Quantitative data analysis Flashcards
What is statistics?
The science of collecting, analysing, interpreting and presenting and organising quantitative data
Common applications of statistics in business
-Financial management
-Operational Process Improvement
-Strategic Planning
-Evaluating Performance
What is statistical inferecne?
How we generalise from a sample to a population providing evidence based asnwers to research questions.
What should quantitative data analysis be guided by?
Your research problem
What is the quantitative data analysis process?
- Data collection
- Descpritive Statistics
- Inferential Statistics
- Interpretation & Application
Methods of quantitative data collection
-Surveys
-Experiments
Secondary sources
What needs to happen to qualitative data before it can be applied to statistics?
It needs to be transformed into quantitative data (e.g. coding, text analysis)
How do we collect data on a population?
-Data on the population is rarely available.
- Instead, we obtain a sample to represent the population
-Statistical methods tell us what we can know about the population from the data
What are variables?
Any quantity that can be measured
What are descriptive statistics used for?
Descriptive statistics are used to organsie and summarise data and identify the eatures of a sample, often including visualisation/plots.
What are the key measures of descriptive statistics?
- Central tendency
- Dispersion
-Association
Define Central tednecy?
What is the typical value of a variable?
Define Dispersion
How far from the typical value are the individual observations of a variable?
Define Association
How does a variable relate to another variable?
What are Inferential Statistics?
Used to make predictions about parameters (characteristics) of the population based on two factors.
Key concepts of Inferential Statistics
- Probability
- Sampling distributions
- Hypotheses testing
Define Probability
What is the chance that a particular event will occur?
Define sampling distributions
What is the probability that we obtain parameters observed in our sample?
Define hypothesis testing
Does the data support our beliefs about the population
Define Population
The entire set of people or obects that is the subject of investigation
Define Sample
A subset of the population for which data has been collected
Define Variable
Any number or quantity that can be counted
Define Observation
Data collected for a specfific individual in the sample
Define Statistic
A numer computed form the sample data to estimate a parameter
Define Parameter
A quantifiable characteristic of a population, inferred from sample data
Define Distribution
How the values of a variable are spread
Define Probability
A measure of the liklihood that a particular event will occur
Define Hypothesis
A specific, testable prediction about what you expect to happen in your study
What does conclusive research require?
Requires quantitative measurement of numerical variables
What is descripitve research?
Seeks to verify the nature/characteristics of a phenomenon
What is causal research?
Seeks to test relationships and hypotheses (predictions) –> inferential statistics
How to choose variables?
- Identify the variables to be measured
- Determine the right measurement approach
- Collect observations of these variables for each individual in our sample
What do we use descriptive & inferential statistics for?
To summarise our sample data, then use inference to generalise about population parameters.
What are the 4 levels of measurement?
-Nominal
-Ordinal
-Interval
-Ratio
Define Nominal measurement
Numbers indetify categories or binary outcomes
Define Ordinal measurement
Numbers indicate categories in an ordered sequence (ranking)
Define Interval measurement
Distances are concistent (scores are comparable but zero point is arbitrary)
Define Ratio measurement
Zero point is non-arbitrary and represents a real measurment
What does each level of measurement have?
-Different properties
-The properties of each level determine the types of statisticsl analysis that can be applied
What can data be?
- Data can be categorical or continuous.
- Continous data can be grouped to examine frequencies
What does visualisation help with?
Helps in understanding the distribution of values: Bar charts for categorical data & histograms for continuous data. These can also be presented in requency tables