KIN 4310 1st Edition Lecture 3 Outline of Last Lecture I Excel Functions II Variability III Why Variability is Important IV Measures of Variability V Definition VI Definition VII Sample Standard Deviation Formula VIII Why n 1 IX Standard Deviation Important Properties X Things to Remember XI Computing Variance XII Standard Deviation or Variance XIII Excel Functions XIV Methodological Approaches XV Descriptive Studies XVI Correlation Studies XVII Experimental Studies Outline of Current Lecture I Example II Sample Selection III Sample Selection IV Methods of Sampling V Random Sampling VI Systematic Sampling VII Convenience Sampling VIII Stratified Sampling IX Cluster Sampling X Definitions XI Definitions XII Definitions Methodological Design XIII Definitions XIV Strategies to Avoid Confounding Current Lecture These notes represent a detailed interpretation of the professor s lecture GradeBuddy is best used as a supplement to your own notes not as a substitute I Example a The Effect of Increased Speed Limits i On Nov 28 1995 the National Highway System Designation Act was signed into law ii Abolished the federal mandate of 55 mph maximum speed limits on roads in the U S iii Of the 50 states plus DC 32 increased their speed limits during 1996 b This was an observational study because nothing was manipulated here the states chose on their own if they were going to increase their speed limits c From the data we cannot conclude that high speed limits increased fatalities because results may be from random noise d Experimental studies are the only ways to prove causation II Sample Selection a Samples should be selected randomly i Best method is random selection b Random selection corrects for systematic bias that may confound results i Eliminates bias this is why random selection is so good c Non random sample selection has to be accounted fro statistically i Can still use non random sample d Very common to have a convenience sample e All human samples are volunteer samples i Has to be a volunteer ii Ethical reasons III Sample Selection a Pick a card i Red King of Hearts 1 16 ii Black 7 of Clubs 1 15 iii Red Ace of Diamonds 1 48 iv Red 4 of Hearts 1 27 v Red 9 of Diamonds 1 17 b There was a lot of bias to pick the Ace because normally the ace is the best card in card games IV Methods of Sampling a Random b Systematic c d e f V Convenience Stratified Cluster Know these different types of sampling and what makes them good or faulty in certain situation TQ Random Sampling a Random Sample i Members of the population are selected in such a way that each individual member has an equal chance of being selected ii Computer generated program iii Draw straws iv Numbers out of a hat b Need a master list from the population to achieve this c A random sample is almost impossible to administrate but still good idea because it eliminated bias VI Systematic Sampling a Select some starting point and then select every Nth element in the population b Hard to put in order though c Almost truly random i Almost as good because people aren t coming in in any particular order d Involves order e Often used in clinical studies VII Convenience Sampling a Data or results that are easy to get b Take individuals that are closest to you c Total opposite of random selection VIII Stratified Sampling a Subdivide the population into at least two different subgroups then draw a sample from each subgroup or stratum b When you take entire population and divide them demographically gender age disease condition into strata c Then do random sampling within each strata IX Cluster Sampling a Divide the population into sections or clusters randomly select some of those clusters choose all members from selected clusters b Usually geographically c No one is left out d Randomly select clusters e In the state and county example they didn t want to travel all over the state so just chose 3 X XI Definitions TQ a Parameter i A numerical measurement describing some characteristic of a population b Statistic i A numerical measurement describing some characteristic of a sample 1 Ex mean standard deviation Definitions a Sampling Error i The difference between a statistic and the associated parameter such an error results from chance when it s a random sample ii Occurs naturally iii Any number off due to random chance iv The more people you select the more x bar and mu will be the same b Nonsampling Error i Sample data that are incorrectly collected recorded or analyzed such as by selecting a biased sample using defective instrument or recording the data incorrectly ii Not due to the sample but due to measurements XII Definitions Methodological Design these have to do with time frame of study a Cross Sectional Study i Data are observed measured and collected at one point in time ii Snap shot in time b Retrospective Study i Data are collected from the past by going back in time ii Looking back iii Data that s already been collected and study those numbers iv Ex chart reviews c Prospective of Longitudinal Study i Data are collected in the future from groups called cohorts sharing common factors ii Looking into the future iii Passage of time is very important element XIII Definitions a Confounding i Occurs in an experiment or observational study when the experimenter is not able to distinguish between the effects of different factors ii Try to plan an experiment to avoid confounding iii Ex people who carry lighters and cancer iv Smoking is a confound v The lighter doesn t cause cancer vi It is important to see possible confounders in an experiment XIV Strategies to Avoid Confounding a Blinding i Participant does not know whether he or she is receiving a treatment or placebo b Matching i Select participants with similar characteristics ii If you re selecting certain groups you match and make sure ages are the same and the number of men and women are similar c Randomized Controlled Trial i Randomly assign participants to each experimental group ii Gold standard of scientific research