Download presentation
Presentation is loading. Please wait.
1
Planning and Conducting a Study
2
What ways can you think of to collect data??
Data Collection What ways can you think of to collect data??
3
Data Collection Surveys Other ways of collecting data
Telephone surveys Mailed questionnaire Personal interview Other ways of collecting data Surveying past records Direct observation
4
Sampling Techniques To obtain samples that are unbiased, statisticians use four basic methods of sampling: random, systematic, stratified, and cluster sampling.
5
Sampling Techniques Random Systematic
Samples are selected by using chance or random numbers Examples: Numbering each subject in the population. Place number cards into a bowl, mix, and choose as many as needed. Numbering each subject of the population and then selecting every nth subject Example: Suppose there are 200 subjects in the population and a sample of 50 is needed. Since 200/50=40, you could take every 40th subject in the population to select for your sample.
6
Sampling Techniques Cluster Stratified
Dividing the population into groups (called strata) according to some characteristic that is important to the study, then sampling from each group. Example: President from a two-year college wants to learn how students feel about some issue. Furthermore, the president wishes to see if the opinions of the first-year students differ from the opinions of the second-year students. The president will select students from each group to use in the sample. The population is divided into groups called clusters by some means such as geographic area or schools in a large school district, etc. Researcher randomly selects some of these clusters and uses all the members of the selected clusters as the subjects of the sample. Example: I want to survey apartment dwellers in a city. If there are 10 apartment buildings in the city, I can select at random 2 of the 10 and interview all of the residents of those 2 buildings.
7
Sampling Techniques Other techniques: Convenience sample
Researcher uses subjects that are convenient Not the most representative technique – researcher has to check how representative the sample would be before conducting the survey/gathering the data.
8
Types of studies Observational Experimental
Researcher merely observes what is happening or what has happened in the past and tries to draw conclusions based on these observations Researcher manipulates one of the variables and tries to determine how the manipulation influences other variables
9
Example 1: Article 1 Visit my teacher page and find the link for article 2 on Fighting racism: Teaching kids to identify individual black people can reduce racial bias. State whether this is an observational or experimental study
10
Example 2: Article 2 Visit my teacher page and find the link for article 2 on High Blood Pressure in Midlife Tied to Later Dementia. State whether this is an observational or experimental study
11
Example 3: Article 3 Visit my teacher page and find the link for article 2 on Brain stimulation can improve athletic performance. State whether this is an observational or experimental study
12
Experimental studies - variables
Independent Dependent Variable that is manipulated by the researcher Also called “explanatory variable” Variable that is affected by the variable that the researcher manipulates Also called “outcome variable” Confounding variable Variable that influences the dependent variable but was not separated from the independent variable
13
Experimental studies - groups
Treatment Group Control Group Group that received a specific treatment Group that receives no treatment Example: A researcher wants to see the effects of a certain weight loss drug. The researcher gives the pill to a group of 15 people and refrains from giving the pill to another 15 people. All 30 people are told to go on about their lives and not change anything about their diet or exercise regimen. Treatment group: ??? Control group: ???
14
Treatment vs Control 1 You are testing to see if a new plant fertilizer increases sunflower size. You put 20 plants of the same height and strain into a location where all the plants get the same amount of water and sunlight. One half of the get the regular fertilizer. The other half of the plants get the fertilizer you are testing.
15
Treatment vs control 2 You are testing to see if a new drug works for asthma. You divide 100 volunteers into two groups of 50. One group of 50 gets the drug. The other 50 people get a sugar pill (a placebo).
16
Treatment vs control 3 You want to prove that covering meat prevents maggots from hatching. You put meat into two different jars: one with a lid and one left open.
17
Misuses of Statistics What are some reasons for misusing statistics??
How could someone take advantage of statistical results?
18
Some ways statistics can be misrepresented…
Suspect Samples Ambiguous Averages “Average” Mean Median Mode Midrange These values can all be different, but a researcher can, without lying, select one of these values that lends most evidence to support their position. Small samples Volunteer samples Convenience samples
19
Ways statistics may be misrepresented…
Changing the Subject Detached Statistics Different values are used to represent the same data Example: 3% increase = $6,000,000 increase Statistics in which no comparisons are made. Example: These crackers have 1/3 less calories.
20
Ways Statistics may be misrepresented
Implied Connections Misleading Graphs Claiming a connection between variables that does not exist. Use “may”, “suggest”, “work for some” If graphs are drawn inappropriately, readers may draw false conclusions.
21
Ways statistics may be misrepresented…
Faulty Survey Questions Phrasing of questions may trick the person answering “always”, “never”, “only” “Do you think the high school should build a new football stadium?” vs. “Do you favor increasing school taxes so that the school can build a new football stadium?”
22
In Summary… Statistics, when used properly, can be beneficial in obtaining much information, but when used improperly, can lead to much misinformation. Like your car – If you use your car to get to school or go visit friends, that’s good. But if you use it to run over your neighbor’s dog because it barks all night, that’s not so good.
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.