Normal Distribution, Trends, Correlations and Hypotheses Flashcards

1
Q

What is normal (Gaussian) distribution?

A

show a symmetric bell shape where mean, median and mode are similar or identical

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

How does normal distribution work?

A

values closer to the mean are more frequent and further are less frequent

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

How are standard deviations and normal distribution linked?

A

2/3 values fall into SD 1 and 95% in SD 1.96

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

What are Z-scores?

A

the individual observations of normally distributed data and how likely a sample point belongs to that data set

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

What do statistical tests aim to do?

A

Compare two mutually exclusive hypotheses

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

What are the 2 types of hypotheses?

A

Null
Alternative

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

What is the null hypothesis?

A

Assumes there is no difference, no correlation, etc. Apparent differences are just due to chance. Rejected if less than 5% likely (i.e. falls outside of 95% interval)

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

What is the alternative hypothesis?

A

Assumes significant difference, significant correlation

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

What can the correlation outcomes be of testing 2 variables?

A

Positive or direct correlation (both increase together)
Negative or inverse correlation (one increases as the other decreases)
no (obvious) correlation

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

What is the numerical measure for the degree of relationship between 2 variables?

A

Correlation coefficient = r = pearson correlation

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

What is the formula for standard deviation?

A

r = Sum of (X-(X mean))(Y-(Y mean))/ (n-1)/Sx X Sy

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

What is the coefficient of determination R*2?

A

measure of the proportion of variability in one variable in comparison to the other variable (extent of predictability)

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

How can the pearson correlation be exoressed?

A

Number between -1 to +1 with 0 being no correlation

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

How can R*2 be expressed?

A

0 to +1 with +1 being predictable without error

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

What does correlation not imply?

A

Causation

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

What does regression assume?

A

that one variable is dependent on another, e.g.
values of variable Y are caused by variable X

17
Q

What does simple linear regression aim to do?

A

place a ‘line of best fit’ through a set of data points, which summarises the
relation between variables

18
Q

What is the equation for simple linear regression line?

A

Y = a + bX

19
Q

How many standard deviations is 95%?

A

1.96