Quantitative Flashcards
Quan
a deductive approach
theory testing
quan starts with a theory and test hypothesis
Hypothesis
an expected answer to our research question
Theory =
a reasoned and precise speculation about the answer to a research question
reliability
the consistency of a measure of a concept
concepts
labels of ideas or phenomena
Descriptive inferences
set of observations in order to understand a phenomena
Validity
data quality- refers to the truthfulness of a measure -
measuring what we think it is measuring
Reliable
data collection is reliable - could apply the same procedure at a different time and will get the same results
Casual relationship
Causality is the relation between an event and a second event, where the second event is understood as a consequence of the first
However finding a relationship doesn’t mean its casual
Methodology
- a system of methods used to test hypothesis
- steps to test a hypothesis
Measurement
process by which raw data is turned into numbers
imposing a numerical structure on our data
Coding
process which observations recorded in the course of social research - then transformed from raw data into categories and classifications which then become subject to quan data analysis
coding involves the act of measurement
trying to measure the underlying social variable
variables
measures of indicators
variables are how we operationalise social concepts
variable is a characteristic that is likely to vary
Not all variables are equal - need different levels
Nominal
Ordinal
Interval
Nominal level variables
are categorical
response categories cannot be placed in a specific order - can’t judge distance between
Nominal and Ordinal
both categorical
Examples of Nominal level variables
Sex
Ethnicity
Examples of Ordinal
Likert scale - agree, strongly agree
Examples of Interval (continuous)
age
temperature
Ordinal level variables -
can be placed in rank orders, one is greater than the other.
But do not have mathematically distance between
Interval (scale) level variables (continuous) =
rank order, with uniformed distance between each response which allows for mathematically measurement
Interval level variable is..
Continuous
Missing data =
-99
Each row in SPSS =
a case
Each column in SPSS =
represents a variable
Each cell in SPSS =
contains a response
Visualising Nominal data -
Pie charts
interested in proportion of people
Visualising Ordinal data-
Bar chart
compare proportion of people agreeing or disagreeing
Visualising Interval (scale) data-
Histograms - normal distribution
Histograms show is variables are..
Normall distributed
Visualising relationship between 2 Interval (scale) variables =
Scatterplot
Inference
using facts we know the data to learn about the facts we do not know
Descriptive statistics
is the main tool to make descriptive inferences
allow us to describe our data
describe basic features of the sample we are interested in
- NOT looking for relationship
- patterns and trends!
Characteristics of a variable - 3
distribution/frequency
central tendency
dispersion
Characteristics of a variable shown in -
Frequency table
displays number of times that a value appears within the data set
Characteristics of a variable shown in -
central tendency
includes the mean, median and mode values
they show us how clustered the data is
Characteristics of a variable shown in -
Dispersion
Range and standard deviation
how spread out the data is
Mode- can be used to describe -
nominal, ordinal and interval (scale)
value occurs most frequently
Median - can be used to describe -
the middle in ordered data
ordinal and interval (scale)
Mean - can be used to describe -
ONLY interval (scale)
Bivariate Data
Data for two variables
shown in scatterplot
Range =
measures between highest and lowest
large range may reveal outliers
standard deviation =
measures the distance (deviation) of each value from the mean
Range and standard deviation- can be used to describe -
interval (scale) (continuous)
