Assignments
WEEK1 - Seminar 1.2
Don’t forget watching the videos!
Statistical concepts to be discussed: Pearson correlation, R-square, simple linear
regression, regression model (or regression equation), prediction model (or regression line)
Question 1
If the dots on a scatter plot generally extend from the upper left to the bottom right of the
scatter plot but are very widely spread out, how would the researcher report the
correlation?
a. Strong and negative
b. Strong and positive
c. Weak and negative
d. Weak and positive
How closer the dots are to each other, the stronger the correlation is. If the scatter
plot goes from top left to bottom right, it is negative, if it is from bottom left to top
right, it is positive.
Question 2
If the scatter plot of two numerical variables resembles a straight line, how can the
relationship between these two variables be defined?
a. An exponential relationship
b. A linear relationship
c. A parabolic relationship
d. No relationship
This means that the correlation is 1 or -1. So, a linear relationship.
Bij een parabool (U vorm of omgekeerd) is de correlatie 0. De linkerhelft is
namelijk negatief, de rechterhelft positief, dus de volledige U is 0. Daarom
moet je nooit alleen de correlatie berekenen, maar ook kijken naar je plot.
, Question 3
To investigate the relationship between the geographic latitudes and the average
temperature in August, a researcher collect the data for 20 cities in Europe. In the
researcher’s study, which is the dependent (or response) variable?
The geographic latitudes (X) (onafhankelijke) and the average temperature (Y)
(afhankelijke).
Question 4
In the body temperature study (see lecture slides), the estimated regression line of body
temperature (in F) on age (in years) is
^
Bodytemperatue = 98.601 -0.014× age
What is the predicted value of body temperate for a 71-year-old person?
Body temperature = 98.601 – 0.014 * (71) = 97.607F
Question 5
In which situation is the Pearson correlation coefficient inappropriate and uninterpretable?
a. If two variables are linearly, but indirectly related
b. If one variable is nominal and the other is interval
c. If one variable is ratio an the other is interval
d. If two variables have a nonlinear relationship
There is no calculation for 2 variables with a nonlinear relationship.
Bijvoorbeeld: als je de variabelen van plaats zou verwisselen, verandert de lijn. De
variabelen hebben een willekeurige volgorde. Het werkt dus niet bij meer dan 2
variabelen. (bij 2 variabelen, keert de correlatie gewoon om van pos naar neg, maar
verandert r niet).
WEEK1 - Seminar 1.2
Don’t forget watching the videos!
Statistical concepts to be discussed: Pearson correlation, R-square, simple linear
regression, regression model (or regression equation), prediction model (or regression line)
Question 1
If the dots on a scatter plot generally extend from the upper left to the bottom right of the
scatter plot but are very widely spread out, how would the researcher report the
correlation?
a. Strong and negative
b. Strong and positive
c. Weak and negative
d. Weak and positive
How closer the dots are to each other, the stronger the correlation is. If the scatter
plot goes from top left to bottom right, it is negative, if it is from bottom left to top
right, it is positive.
Question 2
If the scatter plot of two numerical variables resembles a straight line, how can the
relationship between these two variables be defined?
a. An exponential relationship
b. A linear relationship
c. A parabolic relationship
d. No relationship
This means that the correlation is 1 or -1. So, a linear relationship.
Bij een parabool (U vorm of omgekeerd) is de correlatie 0. De linkerhelft is
namelijk negatief, de rechterhelft positief, dus de volledige U is 0. Daarom
moet je nooit alleen de correlatie berekenen, maar ook kijken naar je plot.
, Question 3
To investigate the relationship between the geographic latitudes and the average
temperature in August, a researcher collect the data for 20 cities in Europe. In the
researcher’s study, which is the dependent (or response) variable?
The geographic latitudes (X) (onafhankelijke) and the average temperature (Y)
(afhankelijke).
Question 4
In the body temperature study (see lecture slides), the estimated regression line of body
temperature (in F) on age (in years) is
^
Bodytemperatue = 98.601 -0.014× age
What is the predicted value of body temperate for a 71-year-old person?
Body temperature = 98.601 – 0.014 * (71) = 97.607F
Question 5
In which situation is the Pearson correlation coefficient inappropriate and uninterpretable?
a. If two variables are linearly, but indirectly related
b. If one variable is nominal and the other is interval
c. If one variable is ratio an the other is interval
d. If two variables have a nonlinear relationship
There is no calculation for 2 variables with a nonlinear relationship.
Bijvoorbeeld: als je de variabelen van plaats zou verwisselen, verandert de lijn. De
variabelen hebben een willekeurige volgorde. Het werkt dus niet bij meer dan 2
variabelen. (bij 2 variabelen, keert de correlatie gewoon om van pos naar neg, maar
verandert r niet).
