TOS B: Research Methods and Statistics Flashcards
(127 cards)
1
Q
Why do we need statistics?
A
For the purpose of describing and make inferences
2
Q
Gathering data
A
Exploratory data analysis
3
Q
Exploratory data analysis
A
Gathering data
4
Q
Data are evaluated against firm statistical rules
A
Confirmatory data
5
Q
Confirmatory data
A
Data are evaluated against firm statistical rules
6
Q
Used to provide a concise description of collection of quantitative observations of a sample to a population
A
Descriptive statistics
7
Q
Descriptive statistics
A
Used to provide a concise description of collection of quantitative observations of a sample to a population
8
Q
Methods used to make inferences from observations of a sample to a population
A
Inferential statistics
9
Q
Inferential statistics
A
Methods used to make inferences from observations of a sample to a population
10
Q
Act of assigning numbers or symbols to characteristics according to rules
A
Measurement
11
Q
Measurement
A
Act of assigning numbers or symbols to characteristics according to rules
12
Q
It’s a group of numbers that are used to represent real things. The way these numbers behave is similar to how the real things behave
A
Scale
13
Q
Scale
A
It’s a group of numbers that are used to represent real things. The way these numbers behave is similar to how the real things behave
14
Q
Numbered values that are measured and can be any number within a particular range
A
Continuous variable
15
Q
Decimal, fractions
A
Continuous variable
16
Q
Numbered values that can only take certain values
A
Discrete variable
17
Q
Nothing in between - no decimals or fractions
A
Discrete variable
18
Q
Whole numbers; counting numbers
A
Discrete variable
19
Q
Everything that affects the score that shouldn’t because it is not part of the test measurement
A
Error
20
Q
Error
A
All factors that can affect a score that is not related to what the test measures
21
Q
Error is always present in _____
A
Continuous scale because the number/used to characterize the trait being measured should be thought as an estimate of the real number
22
Q
M-EI-AO “Meow”
A
Properties of Scales: Magnitude, Equal Intervals, Ratio
23
Q
The property of moreness
A
Magnitude
24
Q
“This object has less of more of this quality than another”
A
Magnitude
25
Magnitude
Scale of how much of something there is compared to something else
26
The difference between two numbers on the scale always mean the same thing
Equal interval
27
"The difference between 10 celcius and 20 celcus is 10 degrees."
Equal Interval
28
Zero means nothing
Absolute Zero
29
Absolute zero
Zero means nothing
30
NOIR
Four Levels or Scales of Measurement: Nominal, Ordinal, Interval, Ratio
31
There are ___ levels/scales of measurement
4
32
Only purpose is to name objects, classify, and all things measured must be mutually exclusive (must fit in only one category) and exhaustive categories (everything must fit and nothing must be left out)
Nominal
33
Nominal
Only purpose is to name objects, classify, and all things measured must be mutually exclusive (must fit in only one category) and exhaustive categories (everything must fit and nothing must be left out)
34
Used when information is qualitative rather than quantitative
Nominal
35
No mathematical manipulations of data
Nominal
36
Rank ordering based on same properties
Ordinal
37
Ordinal
Rank ordering based on same properties
38
Has property of magnitude, no EI nor AO
Ordinal
39
Contain equal intervals between numbers
Interval
40
EI and A0
Interval
41
One cannot say that an IQ of 160 is twice as high as an IQ of 80
Interval
42
Has MEIA0
Ratio
43
All mathematical operations can meaningfully be performed because there exist
equal intervals between the numbers on the scale as well as a true or absolute zero
point
Ratio
44
Ratio
All mathematical operations can meaningfully be performed because there exist
equal intervals between the numbers on the scale as well as a true or absolute zero
point
45
Test results that are organized so we can analyze/study it
Distribution
46
Distribution
Test results that are organized so we can analyze/study it
47
Away that scores can be organized into a distribution of raw scores
Displays scores on a variable or measure to reflect how frequently each value was
obtained
Frequency Distribution
48
Frequency Distribution
Away that scores can be organized into a distribution of raw scores
Displays scores on a variable or measure to reflect how frequently each value was
obtained
49
Simple Frequency Distribution
Shows how often each individual value appears
50
Shows how often each individual value appears
Simple Frequency Distribution
51
Values are grouped into intervals, and the frequency of each group is shown.
Grouped Frequency Distribution
52
Group Frequency Distribution
Values are grouped into intervals, and the frequency of each group is shown.
53
A graphical representation of the frequency distribution of continuous numerical data, where adjacent bars touch to reflect the continuity of the data intervals.
Histogram
54
A chart that represents categorical data with rectangular bars of equal width, where the height corresponds to the frequency or value, and bars are separated to indicate distinct categories.
Bar graph
55
A line graph created by plotting points at the midpoints of each class interval (in a grouped frequency distribution) and connecting them with straight lines, often used to show the shape and trends in the data.
Frequency Polygon
56
answers, “What percent of the scores fall below a particular score (Xi)?
Percentile Rank
57
Pr = B/N x 100 = Pr of Xi
Where
Pr - Percentile rank
Xi - the score of interest
B - the number of scores below Xi
N - total number of scores
58
In a class of 20 students, Emma scored 78 on a test. The scores of all students (in ascending order) are:
55, 60, 62, 65, 66, 68, 70, 72, 74, 75, 78, 79, 80, 82, 84, 85, 87, 88, 90, 95
What is Emma’s percentile rank?
50th percentile rank
59
Instead of indicating what percentage of scores fall below a particular score, they
indicate the
particular score, below which a defined percentage of scores falls
Percentile
60
Equal to the sum of the observations divided by the number of observations
Mean
61
The most appropriate measure of central tendency for interval or ratio data when the distributions are believed to be approximately normal
Mean
62
ΣX / N
Mean
ΣX = summation of scores
N = number of observations
63
The test scores of 5 students are:
70, 75, 80, 85, 90
What is the mean (average) score?
80
64
Middle score in a distribution
Median
65
Median
Middle score in a distribution
66
Order the scores in a list by magnitude (either ascending or descending) → find the
_________
Middle number
67
if the total number of scores is an odd number, the median will the the score
EXACTLY IN THE MIDDLE
68
If even
Arithmetic mean of two middle scores
69
Appropriate for ordinal, interval, ratio data
Median
70
Useful when relatively few scores fall at the high end of the distribution or relatively
few scores fall at the low end of the distribution
Median
71
Mode
Most frequently occurring score in a distribution
72
Most frequently occurring score in a distribution
Mode
73
Two cores that occur with the highest frequency
Bimodal Distribution
74
Bimodal distribution
Two cores that occur with the highest frequency
75
76
What is variation?
Indication of how scores in a distribution are scattered or dispersed.
77
What are measures of variability?
Statistics that describe the amount of variation in a distribution.
78
What is the range?
Difference between the highest score and lowest score.
## Footnote
Range = Highest score - Lowest score (H - L)
79
How do we determine the range?
Highest score minus lowest score (H - L).
80
What are quartiles?
Dividing points between four quarters.
81
What is Q2?
The median.
82
How do we determine the interquartile range (IQR)?
Q3 minus Q1 (Q3 - Q1).
83
How do we get the semi-interquartile range?
IQR divided by 2 (IQR/2).
84
What are deciles?
Mark 10% intervals. D9 = 90%
85
How do we get the SD (Standard deviation)?
Refer to notes for the formula
86
Variance formula
Refer to notes for formula.
86
What is skewness?
Nature and extent to which symmetry is absent.
87
What does a POSITIVE SKEW indicate?
Few of the scores fall at the HIGH end of the distribution, indicate that the test was TOO DIFFICULT.
88
Other term for positive skew?
Right skewed. (Right foot)
89
What does NEGATIVE SKEWED indicate?
Few scores fall at the LOW end of the distribution. May indicate that the test was TOO EASY.
90
Other term for negatively skewed?
Left skewed. (Left foot)
91
What is kurtosis?
Steepness of a distribution in its center
92
Platykurtic
Relatively flat, lower kurtosis, rounded peak and thinner tails
93
Leptokurtic
Relatively peaked, high kurtosis, high peak and fatter tails compared to a normal distribution
94
Mesokurtic
Somewhere in the middle, normal distribution will have a kurtosis of 0
95
Normal Curve
Symmetrical binomial probability distribution, bell-shaped, smooth mathematically defined curve that is highest at its center
96
Standard Scores
Raw score that has been converted from one scale to another scale
97
Conversion of a raw score into a number indicating how many standard deviation units
the raw score is below or above the mean of distribution
Z-score
98
Z-score Mean and SD
Mean = 0; SD = 1
99
Z-score Formula
Raw score - mean / SD
100
If score > mean, the z-score is?
Positive
101
If score < mean, the z-score is?
Negative
102
Composed of a scale that ranges from 5 SD below the mean to 5 SD above the mean
T-score
103
T-score mean and SD
Mean = 50; SD = 10
104
How do we transform a Z-score into a T-score?
T = 10z + 50
105
They take on whole values from 1 to 9, which represent a range of performance that is
half of a standard deviation in width
Stanine
106
Scale divided into nine units
Stanine
107
Stanine mean and SD
Mean = 5; SD = 2
108
Interpret Stanine 1-3
Below Average
109
Interpret Stanine 4-6
Average
110
Interpret Stanine 7-9
Above Average
111
Employed on tests such as the Scholastic Aptitude Test (SAT) and the Graduate Record
Examination (GRE)
A-score
112
A-score mean ; SD
Mean = 500 ; SD = 100
113
Changes the data using a straight-line formula — like adding, subtracting, multiplying, or dividing by a constant — without changing the shape of the distribution.
Linear transformation
114
Uses more complex operations like squares, square roots, logs, or exponents — these change the shape of the data distribution.
Nonlinear transformation
115
Number that provides us with an index of the strength of the
relationship between two things
Correlation coefficient (r)
116
What is correlation?
An expression of the degree and direction of correspondence between two
things
117
If a r = +1 or —1
The relationship between the two variables is
perfect
118
What does a positive correlation imply?
Two variables SIMULTANEOUSLY increase or decrease
119
What does a negative correlation imply?
One variable increases as the other decreases and vice versa
120
If correlation is zero
Absolutely NO RELATIONSHIP exists between the two variables
121
Do correlation imply causation?
No, but there is an implication of PREDICTION
122
True dichotomous
Naturally form TWO categories
123
Example of true dichotomous categories?
Sex, true-false, correct-incorrect
124
Artificial dichotomous
These two categories are not naturally just two options — they are made that way for analysis or comparison.
125
Examples of artificial dichotomous
Pass (scores ≥ 50)
Fail (scores < 50)
Young (≤ 30)
Old (> 30)
Tall (above average)
Short (below average)
126
