Lecture 1-4 Flashcards

1
Q

What do you have be to double-check when reading values in histogram and bar graphs(clustered, stacked, etc)?

A

If the values are row, column totals, or sample totals(n)

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

What are charts that display bivariate relationships?

A

Panelled pie charts, panelled histograms, stacked/ clustered bar graphs,

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

What characteristics do descriptive data focus on?

A

Centre pf data-main
Spread of data-average
Shape of data-ratio level variables only

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

What characteristics do descriptive data focus on?

A

Centre pf data-median
Spread of data- mean average
Shape of data-ratio level variables only

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

What does descriptive stats depend on?

A

Level of measurement for variables

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

Descriptive stats- define and describe the difference between mode, median and mean

A

Mode: most common.
Median: the middle of the data. “50th percentile”
Mean: average of data.

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

Which level of measurement is used for which description, and why?

A

4 leavels of measurement from least to most accurate:
Dictonomous: Mode
Nominal: Mode
Ordinal: Mode, Median
Ratio: Mode, Median, Mean
Ordinal variables: can’t do Mean because can’t apply mathmatical formula
Ratio: can do Mean beacuse can do math formula: total of values/ total of sample

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

What does cell frequency mean?

A

“Hard counts” of a cell

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

What does IAP mean?

A

Not applicable

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

In frequency percentage, What is the difference between percent vs. valid percent vs. culumulative?

A

Valid percent excludes missing data.

Culumulative percent: culumulating previous valid percent and helps to find Median of data

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

What is the equation for mean? What does each of the symbol mean?

A

Mean= Sigma X/ n

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

How to find median in ordinal variables?

A

By stacking values in hierachy. culumulative percent. Cannot locate the exact value, but only rough

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

What does measures of variation tell us about data? How is it different from central tendencies?

A

Measures of variation tell us - how spread out the data is. It is important because

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

What is a range?

A

Range: difference b/w max and min

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

What is the Inter-Quartile Range and why is it important?

A

-Distance between the 25th and 75th percentile, excluding the top and bottom 25 percentile
-Important because it is an effective way to avoid calculating “outliers” if there are a lot present

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

What is the level of measurement data that range has the best use for?

A

Ratio level variables. Sometimes also ordinal if it has a large range.

17
Q

What is a boxplot?

A

In SPSS, a visual graph that displays the RANGE- median, minimum, maximum, IQR, and flags extreme values

18
Q

What is Standard Variation and why is it important?

A
  • Standard Variation(SD) is a mathmatical formula calculating how spread out the data is.
  • SD relies on histogram graph curve to show how spread out the data is
  • SD is ONLY calculated for ratio level data.
  • SD is compared in relation with the Mean, which has a value of 0
  • SD values include +/-1,2,3
19
Q

What you must do when crafting a histogram?

A

Add the overlaying CURVE

20
Q

What is the equation for sample SD?

A

S = √∑ (X - M) 2 / n - 1

21
Q

What does Sigma mean?

A

culumative or sum of something

22
Q

What is a Normal Distribution on histogram and why is it important? What are the important characteristics of ND?

A
  • A set of Data that has a symmetrical curve on a histogram
  • Mean, median and mode should be roughly the same
  • “unimodal”- one value of mode
  • A lot of types of statstics need the Normal Distribution in order to be used.
23
Q

What are the Standard Deviations in a normal distribution?

A
  • 68% with +-1 SDs
  • 95% within +-2 SDs
  • 99% within +-3 SDs
24
Q

How do you interpret and explain SD

A

i.e. 50% fall between +-1 SD AWAY from the mean

25
Q

What is a Z Score and what is the mathmatical formula calculation

A

Standard Deviation expressed in Units of whole number values
Value indicates how Far away from the Mean a particular “case” is
basically Positive/Negative Z score indicate if case is above or below Mean
Z =(Case Value - Mean)/ Standard Deviation Value

26
Q

Skewed Distrbution or “SKEW”

WHy does it happen?

A
  • Data set has too many positive or negative Outliers “skew” the distribution
  • Positive or negative outliers mean outliers that either have positive or negative Standard Deviation Value
27
Q

What is a Kurtosis? How is it different from SKEW?

What are the descriptive termsof Kurtosis?

A

Kurtosis shows on the Y axis of the histogram. Skew shows on the X axis.
In another words, How “Long/peaky or flat/plateaued” the shape is
-Long/peaky: Leptokurtic
-Flattened/Plataeued: Platylkurtic

-

28
Q

How are Standard Deviation and Z Scores different?

A

Essentially
Std. Dev measures the deviation Score of the WHOLE sample or population
Z score measures the deviation Score of a SPECIFIC data (like an individual)

Standard Deviation is a measurement that describes the Overall Shape of the Dataset. (fat, skinny, skewed, kurtosis), as opposed to a Specific data value.

Z score is a Unit of Measurement like the metric system. It is used to show a Specific Data Value’s standard deviation on the distribution curve.