L3 Flashcards

1
Q

What is a percentile

A

A way to verbally divide data into two parts at a key milestone. The percentile assigns the unit at the edge of the dividion . P percent of the population are lesser than the p’th percentile and 100%-p are greater. 25% are lesser than the 25th percentile and 75% are larger

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

How do you calculate percentile

A

Order the data, index it and find the answer at the percentual equivalent of the percentile

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What measure of centrality is equal to the 50th percentile

A

The median

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is the percentile if the dataset is not dividable by 100

A

Somewhere between the numbers available, different softwares give different answers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is the 90/10 quotient

A

A common measure of income inequality. Ratio between 90th and 10th percentile

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is a decile

A

Division of data into ten equal parts D1 is 1-10 percentiles

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is a quartile

A

Division of data into 4 equal parts Q1 is 1-25 percentile

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is a quantile

A

A common name for all divisions of data along divisional lines such as percentiles, deciles and quartiles

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is an abbreviation of the first quartile

A

Q1

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is IQR

A

The inter quartile range is the middle 50% of values, the space between the 25th and 75th percentiles

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

How do you draw a boxplot

A

Draw a box at the IQR and two wishers to the min and max values that are not further from the edges of the box than 1.5 IQR. Draw the median as a dashed line in the box and mark values outside the whiskers using an asterisk as outliers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What does standard deviation tell us about a population

A

Only if observations tend to be close or far away from the mean

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is chebyshevs theorem

A

That the proportion of observations that lie within k standard deviations of the mean is 1-1/k^2

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is meant by the chebyshevs theorem being conservative

A

That it makes a conservative estimate meaning that it the proportion within k stdev can be higher than 1-1/k^2

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the empirical rule concerning standard deviation

A

That when distribution is normal (symmetrical and bell shaped) around 68% is within the first stdev and 95% are within the second while nearly all are within the third

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is the z score of a variable

A

A standardized variable tells how many standard deviations away from mean a variable is. You subtract mean and divide by the standard deviation so that the standard deviation of z-score is always one

17
Q

How can you define an outlier in a population

A

If it is 1.5 IQR or 3 stdev away from mean

18
Q

What is covariance

A

The direction of the linear relationship between two variables. It is the k of the linear trend in a scaterplot

19
Q

What is the correlation coeficient

A

It tells the direction and strength of the linear relationship between two variables. It is unit free and always between 1 and -1.

20
Q

What does a correlation coefficient of -1 mean

A

Perfect negative relationship. All dots are in a perfect downward-sloping row in the scatterplot. Upward-sloping if positive

21
Q

What does a correlation coefficient of 0 mean

A

No correlation, no linear relationship

22
Q

When is correlation not causation

A

When changing one of two variables that tend to move together does not alter the other variable