Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.

Normal Size Small Size show me how

Normal Size Small Size show me how

# Research and Statist

### National Counselors Exam

Question | Answer |
---|---|

Independent vs. Dependent Variables. How they act. | The DV is dependent on the IV which the researcher is free to manipulate. The IV is in the experiement to see how it will effect the DV |

Control Group | A group that does not get the independent variable |

Experimental Group | This is the group that does get the independent variable. |

What is the impact of ________________ on __________________. | What is the impact of the independent variable on the independent variable. |

How does random sampling help to prevent sample bias? | With random sampling every member of the population has an equal chance or probability of being selected for the study. The selection of one member has no effect on the selection of another member. |

After the subjects have been randomly chosen, what else is necessary to prevent sample bias? | Researchers must randomly assign the subjects to the experimenter and control groups. Randam assignment to each group is necessary in order to prevent sample bias. |

Quasi experimental group | Any experiment that fails to use random assignments or does not have a control group is a quasi experimental group. (Such as an intact group ie. Ms Smiths 4th grade class). |

Stratified sample: | In a stratified sample persons from sub groups or strata are selected based on members shared attributes or characteristics. |

Proportional sample: | A proportional sample represents the proportions of the general population. It is the same ratio as would be found in the population. Such as half, male half female. |

Cluster sampling: | A sample is taken from a naturally existing group. From this existing cluster (such as Oregon City High School freshmen) you would randomly select from the exsisting cluster. |

Enth sampling or systematic sampling: | Enth or Caeth or systematic sampling: Newer popular sampling method where every 10th or 15th person from the population is chosen. The results in most experiments seem to be similar no matter which method you use. Systematic sampling is easier. |

Probability Samples: | Stratified, Proportional, Cluster and Enth or Caeth. |

Non-probability Samples: | Judgement, Convenience and Quota |

Stratified sample: | In a stratified sample persons from sub groups or strata are selected based on members shared attributes or characteristics. |

Proportional sample: | A proportional sample represents the proportions of the general population. It is the same ratio as would be found in the population. Such as half, male half female. |

Cluster sampling: | A sample is taken from a naturally existing group. From this existing cluster (such as Oregon City High School freshmen) you would randomly select from the exsisting cluster. |

Enth sampling or systematic sampling: | Enth or Caeth or systematic sampling: Newer popular sampling method where every 10th or 15th person from the population is chosen. The results in most experiments seem to be similar no matter which method you use. Systematic sampling is easier. |

Probability Samples: | Stratified, Proportional, Cluster and Enth or Caeth. |

Non-probability Samples: | Judgement, Convenience and Quota |

Judgment Sample: | A sample which the researcher believes to be representative of the population being studied. |

Convenience Sample: | A sample taken from an intact group without any random selection. |

Quota Sample: | Subjects have pre specified characteristics so that sample will mimic the same characteristics that are assumed to exist in the population. |

The representativeness of the sample is more important than the procedure that is used to pick the subjects. T or F? | True |

Probability Samples | Cluster and...... |

Experimental Hypothesis | An idea or a hunch that if an experiment is performed there will be an outcome effect. |

Null Hypothesis | The idea that if an experiment is performed there will not be an outcome or effect. |

Each experiment has two hypothesis, these are: | Experimental Hypothesis and Null Hypothesis. |

H1 H2 Ha (with small numbers) designates: | Hypothesis, Sub-Hypothesis, or Alternative Hypothesis respectively. |

No (with a small zero) designates: | Null Hypothesis. |

Test Hint: A modern form of hypothesis: | is written in the present tense without using the word significant or measurement. |

A modern form of hypothesis: | Might also include sub hypothesis such as different result for males and females. |

A test of significance or confidence is: | How big of a result would be a significant outcome? How many times would you have to duplicate the results to claim that the result is significant. The results must be duplicated for a certain number of times to claim significance. |

Tests of significance operate on the principle of probability abbreviated as p | // no answere yet |

P<.05 represents: | A 95% chance that the outcome was significant |

External Validity: | Can the results be generalized to other groups, programs, or settings. |

Internal Validity: | Does the experiment really demonstrate that the DV changes or lack of them were caused by the IV. Does the treatment really work? |

Examples of threats to Internal validity: | Errors in administering the test, such as human bias or faulty equipment. These are referred to as instrumentation threats to external validity. |

Threats to internal validity: | Threats to internal validity: When researcher cannot control procedures that impact the experiment. |

Examples of threats to external validity: | Statistical Regression/When a task or test is re-administered the results change. Attrition of group members or maturity/ When subjects or the character of the group changes over time, members drop out. Selection of group was faulty,ie Intact groups |

More Examples of threats to external validity: | Experimental findings will not generalize to the real world. The Hawthorne effect or a reactive effect. The subjects are affected just by being part of a study. Hawthorne effect |

Type 1 | We reject null when it is true. When one error factors goes up the other goes down. The probability of making a type one error is the level of significance. |

Type 2 | We accept null when it is false. When one error factors goes up the other goes down. The probability of making a type one error is the level of significance. |

Independent Variable | A variable that the experimenter manipulates |

Dependent Variable | The results The outcome, data or the scores. Some form of human response. |

Parsimony-Acums Razor | As applies to research, reducing a theory to it's simplest form. |

Experiment-True Experiment | Researcher has control over all relevant variables. |

Confounding | Other extraneous variables were present that could not be controlled. |

Created by:
Natalielpc