A factor that does not depend on other variable for its value
Dependent variable
An event or factor that is effected by, or is dependent on, other factors
Types of data
Nominal
Ordinal
Interval
Ratio
Nominal data
Data that don't have numerical value, may be colors, shapes, brands, or even the number don't have value and might as well be words or letters
Ordinal data
Data that accommodate infinite sequences/ranks and to classify sets with certain kinds of order structures on them
Interval data
Data that not only provide a ranked order, but also a specific scale of measurement
Ratio data
Real values that can be compared to each other and are not limited to scale
Sampling
Data cannot be collected on every event or object within a study area
The next best thing is to select or sample some of the events or object to represent all of them
Statistical sampling requirements
A large number of samples to be representative of the population
Random sampling where each area has an equal chance of being selected so the sample is unbiased
Sample from the population or a homogenous area to which the results will be applied
Sampling techniques
Grid tessalation
Grid pointing sampling
Grid tessalation
Typically used to identify a systematic pattern for determining regular or irregular sampling points, with a sample taken from each grid cell
Grid pointing sampling
The process is the same with grid tessalation, but instead of assuming that entire cell has the same nutrient value, the nutrient value is applied is applied to the point at which the sample was taken
Unbiased samples
Random sampling assures an unbiased sample
Methods for assuring unbiased samples
Centre method
Offset method
Technique of collection sample
Centre method
Takes a sample in the center of the grid cell
Offset method
Creates a diamond pattern by taking the sample a certain distance offset from center
Technique of collection sample
Standard procedures calls for taking at least 10 samples from various location within a radius of 10 feet of the sampling point to create one composite sample
Frequency
The number of times a value occurs
Frequency tables and graphs
Can help people visualize the data
Descriptive statistics
Used to describe numerically what the frequency graph or curve look like, including the center of the curve (central tendency) and the width of it (dispersion)
Inferential statistics
Used when estimating data or making an inference about differences between data sets
Measures of central tendency
Mean
Median
Mode
Mean
The average of all the numbers
Median
The "middle" value in the list of numbers
Mode
The number that is repeated more often than any other
Range
The difference between the largest and smallest values
Standard deviation (SD)
Shows how much variation or dispersion exists from the average (mean), or expected value
Variance
Variance = s^2
Correlation coefficient
A way of measuring the relationship between paired variables
Simple linear regression
Tries to show that one variable is correlated to the second one
Multivariate regression
Uses data sets that have three or more independent attribute values to predict the dependent variable
Most relationships are not perfectly linear
Significance testing
Used to determine if differences between data sets are statistically significant
Research makes significant use of statistics
The objectivity of research is based on valid data collection, the use of statistics, and the replication and control of independent variables
A research project done once, without replication, has little validity