data collection & sampling techniquespnhs.psd202.org/documents/rsaini/1503672654.pdf8/25/2017 1...
TRANSCRIPT
8/25/2017
1
Section 1-3
Objectives Identify the five basic sample techniques
Data Collection In research, statisticians use data in many different
ways.
Data can be used to describe situations.
Data can be collected in a variety of ways, BUT if the sample data is not collected in an appropriate way, the data may be so completely useless that no amount of statistical torturing can salvage them.
8/25/2017
2
Basic Methods of Sampling Random Sampling
Selected by using chance or random numbers
Each individual subject (human or otherwise) has an equal chance of being selected
Examples: Drawing names from a hat
Random Numbers
Basic Methods of Sampling Systematic Sampling
Select a random starting point and then select every kth
subject in the population
Simple to use so it is used often
Basic Methods of Sampling
Convenience Sampling Use subjects that are easily accessible
Examples: Using family members or students in a classroom
Mall shoppers
8/25/2017
3
Basic Methods of Sampling Stratified Sampling
Divide the population into at least two different groups with common characteristic(s), then draw SOME subjects from each group (group is called strata or stratum)
Results in a more representative sample
Basic Methods of Sampling Cluster Sampling
Divide the population into groups (called clusters), randomly select some of the groups, and then collect data from ALL members of the selected groups
Used extensively by government and private research organizations
Examples: Exit Polls
Stratified vs Cluster SamplingStratified Cluster
8/25/2017
4
Sampling MethodsState which sampling method was used.
• Out of 10 hospitals in a municipality, a researcher selects one and collects records for a 24 hour period on the types of emergencies that were treated there.
• A researcher divides a group of student according to gender, major field, and low, average, and high GPA. Then, she randomly selects six students from each group to answer questions in a survey.
• The subscribers to a magazine are numbered. Then a sample of these people is selected using random numbers.
• Every 10th bottle of Diet Cola is selected, and the amount of liquid in the bottle is measured. The purpose is to see if the machines that fill the bottles are working properly.
CLUSTER
STRATIFIED
RANDOM
SYSTEMATIC
Bellwork with Group..Applying the Concepts
Sections 1.3
Page 1-17
&
page 1-17
#11 – 16 all
8/25/2017
5
Section 1-4
Objectives Explain the difference between an observational and
an experimental study
Types of Studies Observational Studies
The researcher merely observes what is happening or what has happened in the past and tries to draw conclusions based on these observations
No interaction with subjects
No modifications on subjects
Occur in natural settings
Can be expensive and time consuming
Example:
Counting cars as they drive by.
8/25/2017
6
SurveysTelephone Mailed Questionnaire Personal Interviews
Less costly than personal interviews
Cover a wider geographicarea than telephone
Provides in-depth responses
Subjects are more candid than if face to face
Less expensive than telephone
Interviewers must betrained
Challenge---some subjects do not have phone, will not answer when called, or hang up (refusal to participate)
Subjects remainanonymous
Most costly of three
Tone of voice of interviewer may influence subjects’ responses
Challenge –low number of subjects’ respond, inappropriate answers to questions, subjects have difficulty reading/understanding the questions
Interviewer may be biased in his/her selection of subjects
Types of Studies Experimental Studies
The researcher manipulates one of the variables and tries to determine how the manipulation influences other variables
Interaction with subject occurs
Modifications on subject occurs
May occur in unnatural settings (labs or classrooms)
Example:
Clinical trials of new medications ,treatments, etc.
Partner chat! For each of the following scenarios determine whether a sample
survey, observational study, or experiment would be best. EXPLAIN YOUR ANSWER. We will discuss as a group in a few minutes.
1. What percentage of teenagers leave the water running when they brush their teeth?
2. Which of two drugs is more effective at preventing nausea following the onset of a migraine?
3. Do male or female teenagers tend to have more numbers stored in their cell phones?
4. What percent of drivers come to a complete stop at a stop sign near a local elementary school?
5. Does printing suggested tip amounts on the bottom of a restaurant bill increase the average amount that customers leave in tips?
8/25/2017
7
Independent/Dependent Variable Independent variable
Manipulated/Controlled by researcher
Explanatory variable
Dependent Variable
Resultant variable
Outcome variable
Independent/Dependent Variable
The grade on a test depends on the number of questions answered correctly
The number of calories consumed in a week determines the number of pounds lost(or gained) that week.
A burning candle is an example of a functional relationship. The variables are the height of the candle and the amount of time the candle has been burning.
Heart rate is a function of the amount of activity someone is engaged in. The variables are heart rate and activity level.
8/25/2017
8
Independent/Dependent Variable
The grade on a test depends on the number of questions answered correctly
The number of calories consumed in a week determines the weight that week.
A burning candle is an example of a functional relationship. The variables are the height of the candle and the amount of time the candle has been burning.
Heart rate is a function of the amount of activity someone is engaged in. The variables are heart rate and activity level.
Sources of Misuse There are two main sources of misuse of statistics:
Evil intent on part of a dishonest researcher
Unintentional errors (stupidity) on part of a researcher who does not know any better
Misuses of Statistics Samples
Voluntary-response sample (or self-selected sample)
One in which the subjects themselves decide whether to be included---creates built-in bias
Telephone call-in polls (radio)
Mail-in polls
Internet polls
Small Samples
Too few subjects used
Convenience
Not representative since subjects can be easily accessed
8/25/2017
9
Misuses of Statistics Graphs
Can be drawn inappropriately leading to false conclusions Watch the “scales”
Omission of labels or units on the axes
Exaggeration of one-dimensional increase by using a two-dimensional graph
Is there anything wrong?
Misuses of Statistics Survey Questions
Loaded Questions---unintentional wording to elicit a desired response
Order of Questions
Nonresponse (Refusal)—subject refuses to answer questions
Self-Interest ---Sponsor of the survey could enjoy monetary gains from the results
8/25/2017
10
Misuses of Statistics Missing Data (Partial Pictures)
Detached Statistics ---no comparison is made
Percentages --
Precise Numbers
People believe this implies accuracy
Implied Connections
Correlation and Causality –when we find a statistical association between two variables, we cannot conclude that one of the variables is the cause of (or directly affects) the other variable
2-29
The Hawthorne Studies
Studies of how characteristics of the work setting affected worker fatigue and performance at the Hawthorne Works of the Western Electric Company from 1924-1932.
2-30
The Hawthorne Studies
Worker productivity was measured at various levels of light illumination.
Researchers found that regardless of whether the light levels were raised or lowered, worker productivity increased.
8/25/2017
11
With a partner
Bias Activity Worksheet
HomeworkPage 1-25
#27 – 46 all
Due Friday at the start of class