Block 2 Revision Guide

1
Block 2 Revision Guide
Processing, Representing and Analysing Data.
By Sonam
2
Charts, Graphs and Diagrams.

• Two-way Tables.
• Frequency Polygons.
• 1) draw bar graph.
• 2) join the middles of the bars together.
• 3) Rub out the bars.
• Cumulative Frequency.
• Cumulative Frequency total so far.
• CF curves are Sigmoidal ( S shape).
• Histograms.
• Undersimplification not simplified enough
• Oversimplification Simplified too much
• Shape of Distributions.
• The normal distribution is what normally
  happens.
• Most people are normal.

3

• Shape of Distributions.
• The normal distribution is what normally
  happens.
• Most people are normal.
• Positive Skew Skewed Right.
• One end has been stretched to the right.
• The mean is more than the median.
• Negative Skew Skewed left.
• One end has been stretched to the left.
• The mean is less than the median.

4
Central Tendency and Dispersion. (1)

• Grouped Frequency Distribution. (mean, median,
  mode estimates.)
• Sigma Notation.
• ? Sigma is a Greek letter which means sum or
  add up
• ?f means add up all the f values
• Averages from transformed data.
• Many ways to transform the values in each set
  of data are
• Add the same number to each value
• Subtract the same number from each value
• Multiply each number by the same value
• Divide each number by the same value.

-To calculate the mean, add up the fx column and
divide by the total frequency. Mean 1120/46
24.347
-To estimate the mode, assume every range only
contains the middle value. So the mode class is
20ltxlt30 and we assume that they are all 25 (MIV)
-The median is 6 numbers through the 15 in the
frequency column.
5

• Weighted Mean.
• Use the formaula for frequency distributions ?
  f x / ? f
• This time f is the weight and x is the
  score.
• Geometric Mean.
• Two steps
• Multiply together the n different values in the
  list.
• Calculate the nth root of the product.
• Use this method only for multiplicative data,
  such as percentage change and write each
  percentage as a multiplier.
• Which average is appropriate?
• 1) Arithmetic (ordinary) mean.
• 2) Median, Mode, Minimum, Maximum, Range.
• 3) Estimates.

6
Central Tendancy and Dispersion. (2)

• Quantiles.
• Quartiles divide the data in to quarters.
• Q0 minimum
• Q1 lower quartile
• Q2 Median
• Q3 upper quartile
• Q4 Maximum
• A small IQR means the data is bunched together
  clse to the centre.
• A big IQR means the data is dispersed all over
  the range.
• DECILESdivide the data into TENTHS.
• QUINTILESdivide the data into FIFTHS.
• PERCENTILESdivide the data into HUNDREDTHS
• Box and Whisker Plots.

7

• Outliers.
• For outliers and anomalies, you mark a fence.
• The fence is 1.5 x IQR beyond the upper and
  lower quartiles.
• If a value lies outside the fence it is an
  outlier and will either be too big or two small.
• Variance.
• Variance is used to measure the spread of data
  by seeing how far each value is from the mean.
• Standard Deviation.
• To calculate the standard deviation, we use the
  variance but square root at the end since we
  squared the values to find the variance.
• The bigger the SD, the more dispersed the data
  is.
• Standardised Scores.
• The formula for standardised scores is
• SS (Score Mean) / SD