Standard Deviation Flashcards

1
Q

State four scales of measurement and give ex of each

A

Nominal ordinal ratio interval

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

Discrete vs continuous

A

Discrete: measured in whole units or categories (like siblings) whereas continuous is measured along a continuum at any place beyond the decimal point (times in Olympics, etc). Continuous can be measured in fractional units.

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

____ describe characteristics in a population, whereas ____ describe(s) characteristics in a sample

A

Parameters; Statistics

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

Operational Definition

A

An Operational Definition is a description of some observable event in terms of the specific process or manner by which it was observed. DVs require an operational definition as they can often be measured in many ways.

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

Experimental requires three things

A

Manipulation; randomization; comparison/ control

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

Quasi-experimental

A

Quasi-independent variable but may lack control group

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

T/F Qualitative Variables can be continuous or discrete

A

False - they can only be discrete

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

Find the Real Range

A

1: one more than the difference between the largest and smallest number in a list of data. If smallest is 0 and highest is 75, real range is 76 (175-0 = 75, 75+1 = 76)

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

Find interval width

A

Observed range divided by number of intervals. Recommended between 5 and 20 only - no more ranges.

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

To construct frequency distribution, 3 steps

A

1 Find real range
2 Find interval width
3 Construct frequency distribution

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

Four rules for frequency distributions

A

1 Each interval is defined w upper and lower boundary
2 Equidistant
3 no interval overlaps (same score can’t occur in more than one interval
4 all values are rounded to same degree of accuracy measured in the original data

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

What is “degree of accuracy”

A

Numbers Rounded to same degree

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

Define “Open interval” or “open class”

A

Interval with no defined upper or lower boundary

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

What is recommended number of intervals that should be included in a simple frequency distribution?

A

5 to 20

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

What is cumulative frequency?

A

A summary display that distributes the SUM of the frequencies across a series of intervals - (so like ascending sum)

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

What is relative frequency?

A

Observed frequency divided by total frequency count - so (basically just a proportion from 0-1 so divide count by total - like if x shows up 2 out of 45 times, it’s relative frequency is .04)

17
Q

What is an ogive

A

Pronounced (Oh-jive)
Used to summarize cumulative percents of continuous data at the upper boundary of each interval. Always goes from 0-100. Page 53

18
Q

Frequency polygon qualities

A

Grouped data; dot-and-line graph where the dot is the midpoint of the interval , and the line connects each dot

19
Q

Name the statistical test you can use to determine if model is a good fit

A

Hosmer-Lemeshow

20
Q

Name 3 ways you can determine if the logistic regression model is a good fit

A

1) Statistical test: Hosmer-Lemeshow (h0=fit is good), but this breaks as #s get high
2) Standardized Deviance Residuals should be between -3 and 3 etc
3) ROC Curve (Receiver Operating Characteristics) Area under the curve, (AUC) graphical plot that visualizes the performance of measurement for classification problems at various threshhold settings - how much a model can distinguish between classes. (want high AUC)