1 / 18

Sampling and Fieldwork

Sampling and Fieldwork. In the event of a system glitch…. A Sampling Puzzler

maxine
Download Presentation

Sampling and Fieldwork

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Sampling and Fieldwork

  2. In the event of a system glitch… A Sampling Puzzler A traveler in Borneo is beset by ferocious natives who immediately decide to burn him at the stake. Upon learning that he is a researcher and sometimes statistician, however, the chief offers him a chance to save his life.

  3. In the event of a system glitch… Two teak mooka bowls will be set in front of him, together with ten black beads and ten red beads. He must use all of the beads and distribute them as he pleases between the two bowls, putting at least one in each bowl.

  4. In the event of a system glitch… The chief will then select a bowl at random and then draw one bead from it. If it is red, the traveler will go free; if it is black, the barbeque will go on as planned. How should the traveler distribute the beads to maximize his chances? If he does so, what is the probability that he will be allowed to go free?

  5. Sampling • Why sample? • Budget restrictions • Time constraints • Inaccessibility of some population members • Sufficient accuracy, reliability with good sample • Larger sample required for more heterogeneous population • Randomly chosen sample is fair in the sense that every member of the population has an equal chance of being chosen

  6. Target Population • To whom do we wish to generalize results of a sample study? • All voters? • All citizens? • Adults?

  7. Sampling Frame • The empirical representation of the theoretical universe of interest • In theory may be the entire population • But, for example • Not all own telephones (for a telephone survey) • Some may be homeless (for a mail survey)

  8. Sampling Unit • Compare to the desired unit of analysis • Individuals • Work groups, teams • Companies • Industries • Markets

  9. Sampling, Non-sampling Error • Sampling error = statistical fluctuations that occur among samples representing a population or universe • It decreases with sample size • Non-sampling error involves various threats to validity and biases discussed earlier

  10. Non-Probability Sampling • Convenience samples – the researcher’s convenience • Judgment sampling – expert selection of respondents • Quota sampling – ensuring representation of certain groups, individuals • Snowball sampling – initially selected respondents (by probability) refer later ones

  11. Probability Sampling • Simple random sample • With replacement • Without replacement • Systematic sampling – every nth member of the sampling frame is chosen • Stratified sampling – the selection of strata must be based on pre-existing knowledge or a sound theoretical basis; a probability sample is taken within strata

  12. Probability Sampling • Cluster sampling – clusters and individual members are chosen randomly (compare to stratified sampling)

  13. Sample Size • Descriptive statistics – frequencies, range, etc. • Inferential statistics – to generalize to the population or universe

  14. Central Tendency • Arithmetic mean • Median • Mode • Unimodal, symmetric distributions have the same mean, median and mode • Skewed distributions (calculated as 3(x-bar – Md)/s) have the mean pulled toward the tail • Kurtosis describes how flat or peaked a distribution is = (z4/n) - 3

  15. Dispersion • Range • Deviation scores • Variance (s2) = (x-xbar)2/(n-1) • Standard deviation (s) = sq root of the variance

  16. Normal Distribution • Z scores Z = X -   but true population means and standard deviations are rarely known

  17. Standard Error of the Mean The standard deviation of the sampling distribution of Xbar Xbar = /n

  18. Confidence Interval (1-)CI = Xbar +/- 1-/2zXbar

More Related