Statistics Flashcards

1
Q

Statistics, population, sample

A

Statistics: collecting, analyzing, interpreting data
Population: a large group of people/animals/objects to be tested
Sample: subset/subgroup of population (the group we’re testing)

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

Random and representative sample

A

Random sample: sample obtained in a way that every member of population has an equal chance to be selected
Representative sample: exactly what it sounds like

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

Frequency, data item, frequency distribution

A

frequency: how often something occurs
Data item: piece of data
Frequency distribution: table of how many times each thing occurred

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

Grouped frequency distribution/classes
Class width

A

Grouping data points when we have a bunch that are hard to read

Class width: number from subtracting two consecutive class limits (smaller from bigger)

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

How to calculate mean?

A

Mean = sum of items/number of items

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

How to calculate mean for frequency distribution?

A

Mean = sum [(data value X frequency)]/ # data items

AKA

sum(xf)/n

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

How to calculate median when even # of data items?

A

Mean of two middle data items

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

How to find position of median?

A

(n+1)/2 where n = number of data items

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

How to find mode?

A

Most frequent data value

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

How to find midrange?

A

(Lowest value + highest value)/2

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

How is correlation coefficient measured? How does it relate to graphs?

A

-1 to 1 (strongest negative to strongest positive)

The more scrunkly the graph around LOBF, the weaker the correlation

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

How do significance levels work?

A

Decimal to percent, 0.05 = 5% means 5% chance of no correlation in population

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

What is regression line? Simple equation?

A

Line of best fit = good old y=mx+b

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

How to calculate range?

A

Highest value - lowest value

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

How to calculate standard deviation? (6 steps)

A

Find mean
Find deviation of each item
Square each deviation
Sum them ^
Divide sum by n-1
Take that square root ^

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

What is normal distribution? What is the rule?

A

Data clusters around mean, spreads or narrows w standard deviation

Rule: 68-95-99.7 = percent of data within 1-2-3 standard deviations respectively

17
Q

What is a Z-score? How do we calc?

A

How many standard deviation an item is from mean.

Z-score = (data item - mean)/SD