GIST 8106 - Quiz Questions

EXCLUDES MATCHING QUESTIONS. No I do not consistently get 100% in all the quizzes.

 What is the primary focus of spatial analysis in GIS?

A	Documenting physical features
B	Understanding patterns, relationships, and actions in geographic data
C	Creating artistic maps
D	Collecting demographic data

B

What is the Modifiable Areal Unit Problem (MAUP)?

A	Difficulty in collecting data
B	Changes in results when spatial scale or aggregation units are modified
C	Inaccurate GPS readings
D	Data loss during processing

B

Which data model is best for representing continuous data like temperature or rainfall?

A	Vector
B	Raster
C	Network
D	CAD

B

Which data model is best for representing discrete data like hydrants or signs?

A	Vector
B	Raster
C	Network
D	CAD

A

What is the main advantage of vector data models?

A	Generalized location and one attribute
B	Precise location and multiple attributes
C	Simple data structure
D	Efficient for continuous surfaces

B

What is a TIN (Triangulated Irregular Network) used for?

A	Modeling discrete features
B	Representing continuous surfaces with triangles
C	Storing raster images
D	Network routing

B

Which of the following is a common application of spatial analysis in health care?    

A	Weather prediction
B	Mapping health variables and optimizing locations for clinics
C	Service Request Management
D	Network routing

B

What is the ecological fallacy?

A	Assuming relationships among aggregate data apply to all  individuals within the enumeration unit
B	Misclassification of raster data
C	Data loss during aggregation
D	Inaccurate GPS readings

A

What is a common raster file format?    

A	Shapefile
B	GeoTIFF
C	DWG
D	GeoJSON

B

What is the main challenge with boundary problems in spatial analysis?

A	Data redundancy
B	Loss of neighbor information at boundaries
C	Inaccurate attribute values
D	Data currency

B

What is the primary difference between vector and raster data models?    

A	Vector is for continuous data, raster for discrete
B	Raster stores many attributes, vector only one
C	Vector provides precise location, raster generalizes location
D	Raster is used for network analysis

C

Which concept is central to understanding spatial analysis in GIS?

A	Data storage formats
B	Map design principles
C	Modeling geographic phenomena and considering scale, boundaries, and aggregation units
D	Satellite imagery projection and resolution

C

Which spatial analysis technique is used for wildlife corridor modeling?

A	Geocoding and Network Routing
B	Least cost path analysis across weighted cost surfaces
C	Raster classification
D	Land Use Classification

B

Which statement about scale in spatial analysis aligns with the presentation?

A	Scale selection is irrelevant to analysis quality
B	Appropriate choice of data collection, representation, and analysis scale is critical
C	Larger scales eliminate MAUP concerns
D	Scale applies only to cartographic outputs, not data

B

Which aspect is not listed among the data quality considerations in the presentation?    

A	Positional and attribute accuracy
B	Logical consistency
C	Completeness and currency
D	Graphic design aesthetics

D

Which concern warns against inferring individual‑level relationships from aggregate data?    

A	Ecological fallacy
B	MAUP
C	Edge effect
D	Nonstationarity bias

A

Which analysis is raster particularly suited for in this course?

A	Topology validation
B	Suitability and multi‑criteria decision analysis
C	Parcel management
D	Linear referencing

B

Which set best matches the four traditional types of spatial analysis covered?

A	Temporal, categorical, qualitative, quantitative
B	Spatial overlay/contiguity, surface analysis, linear analysis, raster analysis
C	Geodatabase, topology, symbology, cartography
D	Classification, clustering, association, regression

B

What is the primary aim of spatial analysis in GIS?

A	Compress large datasets for storage efficiency
B	Replace statistical models with visualizations
C	Map data, explore patterns and derive meaning from geographic data to inform actions
D	Automate cartographic symbolization

C

What is one way GIS supports emergency management?

A	By automating business analytics
B	By mapping damaged infrastructure and prioritizing medical needs
C	By designing vector data models
D	By modeling slope and elevation

B

Which of the following explains why spatial statistics are useful (select all that apply)?

A	Assists in the process of making inferences to communicate characteristics of a population based on data collected from a sample
B	Assists in the process of determining whether or not sample data is inaccurate
C	Assists in the process of summarizing large data sets in order to make sense of them
D	Assists in the process of making a decision to decide whether an observed difference in a relationship between two sets of sample data is significant

A, C,D

(T/F) Numerical summaries mask the detail and sometimes are skewed by outliers

True

Which of the following is used to determine the value around which data are concentrated?

A	Measures of Dispersion
B	Bivariate Correlation
C	Measures of Central Tendency

C

What are the measures of central tendency (select all that apply)

A	Standard Deviation
B	Mean
C	Median
D	Mode

B, C, D

What are the measures of dispersion (select all that apply)

A	Range
B	Standard Deviation
C	Variance
D	Median

A, B, C

In relation to the standard normal distribution which of the following is true?

A	68% of values fall within +/- 3.00 standard deviations from the mean
B	86% of values fall within +/- 2.00 standard deviations from the mean
C	68% of values fall within +/- 1.00 standard deviations from the mean
D	99% of values fall within +/- 2.00 standard deviations from the mean

C

How can Spatial Autocorrelation be described?

A	What happens at one location depends on what is occurring to same variable at nearby locations
B	What happens at one location depends on what is occurring to other variables at nearby locations

A

How can Spatial Correlation be described?

A	What happens at one location depends on what is occurring to same variable at nearby locations
B	What happens at one location depends on what is occurring to other variables at nearby locations

B

When features that are close together are dissimilar in attributes this is termed?

A	Positive spatial autocorrelation
B	Negative spatial autocorrelation
C	Zero spatial autocorrelation
D	Skewed spatial autocorrelation

B

Which of the following are inferential statistics that make an inference in the form of a null hypothesis about a population? (Select all that apply)

A	Measures of Dispersion
B	Regression Analysis
C	Measures of Central Tendency
D	Moran's I

B, D

Which statistic is used frequently to summarize the relationship between two numeric attributes?

A	Correlation Coefficient
B	Global Moran's I
C	Measures of Dispersion
D	Measures of Central Tendency

A

Which of the following is used to summarize the nature and strength of relationships in data?

A	Measures of Central Tendency
B	Bivariate regression
C	Bivariate correlation
D	Measures of Dispersion

B

(T/F) When looking at scatter-plot, high correlations indicate a causal relationship

False

When calculating correlation coefficients, a +1 value indicates:

A	a positive relationship where increasing values of one attribute are associated with increasing values of another attribute
B	a positive relationship where increasing values of one attribute are associated with decreasing values of another attribute
C	a negative relationship where increasing values of one attribute are associated with increasing values of another attribute
D	None of the choices

A

Which of the following statistical tests was used to assist in the process of evaluating social stressors and air pollution across New York City communities?

A	Chi-Square Test
B	Pearson's Correlation Coefficient
C	Regression
D	Spearman Rank for ranked data

B

(T/F) The dependent variable represents what is being modeled, predicted, or explained 

True

(T/F) The independent variable represents what is being modeled, predicted, or explained

False

(T/F) OLS models relationship between an independent variable (Y) and an explanatory variable (X)

False

(T/F) Residuals represent the error between predicted value of Y and explanatory variable

True

Select the true statements about Ordinary least-squares (OLS) regression

A	A common statistical method used to generate predictions or to model a dependent variable in terms of its relationships to a set of explanatory variables
B	It is a generalized linear modelling technique
C	Tests for independence
D	Shows the relationship between two variables –the independent variable, x, used to predict, and dependent variable y, which is what we seek to predict

A, B, C

A properly specified OLS model has which of the following characteristics:

A	Coefficients reflecting a justifiable relationship between independent and dependent variables
B	Explanatory variables that are not redundant (values less than 7.5)
C	Normally distributed residuals indicating your model is free from bias
D	Randomly distributed over and under predictions indicating model residuals are normally distributed (the spatial autocorrelation p-value is not statistically significant)
E	Explanatory variables where all the coefficients are statistically significant

All of the above

A value associated with each independent variable in a regression equation, representing the strength and type of relationship the independent variable has to the dependent variable.

A	Jarque-Bera statistic
B	Variable Inflation Factor (VIF)
C	Coefficient
D	Adjusted R-Squared

C

(T/F) When key explanatory variables are missing from a regression model, coefficients and their associated p-values cannot be trusted.

True

(T/F) Influential outliers can pull modeled regression relationships away from their true best fit, biasing regression coefficients

True

In Regression Analysis when relationships between your dependent and explanatory variables are inconsistent across your study area, computed standard errors will be artificially inflated. This is referred to as:

A	Multicollinearity
B	Nonstationarity
C	Spatially autocorrelated residuals
D	Inconsistent variance

B

In Regression Analysis when one or more explanatory variables are redundant it is:

A	Multicollinearity
B	Spatially autocorrelated residuals
C	Inconsistent variance
D	Nonstationarity

A

In Linear Regression when there is spatial clustering of under-/over predictions, it introduces an over counting type of bias and renders the model unreliable that is referred to as:

A	Inconsistent variance
B	Nonstationarity
C	Multicollinearity
D	Spatially autocorrelated residuals

D

A statistical result of regression analysis that shows what percentage of the variation in the dependent variable is being explained by the independent variables is referred to as:

A	Adjusted R-Squared
B	Jarque-Bera statistic
C	Coefficient
D	Aikake's Information Criterion (AIC)

A

A statistical result of regression analysis that can be used to compare other models that are using the same dependent variable. The lower this number is, the better.

A	Adjusted R-Squared
B	Aikake's Information Criterion (AIC)
C	Coefficient
D	Jarque-Bera statistic

B

A test that indicates whether the residuals (the observed/known dependent variable values minus the predicted/estimated values) are normally distributed with a mean of zero.

A	Jarque-Bera statistic
B	Aikake's Information Criterion (AIC)
C	Adjusted R-Squared
D	Coefficient

A

A test to determine whether the explanatory variables in the model have a consistent relationship to the dependent variable both in geographic space and in data space.

A	Jarque-Bera statistic
B	Koenker statistic
C	Adjusted R-Squared

B

A measure of variable redundancy and can help you decide which variables can be removed from your model without jeopardizing the model.

A	Residual
B	Variable Inflation Factor (VIF)
C	Adjusted R-Squared
D	Koenker statistic

B

(T/F) In order for the Statistical Model to be unbiased and thus suitable for a GWR Statistical Analysis the results from the Moran’s I Spatial Autocorrelation Report must indicate that the sample distribution is random.

True

In the end‑to‑end GWR workflow, the first step is typically to:

A	Edit the parameters cell (paths, fields) for your dataset
B	Export a layout PDF
C	Run GWR on the raw feature class
D	Add OLS outputs to the active map

A

If your dependent variable is highly skewed, the recommended step in the workflow is to:

A	Apply a log transform (use ArcGIS Pro 'Transform' tool) and document the choice
B	Use a square‑root transformation without documentation
C	Drop the variable and choose another
D	Convert it to a categorical variable

A

In the end‑to‑end sequence, Exploratory Regression is used primarily to:

A	Create local R² maps for each variable
B	Estimate the GWR² for each variable
C	Screen variable combinations and check model diagnostics (VIF, Koenker, Jarque–Bera)
D	Create a series of scatterplots

C

After running OLS, you test for spatial clustering of residuals by:

A	Inspecting the correlation matrix
B	Running GWR directly
C	Running Global Moran's I on the OLS residual field
D	Screen variable combinations and check model diagnostics (VIF, Koenker, Jarque–Bera)

C

A significant positive Moran’s I on OLS residuals suggests that:

A	The global model fully explains spatial variation
B	There is spatial autocorrelation in residuals; consider local or spatial models (e.g., GWR)
C	The dependent variable must be replaced
D	The explanatory variables are all perfectly independent

B

Which of the following spatial interpolation techniques is a Local Deterministic method? 

A	IDW
B	Splines
C	Kriging
D	Density estimation

A

Which of the following spatial interpolation techniques is a Local Stochastic method? 

A	Splines
B	Kriging
C	IDW
D	Density estimation

B

Trend surface is a spatial interpolation technique that can be characterized by which method? 

A	Stochastic and Local Method
B	Deterministic and Local Method
C	Deterministic and Global Method
D	Stochastic and Global Method

C

Regression is a spatial interpolation technique that can be characterized by which method? 

A	Stochastic and Local Method
B	Deterministic and Local Method
C	Stochastic and Global Method
D	Deterministic and Global Method

C

Kriging is a spatial interpolation technique that can be characterized by which method? 

A	Deterministic and Local Method
B	Stochastic and Local Method
C	Stochastic and Global Method
D	Deterministic and Global Method

B

(T/F) Spatial Interpolation is the process of using points with known values to estimate values at peripheral locations

True

(T/F) The amount and distribution of sample points can influence accuracy of spatial interpolation

True

Which of the following is an inexact interpolation method that approximates points with known values using a polynomial equation?

A	Regression Model
B	IDW
C	Kriging
D	Trend Surface

D

Which of the following measures cell densities in a raster with a sample of known points?

A	Kriging
B	Density Estimation
C	Regression Model
D	Trend Surface

B

Which of the following methods is a counting method?

A	Simple Density Estimation Method
B	Kernel Density Estimation Method
C	Inexact Interpolation
D	Trend Surface

A

Which of the following methods is a local interpolation method that associates each known point with a kernel function in the form of a bivariate probability function?

A	Kernel Method
B	Simple Method
C	Trend Surface
D	Inexact Interpolation

A

Which of the following is a spatial interpolation method that provides no assessment of errors with predicted values?

A	Global Interpolation
B	Inexact Interpolation
C	Deterministic Interpolation
D	Exact Interpolation

C

Which of the following is a spatial interpolation method that predicts the same value as the known value at the control point?

A	Deterministic and Inexact Interpolation
B	Deterministic and Exact Interpolation
C	Stochastic and Exact Interpolation
D	Stochastic and Inexact Interpolation

B

Which interpolation method uses every control point available in estimating an unknown value?

A	Deterministic and Global Interpolation
B	Stochastic and Exact Interpolation
C	Deterministic and Local Interpolation
D	Stochastic and Inexact Interpolation

A

Which interpolation method predicts a different value from the known value at the control point?

A	Deterministic and Global Interpolation
B	Stochastic and Inexact Interpolation
C	Stochastic and Exact Interpolation
D	Deterministic and Local Interpolation

B

Which method enforces the condition that the unknown value of a point is influenced more by nearby points than by those farther away?

A	Local polynomial interpolation
B	Kriging
C	Density Estimation
D	IDW

D

Which method is a local interpolation method that uses a sample of points with known values and a polynomial equation to estimate the unknown value of a point?

A	Density Estimation
B	Local polynomial interpolation
C	Kriging
D	IDW

B

Which assumes that spatial variation of an attribute is neither totally stochastic nor deterministic?

A	Local polynomial interpolation
B	Kriging
C	Density Estimation
D	IDW

B

Which of the following can assess the quality of prediction with estimated prediction errors?

A	IDW
B	Density Estimation
C	Kriging
D	Local polynomial interpolation

C

Which method relates a dependent variable to a number of independent variables in a linear equation, which can then be used as an interpolator for prediction or estimation?

A	IDW
B	Local polynomial interpolation
C	Kriging
D	Regression

D

(T/F) We can expect to find different results using different interpolation methods with same data

True

(T/F) Different predicted values can occur using the same method with different parameter values

True

(T/F) Distributions are not important when modeling spatial phenomena 

False

(T/F) Some interpolation and statistical techniques assume normal distributions

True

(T/F) Mean is a measure of central tendency that provides a representation of the distribution

True

Spatial variation consists of which of the following components? (select all that apply)

A	Abnormal spatial distribution
B	Spatially correlated component representing variation of regionalized variable
C	A random error
D	A 'drift' or structure, representing a trend

B, C, D

Which method assumes absence of a drift, focuses on the spatially correlated component and uses the fitted semi-variogram directly for interpolation?

A	Universal Kriging
B	Regression
C	Empirical Bayesian Kriging
D	Ordinary Kriging

D

Which method assumes spatial variation in z values has a drift or a trend in addition to spatial correlation between sample points?

A	Ordinary Kriging
B	Empirical Bayesian Kriging
C	Regression
D	Universal Kriging

D

Which statement best distinguishes global from local interpolation methods?

A	Global models broad trends across the entire study area; local models variation within neighborhoods
B	Global uses fewer points; local uses all points
C	Global is exact; local is inexact
D	Global requires a variogram; local does not

A

A common artifact of IDW (Inverse Distance Weighting) surfaces is:

A	Systematic bias at high elevations
B	Edge tapering
C	Bulls‑eye patterns around measurement points
D	Over‑smoothing of sharp boundaries

C

Natural Neighbor interpolation selects contributing points using:

A	K‑means clusters
B	Delaunay triangulation / Voronoi neighbors
C	Randomized sampling windows
D	Fixed‑radius buffers

B

Which is typically true of Spline (radial basis function) interpolation?

A	It always predicts within the range of measured values
B	It requires a modeled variogram
C	It minimizes curvature to create a smooth surface through the points
D	It cannot be an exact interpolator

C

In kriging, the range of the (semi)variogram represents:

A	The distance beyond which spatial autocorrelation becomes negligible
B	The slope of the fitted trend surface
C	The total variance at zero distance
D	The value where measurement error is maximized

A

Which dataset is best treated as conceptual point data rather than true point data?

A	Air temperature at weather stations
B	GPS‑measured soil moisture at probe locations
C	Water quality measures at a gauging station
D	Census tract median income placed at tract centroids

D

For smooth, spatially autocorrelated environmental variables (e.g., temperature), which method is generally most appropriate when you also need an error surface?

A	IDW with high power
B	Global Polynomial only
C	Kernel Density
D	Kriging

D

Which statement correctly contrasts density estimation with interpolation?

A	Interpolation is for counts; density is for continuous measurements
B	Both estimate values at unsampled locations using exact point measurements
C	Density estimation always produces exact surfaces; interpolation is only a prediction
D	Density estimation models intensity of events per area; interpolation predicts a continuous variable's value

D

A positive Moran’s I in exploratory spatial data analysis most strongly indicates:

A	No spatial structure in the data
B	The variogram nugget is zero
C	Strong negative spatial autocorrelation
D	Nearby locations tend to have similar values

D

Which of the following best describes the purpose of Exploratory Spatial Data Analysis (ESDA)?

A	To perform statistical hypothesis testing on completed surfaces
B	To create the final interpolated surface from point data
C	To explore data, identify patterns, look for relationships and rank options before formal modeling
D	To automatically determine the best interpolation method without user input

C

Why is ESDA especially useful when working with point data intended for surface interpolation?

A	It replaces the need for cross‑validation
B	It reveals underlying spatial trends, clusters, or outliers that affect interpolation choices
C	It eliminates the need for selecting interpolation parameters
D	It directly outputs the mathematically optimal interpolation surface

B

Select what is true about Boolean Algebra:

A	Isolates features
B	Reduces information to facilitate analysis
C	1 indicates condition met
D	0 indicates condition not met

All of the above

Limitations of Boolean Algebra include:

A	Criteria are true/false
B	Does not support gradation
C	Assumes equal importance
D	Weights layers that are more important

A, B, C

Correct order for Raster Index Model steps:

A	Weight -> Standardize -> Sum
B	Sum -> Standardize -> Weight
C	Standardize -> Weight -> Sum
D	Weight -> Sum -> Standardize

C