Intro to Stats Flashcards

(32 cards)

1
Q

What is the research process? (8 steps)

A
  1. identify the problem
  2. evaluate the literature
  3. create hypotheses
  4. research design
  5. describe population
  6. data collection
  7. data analysis
  8. report writing
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Hypothesis

A

a proposition or statement whose truth or falsity is capable of being tested

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

define models

A

a means of simplifying reality so that relationships between variables can be more clearly studied

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

define laws

A

mathematical statement that describes how something happens under specific conditions and can predict what will happen if those conditions are met

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

define theories

A

something answers why and it has been tested repeatedly and has so far always been true

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

qualitative data definition

A

why people do what they do

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

quantitative data definition

A

facts and frequencies

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

what are the special considerations for spatial data?

A
  • issues of scale
  • boundary problem
  • spatial sampling procedures
  • spatial autocorrelation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

what are common issues of scale?

A

MAUP, UGCoP, Ecological Fallacy

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

what is the most common spatial error?

A

Issues of scale

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

define modifiable areal unit problem (MAUP)

A

arises when spatial data is aggregated into different aereal unit, which can lead to variations in statistical results depending on the scale or zoning scheme used
- two issues: scale and/or zoning problem

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

what is the scale problem?

A

occurs when the size of the spatial units changes
- aggregating data at different scales can lead to different analytical results

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

what is the zoning problem?

A
  • arises when boundaries of the spatial units are modified
  • different ways of dividing the same area into zones can lead to different analytical outcomes
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

what is the Uncertain Geographic Context Problem (UGCoP)?

A

when the geographic context is used to study the relationship between environmental exposures and health outcomes is not well-defined or varies

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

what is contextual uncertainty?

A

geographic context is often assumed to be a fixed area but the relevant context for individuals can vary greatly (e.g. areas chosen for analysis may not accurately reflect where individuals interact with their environment)

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

what is temporal dynamics?

A

relevant geographic context can change over time

16
Q

what is individual variability?

A

different individuals might experience their environments differently

17
Q

what is ecological fallacy?

A

where assumptions about individuals are incorrectly made based on aggregate data

18
Q

what is aggregation bias?

A

aggregate data masks individual variations

19
Q

what can occur with aggregation bias? give an example

A
  1. loss of detail
  2. homogenization of data
    example: A study aggregates income data at the neighborhood level to analyze economic disparities. The resulting average income may not reflect the true economic diversity within the neighborhood. High-income households might skew the average, masking the presence of low-income households.
20
Q

what are incorrect inferences? give an example

A
  • drawing connections about individual behaviors or attributes based on group-level statistics leads to potentially misleading and incorrect conclusions
  • based on the high average income in a neighborhood, one might assume that every resident is wealthy, ignoring presence of low-income individuals
21
Q

what are possible solutions to ecological fallacy?

A
  • individual data collection
  • multilevel model
  • robustness check (different levels of aggregation)
22
Q

contextual uncertainty, temporal dynamics, individual variability, and ecological fallacy all fall under what spatial problem?

23
Q

what is the boundary problem?

A

the issues that arise when defining and analyzing spatial data across arbitrary borders or boundaries

24
what are edge effects?
occur when the boundaries of the study area affect the analysis of spatial data (data near the edges may be influenced by factors outside the study area
25
what is an example of edge effects?
species distributions near the boundary of a protected area might be affected by land use practices outside the boundary, skewing population estimates
26
what are artificial boundaries? give an example
- human-made lines that may not correspond to natural or social phenomena - example: socio-economic data collected by administrative units like census tracts may not align with actual community boundaries, leading to misleading conclusions about social patterns
27
what are possible solutions to the boundary problem?
- buffer zone - spatial smoothing spatial hierarchical mode
28
what is spatial autocorrelation
the correlation of a variable with itself through space. measures how much nearby or neighboring locations resemble each other
29
positive spatial autocorrelation
occurs when similar values cluster together in space - e.g. high property values clustered in affluent neighborhoods
30
negative spatial autocorrelation
occurs when dissimilar values are found near each other - e.g. industrial areas with high pollution levels next to residential areas with low pollution levels
31
what does no spatial autocorrelation mean?
when the spatial distribution of values is random, showing no discernible pattern