2.4 Bias in Surveys. Statistical bias is any factor that favours certain outcomes or responses and hence systematically skews the survey results.

2.4 Bias in Surveys

• Statistical bias is any factor that favours certain outcomes or responses and hence systematically skews the survey results.

Sampling Bias

• The sampling frame does not reflect the characteristics of the population.

• For example: a Survey asked students of a hockey team to see if the school should pay for all student’s equipment.

Non-Response Bias

• Occurs when certain groups are under represented in the survey because they choose not to participate.

• A researcher asks every 5th student entering the cafeteria to fill out a survey. Less than half agree to fill out the questionnaire.

Response Bias• Occurs when participants in a survey

deliberately give false or misleading answers. The respondents might want to influence the results unduly, or they may be afraid or embarrassed to answer sensitive questions honestly.

• After a lesson, a teacher says “raise your hands if you do not understand”

Measurement Bias

• Occurs when the data collection method consistently either under or overestimates a characteristic of the population

• A police officer tries to survey traffic speeds by patrolling the highway and recording the speeds of cars around them.

Leading question

• Directs the person’s response through limitation.

Loaded question

• Influences a person’s response through inflammation.

Uses and Misuses of Sample Data

Bias can be unintentional

• In other cases, a person could intentionally manipulate the data management process in an attempt to affect the results.

• This happens in advertising on occasion…

A company’s profit increased from $400.00 to $600.00 per

month

TV sales doubled from 2500 to 5000 units.

year

Number of Bookings at Ski Resorts

Homework

• Page 123

• 1-4