, not all of the means are the same
Shorthand notation for hypotheses for Oneway ANOVA
Ho: μ1 = μ2 = μ3 = …
Ha: not all of μ1, μ2, μ3 are the same
For Oneway ANOVA, which scenarios satisfy Ha (2)
- one mean differs from the other two
- all three means differ from one another
What does the Oneway ANOVA mathematically look at to estimate variability (2)
- between-group variation
2. within-group variation
the variability of the group means (how spread out the group means are)
between-group variation
the variability of the group observations about their separate means (how spread out the scores in the groups are, on average)
within-group variation
What is the test statistic for the oneway ANOVA
F statistic
F = between-group variation / within-group variation
What does more between-group variation mean
more evidence against the null
hypothesis.
What does less within-group variation mean?
more evidence against the null
hypothesis.
When Ho is true, what happens to F
F is small
What does a small F mean?
little between-group variation and/or lots of within-group variation).
When Ho is false, what happens to F
F is large
What does a large F mean
lots of between-group variation and/or little within-group variation
What is the relationship between F value and p-value
Inversely proportionate
Data assumptions for the oneway ANOVA (2)
- The population distributions on
the quantitative variable for the groups are roughly normal. - The standard deviations of the
population distributions for the groups are roughly equal.
Guiding rule for Oneway ANOVA sample size
The sample size for each group is large (i.e., >= 50).
Guiding rule for the Oneway ANOVA standard deviations
The largest standard deviation is no larger than twice the smallest one.
Equation for multiple regression lines
Y = b1X1 + b2X2 + a
In Y = b1X1 + b2X2 + a, b1 and b2 are
partial regression coefficients.
b1 represents the change in Y for a unit change in X1, holding X2 constant.
b2 represents the change in Y for a unit change in X2, holding X1 constant.
Standardized versions of b1 and b2
beta1 and beta2
the change in Y in standard
deviations for a one standard deviation change in X1, holding X2 constant.
beta1