Brainscape's Knowledge GenomeTM


Top Flashcards (Certified)
All Flashcards

data analysis > test 1 > Flashcards

test 1 Flashcards

(85 cards)

Start Studying
1
Q

descriptive statistics

A

organize, summarize and communicate a group of numerical observations (communicate what the data look like more clearly)

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

inferential statistics

A

use sample data to make estimates about larger populations (tell you if the data are meaningful)
-make some sort of conclusion

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

research questions usually want

A

to know something about the population

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

a sample is

A

a set of observations drawn from the population of interest (could be smaller or big set)

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

variables

A

any observation of a physical attitudinal or behavioural characteristic that can take on different values

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

operational definitions

A

specify the procedure used to measure or manipulate variables

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

discrete observations

A

can take on only whole numbers (specific values with nothing in between)

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

continuous observations

A

have a full range of values with points in between the integers (zero)

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

nominal variables

A

are used for observations that have categories or names in their value (no greater/lesser than quality)

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

ordinal variables

A

have a directional relationship between categories (are used for observations that have rankings)

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

interval variables

A

are used for observations that have #s in their value and have an arbitrary zero point (the zero does not mean there is “nothing” ex: temperature)

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

ratio variables

A

have an absolute zero (ex:money) plus allows ratio comparisons

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

independent variable (IV)

A

establishes the different conditions used for comparison (referred to as levels) this is what we manipulate and observe

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

dependent variable (DV)

A

is the outcome variable we are interested in and measure

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

confounding variable

A

any variable that changes systematically with the independent variable so that we cannot determine which variable may explain the results

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

reliability of measurement

A

if you measure the same thing multiple times you will get the same answer
(measure is consistent)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

validity of measure

A

measurements need to measure what you are intending to measure
(a bathroom scale can be incorrect but consistently incorrect, so that is reliable but not valid)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

hypothesis testing

A

process of drawing conclusions about whether our data support the hypothesis
(involves selecting a specific statistical approach that is most appropriate for that specific research strategy and design)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

experimental research involves

A

manipulating an IV and observing DV

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

correlational research involves

A

identifying if there is an association between two or more existing variables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

the discrete values or conditions of the IV are referred to as

A

levels
(needs a minimum of 2 levels)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

research process involves

A
  1. develop a hypothesis
  2. define our variables
  3. make observations of our variables
  4. hypothesis testing
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

correlation does not equal causation but correlation can measure

A

the direction of relationship and strength of relationship

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

random assignment

A

every participant in a study has an equal chance of being assigned to any of the groups, or experimental conditions in the study
(can reduce the impact of potential confounding variables)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
between groups design
participants experience one and only one level of the independent variable
26
control group
a level of the IV that does not receive the treatment of interest in a study
27
within groups designs
participants experience all levels of the independent variable
28
raw scores
a data point that has not yet been transformed or analyzed (nothing has been done with it)
29
frequency distribution
describes the pattern of a set of numbers by displaying a count or proportion for each possible value of a variable (often first step is to organize raw scores into a frequency distribution)
30
frequency distributions can reveal
patterns within the data (shape of the distribution) Can also reveal outliers (data points that stand out from the rest)
31
normal distributions follow a
unimodal, symmetrical bell curve
32
skewed distributions are
Asymmetrical frequency distributions where the tail is pulled away from the centre
33
positive skew
tail is to the right, may represent floor effects
34
negative skew
Taylor is to left, may represent ceiling effects
35
we use a histogram if
it has one scale variable (with frequencies)
36
we use a scatterplot or line graph
When there are two scale variables
37
we use a bar graph or pareto chart
when the independent variables that are nominal or ordinal and dependent variable are measured on a scale
38
scatterplots
delict the relation between two scale variables A linear relationship is shown by a straight line or a non-linear relationship is shown by a line that curves or brakes
39
best fit graphs
are based on a scatterplot and used to construct a line of best fit that represents the predicted Y score for each X value
40
bar graph
in the graph, the independent variable is nominal or ordinal, and the dependent variable is scale (height of each bar typically represents the average value of the dependent variable for each category)
41
pareto chart
A bar graph in which categories along the X axis are ordered from highest to lowest (allows, easier comparison and identification of most least common categories)
42
central tendency
The point a data is centred around can be described by measures of central tendency (mean, median, and mode)
43
mean
is the average Calculated by adding up all the individual scores in a data set and then dividing them by the total number of scores (most commonly reported measure of central tendency)
44
statistic is a number based on
A sample taken from the population
45
parameter is a number based on
The whole population
46
Means could represent a
statistic or a parameter, depending on what is used in the calculation
47
median
is the middle score of all the scores in a sample when the scores are arranged in ascending order (if there is no single middle score, the median is the mean of the two middle scores)
48
mode
most frequently occurred number found in a set of numbers unimodal distribution = one mode bimodal distribution = two modes multimodal distribution = more than two modes
49
Outliers have greater effects on
Means than on other measures of central tendency
50
The meanest, most commonly used and best for
Symmetric distributions
51
The median is best for a
Skewed distribution or one with one or more outliers
52
The mode is used in three cases
1. One particular score dominates a distribution 2. Distribution is bimodal or multimodal 3. data are nominal
53
Variability describes and measures with
The spread of the distribution 1. Range 2. Variance 3. Standard deviation
54
55
range
Gives the distance between the lowest and highest scores
56
variance (SD^2)
measures the amount of variability using all of the data (not just the end points)
57
variance, the average square deviation from the mean
deviation = how far away a data point is from the mean square = times the number by itself average = find the mean of the squared deviations
58
with variance a small number indicates
A small amount of spread or deviation around the mean
59
with variance a larger number indicates
A great deal of spread or deviation around the mean
60
The goal of sampling is
To obtain a sample that is representative of the population (a sample that is not representative of the population can drastically affect the results)
61
There are two main approaches to sampling
Random and convenience
62
Random sampling
Select a random sample from the population, every member has an equal chance of selection (a tool is usually used to randomly select individuals) (can still lead to over/under representation of sub groups)
63
64
convenience sampling
Recruit participants from the accessible population (the individuals who are readily available or easier to access)
65
generalizability
refers to the researcher’s ability to apply the findings from one sample or in one context to another sample or context
66
Random assignment
uses similar procedures to random sampling, but applied to enrolled participants to determine which study group they belong to
67
Random sampling versus random assignment
Random sampling is the process of picking who will be included in the study (requires knowing the entire list of eligible participants, and everyone has an equal chance of being included) Random assignment is the process of deciding which group individuals will be in (happened after sampling has occurred)
68
Confirmation bias
tendency to accept confirming and downplay contrary evidence
69
illusory correlation
seeing patterns/correlation where there is none
70
Probability
numerical measure of the likelihood that an event will occur (use probability to estimate the likelihood that what is observed in the sample, reflects the population) probability values range from zero to one
71
expected relative-frequency probability
the likelihood of occurrence based on the outcome of many, many trials expected = what we anticipate (but could end differently) relative = likelihood is related to the overall number trials
72
73
statistical probability needs
trials to be independent
74
null hypothesis
there is no difference between groups/conditions (is a statement of “no effect” or “no difference”, basically saying that the results could be explained by chance)
75
research (alternative) hypothesis
there is a difference between groups/conditions
76
type 1 error
we reject the no hypothesis, but it is true (a false positive) Meaning we found something when really there was nothing
77
type 2 error
we failed to reject the no hypothesis, but it is false (a false negative) Meaning there was something there and we missed it
78
in relation to the normal curve, sample size
is important As the sample size increases the distribution more and more closely resembles a normal curve as the size of the sample approaches, the size of the population, the shape of the distribution tends to be normally distributed
79
Normal curves, permit comparisons
between a single score and the entire distribution (Scores must be standardized in order to perform this comparison)
80
standardization
Is a way to create meaningful comparisons by converting different scales to common or standardized scale
81
z score
The number of standard deviations a particular score is from the mean
82
The standardized Z distribution allows us to
1. transform scores into standardized Z scores 2. Transform Z scores back into raw scores 3. Make comparisons between Z score (even when different scales are used) 4. Transform Z scores into percentiles
83
Central limit theorem
A distribution of sample means is a more normal distribution than a distribution of scores, even when the population distribution is not normal
84
the standard error
Standard deviation of the population divided by the square root of the sample size
85
statistical assumption
characteristic about a population that we are sampling that are necessary for accurate inferences

data analysis (4 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions