Research, Statistical Bias, Surveys, GIS, Big Data

Seven Steps of Problem Definition

1. develop preliminary definition of problem

2. specify the boundaries to the problem

3. develop a fact base

4. list goals and objectives

5. identify the range of solutions

6. define potential costs and benefits

7. review the problem statement

Survey Research

he method of collecting information by asking a set of pre-formulated questions in a predetermined sequence in a structured questionnaire to a sample of individuals drawn so as to be representative of a defined population

Population

The group you want to generalize to.

The entire set of persons that have at least one common characteristic of interest to the researcher.

the sample is selected from the population

Sample

a subset of a population

calculate a sample statistics because collecting data on the entire population is neither feasible not necessary.

a sample statistic is an estimated population parameter

research focuses on collecting a sample of observations to make inferences about a general population

Sample Size

the number of data points, individuals, or items included in a study to make inferences about a larger population

generally live with 5% chance of being wrong

diminishing returns—a sample of 10k is not twice as good as 5k, and may not be much better at all. need to look at statistical significance tables to determine

as sample size increases, the standard error increases

Sampling Error

the error expected in probability sampling, composed of population parameter, sample size, and standard error

Sampling Frame

the listing of the accessible population from which you draw your sample

ex: sampling residents using a phone book, if you select a random area code then that becomes the sampling frame

Convenience Sampling

a non-probability sampling method where participants are selected based on their accessibility and availability rather than representativeness of the population.

Volunteer Sampling

a non‑probability method in which participants self‑select into a study, meaning they volunteer rather than being randomly chosen.

It relies on open invitations—such as online surveys, ads, or sign‑up forms—and is widely used because it is easy and inexpensive, though it introduces self‑selection bias.

Simple Random Sampling

a type of probability sampling where each individual has an equal chance of being selected for the sample

Systematic Sampling

a type of probability sampling where every Xth individual is selected from the list, starting at a randomly chosen point

Stratified Sampling

a type of probability sampling where population may have two or more groups in the study that need to be adequately represented.

provides best results because it ensures even coverage of the population but maintains random selection probabilities

Cluster Sampling

the population is divided into smaller groups, called clusters, that represent the larger population.

used when stratified or simple random sampling would be difficult and/or expensive

Nominal Scale

assignment of numbers of symbols for the purpose of designating subclasses that represent unique characteristics

weakest level of measurement, meaningless to find mean, standard deviations, etc.

Ordinal Data

a type of categorical data where the categories have a meaningful order, but the exact differences between them are unknown or unequal.

ex: rank order of people’s height, order of ten largest cities

Interval Scale

a quantitative measurement scale where values have a meaningful order and equal differences between them, but no true zero point.

properties of magnitude and intervals

Ratio Scale

a measurement scale with ordered values, equal intervals, and a true zero, allowing meaningful comparisons and ratios between values.

Qualitative Variable

nominal and sometimes ordinal

Quantitative Variable

interval or ratio

Discrete Variable

takes on a finite number of values, generally whole numbers

Continuous Variable

any number value can change to another in a given moment (ex: height, GPA)

Dichotomous Variable

a fixed value throughout time (ex: pass or fail)

Mode

the most frequent score in a distribution

Mean

the sum of the scores in a distribution divides by the number of scores

ex: batting average, grade point average

Median

the midpoint in a distribution

Range

the difference between the highest and lowest score

Dependent Variable

the outcome or effect in a study that changes in response to the independent variable.

Independent Variable

the factor a researcher deliberately changes or controls to test its effect on another variable, such as treatment type in an experiment.

Linear Regression

a method of inferential statistics that tries to explain the correlation between a dependent variable and one or more independent variables using a straight line

finding the best-fitting straight line through a set of points plotted on a scatter plot

used in regression analysis

Hypothesis Testing

a statistical method used to decide whether there is enough evidence in a sample to infer that a certain condition holds true for the entire population

T-Test

a statistical hypothesis test used to determine whether the means of one or two groups are significantly different from each other when the population standard deviation is unknown

best when there’s a small sample size

Z-Test

a statistical method used to determine whether there is a significant difference between a sample mean and a population mean, or between two sample means

It is particularly effective when the sample size is large and the population standard deviation is known

Bias

a systematic error that leads to an inaccurate representation of reality.

It can occur at various stages of data collection and analysis, including the source of the data, the methods used to collect the data, the estimator chosen, and the methods used to analyze the data.

is often confused with sampling error. sampling error is the natural consequence arising out of the fact that sample size is much less when compared to the population size

Selection Bias

a systematic error that occurs when a study’s sample does not accurately represent the target population, leading to distorted or misleading results.

also known as a non representative sampling bias

Leading Question

the bias caused in measurements due to leading questions is often intended

the questions or survey might be framed in a way to lead to the responses desired by the researcher

Probability Sampling

samples that are selected in such a way as to be representative of the population

ex: simple random sampling, stratified sampling

Nonprobability Sampling

a method used in research where samples are selected based on non-random criteria such as availability, geographical proximity, or expert knowledge

ex: volunteer sampling, convenience sampling

Big Data

an accumulation of data that is too large and complex for processing with traditional database management tools

Downsides to Big Data

privacy, control and access to the data

fallibility and quality of data

structure and compatibility of datasets

learning curve and skills gap in terms of analyzing big data

Algorithmic Bias

systematic and repeatable errors in a computer system that create unfair outcomes, typically privileging one group of users over another

in regards to ai and planning

Smart City Digital Twin

a digital representation of the built environment or system.

it is continuously updated with real-time data and analytics on interactions between humans, infrastructure, and technology to create a living digital representation of a city

System Analysis

the process of studying a procedure or business to identify its goal and purposes and create systems and procedures that will efficiently achieve them

can think of a city as a system, or the plan making process