Beruflich Dokumente
Kultur Dokumente
Types of Variables!
Categorical Data - Can only be classified by the name of the category it belongs to. No quantity is
associated with a category.!
Ordinal Data - To do with order, generally seen in ordering and ranking data points.!
Nominal Data - Putting data points into specific categories.!
!
Numerical Data - Any data pertaining to a number value.!
!
Discrete Data - When data points can only take on certain values. This occurs when counting is
involved.!
Continuous Data - When data can take on any value within a range. This occurs when data is
measured.!
To organise Categorical Data, we make a frequency table, then use that information to graphically
create a bar chart.!
!
On a frequency table, it should read: Data Sort, Frequency, Relative Frequency.!
!
Bar charts are for categorical data only.!
The bars should not be touching each other.!
It needs to be properly labelled. !
Categories are on the x, Frequency is on the y.!
Distributions!
The centre is where most data points lie. !
The spread is how far the values depart from the centre. !
If a distribution is not symmetrical, it is said to have a skew.!
Summarising Data!
Mean = Sum of Data Values/Total Number of Data Values!
Median = (n+1)/2th point!
Mode = Highest Frequency!
Range = Largest Data Point - Smallest Data Point!
Interquartile Range = Q3 - Q1!
Standard Deviation = How far each data point is from the mean.!
s= sqrt(sum of(data values - mean)^2/n-1)!
!
!
BIVARIATE DATA!
Relationships!
A scatterplot with a positive relationship will tend to increase in a positive gradient fashion.!
The opposite goes for a negative relationship.!
!
Correlation =/= Causation!
!
The process of fitting a straight line to bivariate data is know as linear regression. !
In regression, we write the equation as y = a + bx!
A method of finding the regression line is the two-mean method. To do this we:!
Order the data pairs by x values and divide into two groups. If there is an odd number of data
points, discard the middle one.!
Find the mean of both x and y in each half, then plot them on the graph and draw a line between
them.!
!
r is between -1 and 1. The strength of the according number is the same as the q correlation.!
!
The most common method for fitting a straight line to data is the method of least squares. The
least squares regression line is the line for which the sum of squares of the vertical deviations from
the line is a minimum. These deviations are called residuals. !
The slope of this regression line is given by b = r x Sy/ Sx and a = ybar - b x xbar!
Where!
r = Correlation coefficient!
Sx and Sy = Standard deviation of x and y!
xbar and ybar = mean values of x and y!
!
!
!
!
!
!
G.S:!
Diverge when r is smaller than -1 or greater than 1!
Converge when between -1 and 1!
Oscillate when less than 0!
Difference Equation!
tn + 1 = 5tn + 2, a = 4!
The sequence would be, 4,22,112,562.!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
NETWORKS!
A network is a graph of dots and lines, called vertices and edges respectively. !
The degree of a vertex is the number of edges attached to the vertex.!
Two graphs are isomorphic if they have the same numbers of edges and vertices, and
corresponding vertices have the same degree and the edges connect to the same vertices.!
A graph is not connected if there is not a path along the edges that connects the vertices to each
other. ie. a vertex is on its own, separated from the rest of the graph.!
A planar graph can be drawn so that no edges intersect, except at the vertices.!
We can divide such a graph into faces, such that there are regions inside the graph, as well as the
region outside.!
A network is traversable if you can find a route through the network, along the edges, that uses all
edges, but once only. A connected network is traversable if all vertices are of even degree, or
exactly two vertices are of odd degree, and the rest are even.!
A path is a sequence of edges, linking successive vertices, that connects two different vertices in a
network.!
!
A circuit is like a path, but starts and finishes at the same vertex.!
!
An euler path passes along every edge in a connected network, but uses each edge only once. It
may pass through a vertex more than once. If a network is traversable, it has Euler paths.!
!
An euler circuit is an euler path that starts and finishes at the same vertex.!
!
To have an euler circuit, the connected network must have all vertices of even degree. It can start
and finish at any vertex in the network.!
A hamilton path passes through ever vertex in a connected network once and once only. It may or
may not involve all the edges.!
!
A hamilton circuit is a hamilton path that finished at the same vertex.!
!
The shortest path that passes through each vertex once only is the shortest hamilton circuit.!
!
A tree is a connected graph that contains no circuits, multiple edges or loops. It may be a part of a
large graph. A tree with n vertices has n-1 edges. !
A spanning tree connects all vertices in a connected graph but has no circuits, multiple edges or
loops. !
The minimum spanning tree is the spanning tree of minimum length. There may be more than one
minimum spanning tree in a graph. !
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
!
TRIGONOMETRY!
A compass bearing is in the form N30E!
A true bearing is in the form 030T!
A triangle is labelled with the side opposite the letter being the lowercase version.!
ie. Opposite Angle A is side a.!
!
a / Sin A = b / Sin B = c / Sin C!
!
Herons Rule!
Atri = sqrt( s(s-a)(s-b)(s-c)!
where s = a+b+c/2!