stud
bud
Sign up
Log in
Home
Library
Explore
SAT
More
Duplicate of Practical 3 - Correlation and Regression Flashcards | StudBud
Explore
/
Duplicate of Practical 3 - Correlation and Regression
Duplicate of Practical 3 - Correlation and Regression
20 terms
·
StudBud Administration
Imported from external platform
Flashcards
20 cards
F
Practice quiz
P
Host live
L
Questions
20
Answers
1
Multiple R-squared: 0.6861 means
68.61% is the probability to survive for a given body size
68.61% of variation of survival explained by body size
2
In relation to the model
lm(longevity ~ body size + egg rate);
the order of the independent variables
does not affect the result
does affect the result
3
If the goal is to
understand survival in function of body size
, the appropriate statistical analysis should be
ANOVA
Simple regression
Correlation
Partial correlation
4
Data are reproductive effort, survival and body size. According to the goal of the study, the dependent variable is
reproductive effort
survival (longevity)
body size
5
Correlation between body size and longevity is 0.83. The regression coefficient is 1.03; which statement is correct?
67% (0.832) of variation is explained by the relationship
83% of variation is explained by the relationship.
103% of variation is explained by the relationship
6
The linear relationship between survival and reproduction is
Significant because the p-value of the intercept is 9.19e-08
Significant because R2 is high
Not significant because R2 is small
Significant because the p-value of the slope is 0.0241
7
Putting together all the information, the result of the simple regression analysis between longevity and egg rate is
We must run a partial correlation to know.
an artifact (a confounding)
is correct
8
In your opinion, why the result in simple and multiple regression is so different?
because body size and reproduction effort shouldn’t be analysed together
because body size and reproduction effort are correlated
because there is an error in the analysis
9
lm
refers to
Luis Miguel
Linear mathematics
Linear Markov
linear models
10
If the amount of variation explained is R
2
= 0.81
the correlation is 0.812 = 0.65
we cannot know
the correlation is 0.9 (0.92 =0.81)
11
If the intercept is 1 and the slope is 0.3, the expected survival of a fly with an egg rate of 2 is
0.3 days
1 day
2.6 days: 1 + 2 x 0.3 = 1.6
12
Variables con be considered
The dependent categorical and the independents continuous
Qualitative categorical
The dependent continuous and the independents categorical
Quantitative Continuous
13
Looking to the plot and ignoring the colours
No pattern
Bigger flies lay less eggs
Bigger flies lay more eggs
14
the correlation is 0.83 and 95% confidence interval is [0.54 - 0.89]. Which sentence is correct?
Correlation is not significant because the CI contains the value 0
Correlation is significant because the CI contains the value 0.83
Correlation is significant because the CI does not contain the value 0
15
for each group of body size
When egg rate increase, longevity decrease
When egg rate increase, longevity increase
No pattern
16
Multiple R-squared: 0.6861, Adjusted R-squared: 0.6725. The R
2
and R
2
adjusted have different numbers because
The number of independents variables is different
The number of dependents variables is different
A mistake in the R program
The formula to calculate the 2 statistics is different
17
The result of the simple regression analysis is
Not Significant, the p-value for the slope is low than 0.05
Not Significant, the p-value for the intercept is low than 0.05
Significant because the p-value for the intercept is low than 0.05
Significant because the p-value for the slope is low than 0.05
18
The partial correlation result is similar to
ANOVA
Multiple regression
Simple regression
Bivariate correlation
19
The result of this analysis and in relation the slope of reproduction
An increase of longevity of 0.289
An increase of longevity of 0.289 for fixed body size
A decrease of longevity of 0.289
A decrease of longevity of 0.289 for fixed body size
20
In a simple regression analysis, the result of the test on the slope and the ANOVA on the whole model give
different p-values
depend on the variable
the same p-value
