Chapter 1 Flashcards
Research Design
planning and designing appropriate ways of collecting data for the
investigation of a particular scientific problem
Descriptive Statistics
description, summarization and presentation of data using both numerical and graphical methods
Inferential Statistics
drawing scientific conclusions and making a prediction ab population based on the data from a sample of the population. eg: hypothesis tests, confidence intervals, making a estimate ab population based on size of sample.
Variable
any characteristic that varies (natural variation), often several, the “What”.
Distribution of a Variable
all the values that a variable takes on.
Categorical Variables (Qualitative Variable)
Data Recorded on a Nominal (names) Scale, is a non-numerical value. No measurements are obtained from this but they obtain numbers for analysis eg: color, gender, animals
Nominal Scale (name scale)
Nominal scales may sometimes be assigned numbers for ease of recording, but the variable is still
categorical (not quantitative), for example, 1 = single, 2 = common-law, 3 = married, 4 = separated, 5 = widowed, 6 = divorced.
Binary categorical variable
a variable that has only two possible categories
Ordinal Scale Variables/Data
Data or observations can be put in order from lowest to highest, but which do not have a constant interval between successive units, i.e., the data can be ranked. an ordinal scale of 1 – 5 can be used, where 1 = very poor, 2 = poor, 3 = moderate, 4 = good, 5 =very good.
Quantitative Variables/Data
A quantitative variable is a numerically-valued variable.
Constant interval size between successive units.
Discrete or discontinuous quantitative variable
a quantitative variable whose possible values only take on specific values, usually whole numbers.
▪ a countable variable.
▪ e.g., the number of people, animals, or stars must be whole numbers.
Continuous quantitative variable
a quantitative variable that has an infinite number of possible values between any observed range.
▪ a measureable variable.
▪ e.g., the weight of a person may be 71 kg or 72 kg or an infinite number of possible values
between, e.g., 71.42 kg or 71.42893 kg, depending upon the accuracy of the balance used.
▪ Time, distance and height (regardless of units) are always continuous variables.
▪ Even if the measurements are rounded to whole numbers
Explanatory or Predictor variables
variables of interest that are hypothesized to explain or affect other variables in the study, but which are not likely to be affected by those other variables. (Independent Variable)
Response variable
the variable that is hypothesized
to be affected by the explanatory or independent variables. (Dependant Variable)
* E.g., age and height – height does not affect age, but age affects height
Extraneous variables
Explanatory variables that are NOT of interest or are NOT related to the purpose of the study, though they could be of interest in a different study.
* These may potentially affect the response variable, interfering with the study and leading to “experimental error”.
Factors (Categorical predictor variables)
When explanatory variables are applied as treatments in an experiment or considered as levels in an observational study,
* The researcher tries to determine the effects that the different levels of the factor have on the responses of the study units
Spatial Aspects of Design
The “Where” Involves the way the observations or replicates are arranged in space (distance, area, or volume), where they are sampled and measured
Temporal Aspects of Design
The “When” Involves the way observations or replicates are arranged in time
* Time period (year, month, time of day) and frequency of observations
* Start, end, frequency of recording the variables
Techniques and Methods of Data Collection
The “How”
* Specific methods and techniques used to take measurements of the variables or to record data
Simple random sampling
o Every individual is selected completely randomly and independently
o Every group or area of the population have an equal chance of selection
o All the statistical tests dealt with in this course require simple random sampling
Systematic random sampling
o The first sample is selected randomly, then all other samples are selected sequentially,
E.g., every 30 seconds of swimming over a coral reef, every 10 m, every 5 min, o E.g., every 5th person, etc.
o E.g. sampling plots in a forest
o Usually random enough unless there is a rhythmic cycle in the data
Stratified random sampling
The population is divided into strata, based on a pilot study or some prior information
o Items within each subpopulation are considered relatively homogeneous
o Proportional allocation = sampling intensity in each stratum is proportional to the
estimated density of the items in the stratum or size of the stratum
Multistage Random sampling
- Example of sampling leaves on trees of a certain species:
o Randomly sample trees, then
o Randomly sample the branches on the selected trees, then
o Randomly sample some of the leaves from the selected branches and take them for
analysis.
Cluster Random Sampling
For example, if a company with a large number of apartment blocks (e.g. 100) want to get the
opinions of their tenants about some proposed changes.
▪ Randomly select a few apartment blocks and then interview all the tenants in the selected
blocks. Each selected block would then be considered as a cluster.
Convenience sampling
selecting individuals for recording data simply because they are convenient to observe information from or question
* E.g. interviewing people in a shopping mall
Voluntary response bias
asking for volunteers to participate in a social survey
Response bias
questions in a social survey that appear to suggest or prompt a particular response favored by the researcher
Nonresponse bias
occurs when a large fraction of those sampled fail to respond to some or any of the questions
Incomplete sampling frame
some individuals or groups who actually belong to a certain population are not included in the sampling frame
Undercoverage
some portion of the population not being included or given smaller representation
Observational Research
IMPORTANT CHECK NOTES
Experimental Studies
IMPORTANT CHECK NOTES
Extraneous Variables
IMPORTANT CHECK NOTES
Blinding
Those who could affect the results, and those who evaluate the results
Single-blind experiment
all individuals of one or the other of the above groups are blind.
Double Blind Experiment
all individuals of both of the above groups are blind.
Placebo Effect
Psychological effect of receiving a placebo, which may result in a subject responding to a treatment when, in fact, they only received an inert placebo.
