Popular in Statistics 1350
verified elite notetaker
Popular in Department
This 4 page Study Guide was uploaded by Alyssa Leathers on Thursday February 19, 2015. The Study Guide belongs to Stats 1350 at Ohio State University taught by Ali Miller in Winter2015. Since its upload, it has received 318 views.
Reviews for SSStudyGuide#1.pdf
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 02/19/15
STATS Exam 1 Study Guide Chapter One Individuals objects described by a set of data subjectsparticipants Variables characteristics of individuals diff values for diff individuals 0 Quantitative in terms of numbers 0 Categorical words not numbers Populations set of all individuals that we want info about Samples a part of the population to gather data from cheaperfastereasier Observations studies Passive way to obtain information Surveys observational study quick cheap Experiments Impose some type of treatment medical Census Attempt to get info from every individual in population expensivetime consuming Chapter Two Bias some individuals are more likely to be chosen Convenience sampling sample individuals who are easily accessible fast cheap easy can t make much inference representatives Voluntary response sample individuals choose whether or not to be included easyfast cheap ethical most opinionated people bias Simple random sample SRS need an ordered list of population sampling frame select random number from list choose accordingly Chapter Three Statistics measurement of sample Parameters measurement of population Bias a consistent repeated deviation of the sample statistics from the population parameter in the same direction when we take many samples we want small bias Variability how spread out the values are when we take many samples determined by sampling design and sample size we want small variability Margin of Error helps to understand how close the estimate is to the truth the 95 confidence statement Confidence statements 1 square root of sample that from the percentage given We are 95 confident that between and H Chapter Four Sampling errors sample chosen from a set that is not the population not including all individuals as sample candidates cause simple statistics to be different from population parameters Nonsampling errors arise when data is obtained incorrectly bad measurement 0 Response error wrong information is obtained from individuals in the study 0 Nonresponse error data not obtained for individuals selected in sample Under coverage systematically excluding part of the population from consideration in the sample Wording of Questions questions with more information can give a big difference in results clear Biased Favoring one response over the other Stratified Random Samples divide population into groups subgroups with something in common strata do SRS of each group strata eliminates variability between groups Chapter Five Response variable dependent variable outcome that is measured depends on explanatory variable researcher has no control Explanatory variable independent variable variable that is controlled by researcher suspect it has in uenced the outcome Treatment specific combination of variables factors the individuals are exposed to Subjects use enough to reduce variability Placebo effect dummy treatmentquot with no active ingredients the response Lurking variables variable that affects the response but it is not being studied not the variable you re trying to study bad variability Cofounding when affects on a result can t be distinguished Doubleblind Control groups have no treatment Randomized comparative experiment Statistical Significance Principles of experimental design 0 Control lurking variables 0 Randomization randomly assign individuals to treatment groups 0 Using enough subjects to reduce variability Chapter Six Doubleblind experiments Completely randomized designs treatments groups individuals are all chosen completely randomly Block design participants are divided into blocks group of participants with something in common and then randomly assigned to treatment groups Matched pairs design technique for comparing two treatments of similar circumstances same person getting two treatments or randomly assign the order of the two treatments to similar individuals Chapter Eight Validity appropriately summarizes describes the variable in questions accurate measurement tool whether the instrument was the right choice Reliability measurement with small random variation no process is perfectly reliablequot how consistently the instrument measures Bias something being more likely under estimate over estimate Improving reliability by using the average Chapter Nine Do the numbers make sense The commercial claims usually don t actually make any sense Chapter Ten Distribution of a variable tells us what values it takes and how often it takes these values Categorical Variables individual into one of several groups words not numbers 0 Bar graphs 0 Pie Chart Quantitative Variables numerical value Line Graph time series plots measures change overtime general trend overall increase vs overall decrease patters Chapter Eleven Histograms similar to bar graph no space show distributionpeaks o 1 peakbump unimodal o 2 peaksbumps bimodal Outliers unusually large deviations from the overall pattern Symmetric no skew median mode Skewed median goes with the bump mean goes with tail 0 Left long tail on the left median gtmode 0 Right long tail on the right median lt mode Distributions o In terms of shape skewpeaks o In terms of center mean average mode most commonbiggest peak median middle n 12 gives the exact middle point 0 In terms of spread variability the range overall distance of the numbers standard deviation Chapter Twelve Median middle number n12 Quartiles Q1 25th percentile median 50th percentile Q3 75th percentile 5 number summary 0 Min Q1 Median Q3 Max Boxplots the 5 number summary visually make number scale first 0 Show symmetry vs skew 0 Show center and spread 0 Make comparisons among groups 0 Tell nothing about the size of the data set frequency of values 0 Don t show if the distribution is bimodal spikes Mean average Standard deviation the average distance of data values from the mean 0 Calculate mean 0 Calculate variance subtract mean from each number in set square them add them up take square root Choosing an appropriate summary mean standard deviation OR medianIQR Finding outliers find the IQR Q3Q1 low outlier Q115 x IQR high outlier Q315 x IQR
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'