Descriptive statistics Flashcards
What are the**Types of data **?
- Primary data
- Secondary data
- Qualitative data
- Quantititative data
- Meta-analysis
Primary data
*Data obtained from the participants directly *
- Time consuming and expensive to obtain & analyse
+ Collected first hand- has not been altered by others
+ Gathered for the purpose of study
**Secondary data **
Data that has already been collected from other researchers
+ Quick & cheap
- Information may be outdated or incomplete
Q
**Qualitative data **
*Descriptive data based on thoughts, opinions & feelings *derived from open-ended questions
+ Gives richer detail
- Difficult to analyse
Quantitative data
Numerical data, derived from *closed-ended questions *
+ Easy to analyse
+ Much more reliable
- Oversimplifies behaviour
Meta-analysis
**Reviewing & comparing the findings of previously conducted research studies **
+ Less time consuming because study has already been done
+ Inexpensive
- Reling on other people, so mistakes & bias affect your results
**Levels of data **
- Nominal Data
- Ordinal Data
- Interval Data
Nominal Data
Categorical variables, it classifies things
e.g gender: female / male
colour: blue, green, brown, black
Ordinal Data
Categories are rank ordered
They indicate a greater than relationship but dont show how much greater
e.g Olympic marathon results- first to last
Exam results - A* - U
Interval Data
Measurement on a scale
They have *equal units of measurements *
e.g temperature, time, weight, height
Exam results- using % and scores instead of grades
Measures of central tendancy
Tendancy: Inform researchers of the average for data collected
Mean
The average score
* all scores are added together & divided by the numer of scores
+ *Considers the average of all *the numbers in data
- Can be distorted by extreme values, may not be accurate
Median
The middle value of data
* All *scores are placed in order and middle value is identified *
+ Unaffected by extreme values
- Only takes into account one/two values and does not represent the whole data set
Mode
Most common score in data set
* All scores are placed in order and most common is identified
+ Unaffected by exterme results
- Can be affected by extreme change in score and doesnt represent whole data set
Measures of dispersion
Dispersion: Inform researchers of how spread out the data is
Range
Difference between the smallest and largest number
* All scores are placed in order and smallest is taken away from largest
+ Easy to obtain
- Does not take into account values
Standard Deviation
- Describes how much *dispersion there is around the mean *in the data set
+ Takes into account every score
- Easily distorted by extreme values - The** lower the standard deviation, the better** because it shows more consistency between the results
Visual Representation of Data
Scattergraph
- Used for the *correlation analysis/ to show the relationship between co-variables *
- One of the co-variables is plotted on the x-axis and the other is plotted on the* y-axis*
Bar graph
- Used to display categorical data
- Bars are seperated to show we are dealing with seperate conditions
Histogram
- Bars touch eachother to show that data is continous
Line Graph
- Also represent* continuous data *and use points connected by a line to show how something changes in value
Distribution graphs
- Show measures of central tendancy
1. Normal distribution graph
2. Positive graph
3. Negative graph
Normal distribution graph
- Bell-shaped curve
- Mean, mode, median occupy the* same midpoint* of the curve
- There is a balanced symmetrical pattern
Positive Skew Graph
- Most of the* distribution is concentrated towards the left of the graph *
- Mean is the lowest score, median is the middle and mode is the highest score
Negative Skew Graph
- Most of the distribution is concentrated to the right of the graph
- Mean is the lowest score, median is the middle and mode is the highest
Computation
- Fractions
- Decimals
- Percentages
- Ratio
- Range
- Significant Figures
