Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Introduction to statistical terms

4,736 views

Published on

Introduction to Statistical Terms

Published in: Business
  • Be the first to comment

Introduction to statistical terms

  1. 1. Introduction to Statistical Terms Dr Bryan Mills
  2. 2. Contents <ul><li>Some key statistical terms </li></ul><ul><li>What makes useful output </li></ul><ul><li>Sampling </li></ul>
  3. 3. <ul><li>Statistics – turn data into information </li></ul><ul><li>Inferential statistics – using a sample to talk about the whole population </li></ul><ul><li>Variables – things that can vary e.g. student grades, height, etc. </li></ul><ul><li>Empirical data – data collected from observation or measurement </li></ul>
  4. 4. The Problem <ul><li>Measurements </li></ul><ul><li>The basis of both models and statistics is being able to measure a variable numerically (quantitatively). </li></ul><ul><li>Statistics </li></ul><ul><li>Usually describe either a set of data or the strength of a relationship. </li></ul><ul><li>Mathematical models </li></ul><ul><li>Something along the lines of &quot;this = that + something else * something other&quot; </li></ul><ul><li>These are often expressed as x = f (a,b,c) or income = f (age, social class, qualifications) - in other words x is a function of other variables </li></ul>
  5. 5. Types of Data (Discrete ) <ul><li>Nominal - differences e.g. voting preference, Towns, types of beach (sandy, rocky, etc.), discrete categories, occupations, named groups. Uses cross-tabulation (contingency tables) and Chi 2 as a means of display/analysis ( Non-parametric ). </li></ul><ul><li>Ordinal - differences and magnitude - e.g. ratings in order, A, B, C grades, small- medium - large ( Non-parametric ). Use Mann-Whitney, Kruskal Wallis, Spearmans </li></ul>
  6. 6. Types of Data (Continuous) <ul><li>Interval - differences, magnitude and equal intervals, centimetres above and below an average height, IQ - 125 is the same to 110 as 115 is to 100, but 120 is not twice 60, Centigrade, there can be no 0 , however, so height from 0 would be a ratio scale ( Parametric ). </li></ul><ul><li>Ratio - differences, magnitude and equal intervals plus the ability to say this is twice that etc. MPH, size, Kelvin ( Parametric ). </li></ul>
  7. 7. Type of analysis <ul><li>Between groups - between different groups (e.g. independent group t-test) </li></ul><ul><li>Within groups - repeated measures, before and after an experiment (e.g. related samples t-test) </li></ul>
  8. 8. Number of Variables <ul><li>Univariate - 1 variable </li></ul><ul><li>Bivariate - 2 variables </li></ul><ul><li>Multivariate </li></ul>
  9. 10. Meaningless Mean <ul><li>  Mean grade = 56% but 7 students out of the 10 are below this. </li></ul>
  10. 12. A Reminder Often Low High Small and rich in data Qualitative Phenomenology High Often Low Represents a large population Both, but mostly quantitative Positivist Reliability Validity Sample Size Qualitative Quantitative
  11. 13. What Makes Good Output <ul><li>There are 2 main points to consider: </li></ul><ul><li>Your audience </li></ul><ul><li>The data </li></ul>
  12. 15. Sampling <ul><li>Statistics rely on having gathered enough data from a sample to be able to represent the population . </li></ul><ul><li>A sample is a subset of the main population . </li></ul>
  13. 16. Stratification <ul><li>population stratification </li></ul><ul><ul><li>Age </li></ul></ul><ul><ul><li>Gender </li></ul></ul><ul><ul><li>Ethnicity </li></ul></ul><ul><ul><li>Other known characteristics </li></ul></ul>
  14. 17. Ideal Response Size <ul><li>Sample size = Ideal Response Size </li></ul><ul><li>Estimated Response Rate (%) </li></ul>
  15. 18. <ul><li>Where: </li></ul><ul><li>n = Number of usable questionnaires returned p = Proportion being estimated </li></ul><ul><li>Z = Confidence coefficient (1.96 by convention) E = Error in proportion (<5% by convention) </li></ul>
  16. 21. Types of Sample (probability) <ul><li>Simple Random Sampling </li></ul><ul><li>Stratified Random Sampling </li></ul><ul><ul><li>proportional or quota </li></ul></ul><ul><ul><li>Divide into sub-groups and take random sample from each </li></ul></ul><ul><li>Cluster (Area) Random Sampling </li></ul><ul><ul><li>Narrow down to area (e,.g. Districts) </li></ul></ul>
  17. 22. Types of Sample (non-probability) <ul><li>Convenience Sampling </li></ul><ul><li>Purposive Sampling </li></ul><ul><ul><li>Modal Instance Sampling </li></ul></ul><ul><ul><ul><li>Target ‘typical’ </li></ul></ul></ul><ul><ul><li>Expert Sampling (Delphi) </li></ul></ul><ul><ul><li>Quota Sampling (work to a quota) </li></ul></ul><ul><ul><li>Heterogeneity Sampling (diversity of views) </li></ul></ul><ul><ul><li>Snowball Sampling </li></ul></ul>

×