Data collection
Download
1 / 31

Data Collection - PowerPoint PPT Presentation


  • 92 Views
  • Updated On :

Data Collection. Sampling. Target Population. The group of people to whom the researcher wishes to generalize the results of the study. Accessible Population. -The smaller portion of the target population to whom the researcher actually has access. Sample.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Data Collection' - anchoret


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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Data collection

Data Collection

Sampling


Target population
Target Population

The group of people to whom the researcher wishes to generalize the results of the study


Accessible population
Accessible Population

  • -The smaller portion of the target population to whom the researcher actually has access


Sample
Sample

  • -The group of people who supply data for the study (Study group)


Sampling
Sampling

  • the process of selecting a portion of the target population (sample) in such a way that the individuals chosen represent, as nearly as possible, the characteristics of the target population.


Sampling unit
Sampling Unit

  • -A single member of the target population.


Sampling bias
Sampling Bias

-An overrepresentation or underrepresentation of some characteristic in the sample relative to the target population

Unconscious

Conscious



Strata
Strata homogeneity or heterogeneity of the target population.

  • -Subpopulations of the target population


Sampling error
Sampling error homogeneity or heterogeneity of the target population.

  • -the fluctuation of a statistic from one sample to another drawn from the same population. (Can be estimated with probability sampling) Note: the larger the sample, the less sampling error.


Probability sampling
Probability Sampling homogeneity or heterogeneity of the target population.

  • -Sampling procedures use some form of randomization to select samples from the population.


Non probability sampling
Non Probability Sampling homogeneity or heterogeneity of the target population.

  • Sampling procedures

    using other than random procedures.


Non probability sampling1
NON PROBABILITY SAMPLING homogeneity or heterogeneity of the target population.

  • CONVENIENCE SAMPLING

  • PURPOSIVE SAMPLING

  • QUOTA SAMPLING


Convenience sampling accidental sampling
Convenience Sampling homogeneity or heterogeneity of the target population.(Accidental Sampling)

  • Involves the use of the most convenient and readily available subjects for the sample.

    • CMan on the street interviews

    • C Teacher uses students

    • C Volunteers


Convenience accidental sampling
Convenience/accidental sampling homogeneity or heterogeneity of the target population.

  • Problem: Sample bias because of “self selection”--available subjects may be highly atypical of the population with regard to critical variables.


Snowball sampling
SNOWBALL SAMPLING” homogeneity or heterogeneity of the target population.

  • Variation of above, used when subjects are hard to find. One subject recommends another. Even more prone to bias.



Quota sampling
QUOTA SAMPLING form of sampling. There is no way to evaluate all of the biases that may be operating.

  • Researcher uses some knowledge of the population to build some representativeness into the sampling plan

  • divides population into different strata and samples from each of them

  • USUALLY BETTER THAN JUST CONVENIENCE



Quota sampling1
Quota Sampling IMPORTANT DIFFERENCES IN THE DEPENDENT VARIABLE

  • Problem: you cant always determine which characteristics in the sample are going to be reflected in the dependent variable


Purposive sampling judgmental sampling
PURPOSIVE SAMPLING IMPORTANT DIFFERENCES IN THE DEPENDENT VARIABLE“Judgmental Sampling”

  • PROCEEDS ON THE BELIEF THAT THE RESEARCHER KNOWS ENOUGH ABOUT THE POPULATION AND ITS ELEMENT TO HANDPICK THE SAMPLE

    • C selects “typical” persons

    • C selects widest variety


Purposive or judgemental sampling
Purposive or Judgemental Sampling IMPORTANT DIFFERENCES IN THE DEPENDENT VARIABLE

  • Assumption:

  • judgemental errors will tend to balance out.

  • Risk of conscious bias greatly multiplied

  • Should be avoided if the population is heterogeneous.


Probability sampling1
PROBABILITY SAMPLING IMPORTANT DIFFERENCES IN THE DEPENDENT VARIABLE

  • SIMPLE RANDOM

  • STRATIFIED RANDOM

  • CLUSTER

    The probability of any member of the target population being included in the sample can be calculated.

  • SYSTEMATIC SAMPLING(Can be either probability or non probability)


Simple random sampling
SIMPLE RANDOM SAMPLING IMPORTANT DIFFERENCES IN THE DEPENDENT VARIABLE

C identify population

C establish sampling frame

C number elements in sampling frame consecutively

C randomly select from list



Stratified random sample
STRATIFIED RANDOM SAMPLE does guarantee that difference between the sample and the population are purely a function of chance

  • The population is divided into two or more strata by relevant characteristics and subjects are randomly chosen from these strata

  • Slightly better than simple random, especially if the sample is not very large.


Cluster sampling
CLUSTER SAMPLING does guarantee that difference between the sample and the population are purely a function of chance

  • Multistage sampling process

  • Used when target population is very large

  • Results in more sampling error

  • Statistical analysis more complicated


Systematic sampling
SYSTEMATIC SAMPLING does guarantee that difference between the sample and the population are purely a function of chance

  • Selection of every Kth case from a list of possible subjects.

  • ( K represents any number)


Sample size
SAMPLE SIZE does guarantee that difference between the sample and the population are purely a function of chance

  • N Determined by:

  • COHEN’S POWER ANALYSIS

    Determine “effect size of treatment”

    Use in power analysis formula

    Achieves the least measurement error


N determined by convention
N DETERMINED BY CONVENTION does guarantee that difference between the sample and the population are purely a function of chance

The bigger the better

C cost and convenience

C 10% minimum for descriptive studies

C 15 subjects/group for experiments

C 5 for each cell in factorial


ad