Experimental Design and Data Analysis

Flashcards covering key concepts from Experimental Design and Data Analysis lecture notes, focusing on data distribution, normal and non-normal distributions, skewness, kurtosis, and z-scores.

Data Distribution

A way of representing data, often as big spreadsheets containing numbers and values.

Data Distribution

A visual representation of data showing how far each item is from the center (mean).

Normal Distribution

The most frequently encountered data distribution, also known as Gaussian or Parametric distribution.

Normal Distribution

A distribution centered on the mean of the data.

Normal Distribution

A distribution where most data are clustered around the center.

Normal Distribution

In a perfectly normal distribution, the mean, median, and mode have the same value.

Non-Normal Distribution

A type of distribution where the majority of data is found either to the left or right of the center.

Skewness

Another term used to describe Non-Normal Distribution.

Right-Skewed (positive skew)

The tail of the distribution reaches to the right-hand side of the x-axis.

Left Skewed (negative skew)

The tail of the distribution reaches to the left-hand side of the x-axis.

Kurtosis

A measure of how wide or narrow the tails of a distribution are.

Kurtosis

Represents how often outliers occur in a distribution.

Normal Distribution

Distribution measured relative to normal distribution when considering Kurtosis

Other Non-Normal Distribution

Examples: Continuous Uniform Distribution, Negative Exponential Distribution

Normal Distribution

Common in biomedical data like blood cell counts, serum sodium concentration, height and weight.

Standard Deviation and Normal Distribution

Area between ±1 standard deviation from the mean in a normal distribution: ~68%.

Standard Deviation and Normal Distribution

Area between ±2 standard deviations from the mean in a normal distribution: ~95%.

Standard Deviation and Normal Distribution

Area between ±3 standard deviations from the mean in a normal distribution: ~99.7%.

Z-score

The number of standard deviation units an observation is away from the population mean.

Z-score

+1 standard deviation gives a z-score of 1.

Z-score

-1 standard deviation gives a z-score of -1.

Z-scores

Allows you to standardize differences across different distributions.

Z-scores

Can be useful in determining malnutrition, etc., in human growth.

Frequency Distribution

Plotting data as a histogram.

Data Distribution

Presents how far each individual item is from the center of the data.

Normal Distribution

The most frequently encountered data distribution.

Normal Distribution

Curve is centred on the mean (average) of the data

Non-Normal Distribution

The majority of the data is found either to the left or the right of the center of the data

Right-Skewed

The tail of the distribution reaches to the right hand side of the x axis.

Left Skewed

The tail of the distribution reaches to the left hand side of the x axis.

Kurtosis

Measure of how wide or narrow the tails of a distribution are.

Kurtosis

This tailedness represents how often outliers occur.

Z-score

The number of standard deviation units that an observation is away from the population mean.

Z-score

If an observation has a value above the population mean, it has a positive z score

Z-score

A value below the mean has a negative z-score

Right Skew

Distribution type common in scenarios such as income distribution.

Left Skew

Distribution type common in scenarios such as age-related deaths

[e-mail]

Contact email for Dr. Andy Lewis, the module organiser.

BIOL143

Course code for Experimental Design and Data Analysis.

Gaussian Distribution

Another name for the normal distribution.

Parametric Distribution

Another name for the normal distribution.

Skewed Distribution

Term for a distribution where the majority of data is not centered.

SD

Term for standard deviation in relation to z-scores

Central Limit Theorem

What helps to avoid worrying about data's underlying distribution.

https://shiny.rit.albany.edu/stat/sampdist/

The point where you can find interactive simulations for the central limit theorem

Z-Scores

Used can standardize differences across different distributions with these

Sport Injuries

Elite Boxers were used when collecting data on

Histogram

Visual representation of data for elite boxer's sport injuries

Non-Normal Distribution

The second most common type of distribution

Kurtosis

Describes how often outliers occur

Normally Distributed

We should be almost always talking about that sample data is approximately