Where do we get the data? <ul><li>Census vs sample </li></ul><ul><li>Observations </li></ul><ul><ul><li>“ Watching” real a...
For Example <ul><li>TV watching and test scores </li></ul><ul><li>Observation </li></ul><ul><ul><li>Use a survey that asks...
Live Example <ul><li>Movie popularity </li></ul><ul><li>Observation </li></ul><ul><li>Experiment </li></ul><ul><li>Cell Ph...
Variables <ul><li>Variable  refers to any characteristic that could effect an outcome being tested. </li></ul><ul><ul><li>...
Varying and Controlling <ul><li>In a statistics study, we test if one variable really has an affect on the outcome. </li><...
Treatment <ul><li>When running a experiment that tests a variable: </li></ul><ul><ul><li>The sample will be split into gro...
Placebo Effect <ul><li>The subject, but especially the control group, might think they are being given the treatment and s...
Sampling <ul><li>Sampling: picking a subset of a population  </li></ul><ul><li>Sample’s characteristics should reflect the...
Sample Scheme Characteristics <ul><li>Random sample </li></ul><ul><ul><li>Each member of the population has an equal chanc...
Sampling Strategies <ul><li>Self-selected </li></ul><ul><ul><li>Population members volunteer </li></ul></ul><ul><ul><li>E....
Sampling Strategies <ul><li>Random sample </li></ul><ul><ul><li>Each member of the population is selected at random </li><...
More Sampling Selection and Collection <ul><li>Stratified sampling </li></ul><ul><ul><li>Divide the population into groups...
Example: Student Opinion Poll <ul><li>Self-selecting </li></ul><ul><li>Random sampling </li></ul><ul><li>Systematic sampli...
Example: Crashworthiness <ul><li>Self-selecting </li></ul><ul><li>Random sample </li></ul><ul><li>Systematic sampling </li...
Bias <ul><li>Sampling members of a population… </li></ul><ul><ul><li>With a specific characteristic </li></ul></ul><ul><ul...
More on Bias <ul><li>If I want my test to support the claim that watching too much TV hurts SAT scores, how do I rig the s...
Upcoming SlideShare
Loading in …5
×

1 4 where do we get the data

524 views
477 views

Published on

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
524
On SlideShare
0
From Embeds
0
Number of Embeds
4
Actions
Shares
0
Downloads
8
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

1 4 where do we get the data

  1. 1. Where do we get the data? <ul><li>Census vs sample </li></ul><ul><li>Observations </li></ul><ul><ul><li>“ Watching” real activity and collecting data </li></ul></ul><ul><ul><li>Opinion polls </li></ul></ul><ul><li>Experiments </li></ul><ul><ul><li>Running the activity and measuring the results </li></ul></ul><ul><ul><li>Relatively easy to control </li></ul></ul>
  2. 2. For Example <ul><li>TV watching and test scores </li></ul><ul><li>Observation </li></ul><ul><ul><li>Use a survey that asks your sampled students their TV watching habits and their test scores. </li></ul></ul><ul><li>Experiment </li></ul><ul><ul><li>Design varied TV-watching schedules for your samples </li></ul></ul><ul><ul><li>Design and/or administer an test to measure learning </li></ul></ul><ul><li>Car crashworthiness and make </li></ul><ul><li>Observation </li></ul><ul><ul><li>Collect accident data and auto repair data </li></ul></ul><ul><li>Experiment </li></ul><ul><ul><li>Deliberately crash cars and measure the results </li></ul></ul>
  3. 3. Live Example <ul><li>Movie popularity </li></ul><ul><li>Observation </li></ul><ul><li>Experiment </li></ul><ul><li>Cell Phone Reception </li></ul><ul><li>Observation </li></ul><ul><li>Experiment </li></ul>
  4. 4. Variables <ul><li>Variable refers to any characteristic that could effect an outcome being tested. </li></ul><ul><ul><li>Variables have to be measureable </li></ul></ul><ul><li>What characteristics affect SAT scores? </li></ul><ul><li>What characteristics affect car crashworthiness? </li></ul>
  5. 5. Varying and Controlling <ul><li>In a statistics study, we test if one variable really has an affect on the outcome. </li></ul><ul><li>We will vary the test variable </li></ul><ul><ul><li>Change the value to see if the outcome also changes </li></ul></ul><ul><li>To prevent confounding , we will control the other variables </li></ul><ul><ul><li>Confounding: The effects of two or more variables can not be distinguished </li></ul></ul><ul><ul><li>Control: Samples with similar values for the kother variables may be grouped </li></ul></ul>
  6. 6. Treatment <ul><li>When running a experiment that tests a variable: </li></ul><ul><ul><li>The sample will be split into groups </li></ul></ul><ul><ul><li>Each group will be administered one level of the variable </li></ul></ul><ul><ul><li>Who or what is assigned to each group is randomly determined. </li></ul></ul><ul><li>In some experiments the test variable is all or none. </li></ul><ul><ul><li>E.g., a drug </li></ul></ul><ul><ul><li>One group, the treatment group, receives all (called the treatment) </li></ul></ul><ul><ul><li>The other group, the control group, receives nothing or a pretend treatment called a placebo </li></ul></ul>
  7. 7. Placebo Effect <ul><li>The subject, but especially the control group, might think they are being given the treatment and start to act accordingly. </li></ul><ul><li>If the experiment is blinded the subjects are not told if they are receiving the real treatment or placebo. </li></ul><ul><ul><li>The subjects should also not be told the outcome </li></ul></ul><ul><li>If the experiment is double blinded the people administering the experiment are also not told </li></ul>
  8. 8. Sampling <ul><li>Sampling: picking a subset of a population </li></ul><ul><li>Sample’s characteristics should reflect the population’s in the same proportion </li></ul><ul><li>E.g., our school’s demographic break-down is </li></ul>Frosh Sophomore Junior Senior Male 13% 12% 12% 13% Female 13% 13% 11% 13%
  9. 9. Sample Scheme Characteristics <ul><li>Random sample </li></ul><ul><ul><li>Each member of the population has an equal chance to be selected </li></ul></ul><ul><li>Simple random sample </li></ul><ul><ul><li>Each subset a population has an equal change of being selected. </li></ul></ul>
  10. 10. Sampling Strategies <ul><li>Self-selected </li></ul><ul><ul><li>Population members volunteer </li></ul></ul><ul><ul><li>E.g., Call-in phone lines </li></ul></ul><ul><ul><li>Easy to implement </li></ul></ul><ul><ul><li>Difficult to get a proportional sample </li></ul></ul><ul><ul><li>Susceptible to bias </li></ul></ul><ul><li>Convenience sampling </li></ul><ul><ul><li>Whoever happens by </li></ul></ul><ul><ul><li>E.g., Mall surveys </li></ul></ul><ul><ul><li>Also susceptible to bias </li></ul></ul>
  11. 11. Sampling Strategies <ul><li>Random sample </li></ul><ul><ul><li>Each member of the population is selected at random </li></ul></ul><ul><ul><li>E.g., Generate random student id’s </li></ul></ul><ul><li>Systematic sampling </li></ul><ul><ul><li>Population is put into some order </li></ul></ul><ul><ul><li>Select some starting point, then select every n th individual in a population </li></ul></ul><ul><ul><li>The starting point and maybe the interval ( n ) are picked at random </li></ul></ul>
  12. 12. More Sampling Selection and Collection <ul><li>Stratified sampling </li></ul><ul><ul><li>Divide the population into groups. </li></ul></ul><ul><ul><ul><li>Groups are determined by control variables </li></ul></ul></ul><ul><ul><li>Randomly sample within each group </li></ul></ul><ul><li>Cluster sample </li></ul><ul><ul><li>Divide the population into clusters, randomly pick a cluster, then sample all (or most) members of the cluster </li></ul></ul>
  13. 13. Example: Student Opinion Poll <ul><li>Self-selecting </li></ul><ul><li>Random sampling </li></ul><ul><li>Systematic sampling </li></ul><ul><li>Convenience sampling </li></ul><ul><li>Stratified sampling </li></ul><ul><li>Cluster sample </li></ul>
  14. 14. Example: Crashworthiness <ul><li>Self-selecting </li></ul><ul><li>Random sample </li></ul><ul><li>Systematic sampling </li></ul><ul><li>Convenience sampling </li></ul><ul><li>Stratified sampling </li></ul><ul><li>Cluster sample </li></ul>
  15. 15. Bias <ul><li>Sampling members of a population… </li></ul><ul><ul><li>With a specific characteristic </li></ul></ul><ul><ul><li>That will give a specific outcome </li></ul></ul><ul><ul><li>“ Rigging the game” </li></ul></ul><ul><li>Selection and undercoverage bias </li></ul><ul><ul><li>E.g., FOX news and health care </li></ul></ul><ul><li>Non-response bias </li></ul><ul><ul><li>Counting non-response as one answer </li></ul></ul><ul><li>Voluntary response bias </li></ul>
  16. 16. More on Bias <ul><li>If I want my test to support the claim that watching too much TV hurts SAT scores, how do I rig the sample? </li></ul><ul><li>If I want my test to support the claim that US cars are safer that Japanese cars, how do I rig the sample? </li></ul>

×