2 - Ms Beaubien's Classroom



1.6 Avoiding Bias

When collecting data for your course project, truth is your #1 goal. To avoid distorting the truth you must have carefully executed and well planned data-collection methods. In this section we will explore how a researcher can unintentionally influence results and how to avoid doing this yourself, or taking information from websites that may have bias.

Definitions

Bias- an unintended influence on a data-gathering method.

Types of Bias

Sampling Bias- when the chosen sample does not accurately reflect the characteristics of the population.

Non-response Bias-when surveys are not returned, thus influencing the result. Particular groups are under-represented.

House-hold Bias- when one type of respondent is overrepresented because groupings of different sizes are polled equally.

Response Bias- factors in the sampling method that influence the result. It occurs when participants in a survey deliberately give false or misleading information.

Measurement Bias – when the data-collection method consistently either under- or overestimates the characteristic of the population

Scenario:

You are the campaign manager for your best friend, Rebecca, who is running for student council president. You have been asked to determine the overall level of support for Rebecca amoung the 1500 students at your school. Read each of the 3 sampling methods, determine what bias exists for each one. Determine which option is the least biased.

Option A:

You have decided to sample 50 students. Students have lunch in periods 3 or 4. By random draw from a hat, you have decided to conduct the survey in the cafeteria during period 4. The first 50 students who enter the cafeteria are give the questionnaire and you instruct them to fill it out and return it to you before the end of lunch.

Option B

You have decided to provide a questionnaire to one person from each homeroom. There are 73 homeroom classes, all of varying sizes. You can wait until the respondent finishes with the questionnaire to collect it.

[pic]

Option C

You use a stratified random sampling technique. Students in each grade could be assigned a number. The appropriate number of males and females from each grade could then be selected using a random number generator. You could interview each selected student. [pic]

Bias in a Questionnaire

What are some of the problems with this questionnaire:

[pic]

Improved:

[pic]

Homework: Page 123 #1, 2 -3, 5, 6.

................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download