2 Individuals vs. Variables People or objects included in the studyCharacteristic of the individual to be measured or observed
3 Quantitative vs. Qualitative Quantitative VariablesQualitative VariablesHave value or numerical measurement for which operations such as addition or averaging make senseDescribes an individual by placing the individual into a category or group, such as male or female
4 Population vs. Sample Population Data Sample Data Data is from every individual of interestPopulation Parameters are numerical measures that describe an aspect of a populationThe data are from only some of the individuals of interestSample Statistics are numerical measures that describe an aspect of a sample
5 Levels of Measurement Nominal – Names, Labels, Categories Ordinal – Arranged in meaningful mathematical orderInterval – Differences are meaningfulRatio – Division or percentage comparisons make sense; zero point
8 Simple Random Sample (SRS) A simple random sample of n measurements from a population is a subset of the population selected in such a manner that every sample of size n from the population has an equal chance of being selected.
9 Random Number Tables (RNT) Used to help secure a SRSSteps:Number all members of the population sequentially.Drop a pin on the RNT to pick a starting pointPull digits n at a time, discarding non-used numbersRepetition?
10 Do NowWith a partner, discuss how a Random Number Table or Random Number Generator could be used to generate the answer key for a multiple choice test (assume 10 questions on quiz and 5 choices per question).Rephrased: How can a RNT or RNG be used to determine next to which letter the correct answer to each question should be placed?
11 Other Methods to Secure a Sample SystematicStratifiedClusterMultistageConvenience
12 Systematic Sampling Population is numbered Select a starting point at random and pick every kth member
13 Convenience SamplingCreate sample by selecting population members which are easily available
14 Stratified SamplingDivide population into distinct subgroups based on specific characteristicsDraw random samples from each strata
15 Cluster SamplingDivide population into pre-existing segments or clusters (often geographic).Make a random selection of clusters.All members of cluster are chosen.
16 Multistage SamplingUse a variety of sampling methods to create successively smaller groups at each stage.Final sample is made of clusters.
17 Do NowCopy the Blue Box from page 21 into your notebooks. This is the beginning of Section 1.3 “Introduction to Experimental Design”
18 Census vs. SampleCensus – measurements from observations from the entire population are used.Sample – measurements from observations from part of the population are used
19 Observational Study vs. Experiment Observational Study – observations and measurements of individuals are conducted in a way that doesn’t change the response or the variable being measuredExperiment – a treatment is deliberately imposed on the individuals in order to observe a possible change in the response or variable being measured
20 Within Experiments:Placebo Effect – occurs when a subject receives no treatment but (incorrectly) believes he or she is in fact receiving treatment and responds favorablyControl Group – those who receive the placebo treatmentTreatment Group – those who receive the actual treatmentCompletely Randomized Experiment – one in which a random process is used to assign each individual to one of the treatments
21 Completely Randomized Experiment C.R.E. – is one in which a random process is used to assign each individual to one of the treatments
22 Characteristics of a Well-Designed Experiment Block – a group of individuals sharing some common features that might affect the treatmentRandomized Block Experiment – individuals are first sorted into blocks, and then a random process is used to assign each individual in the block to one of the treatments
23 Characteristics of a Well-Designed Experiment Control Groups – used to account for the influence of other known or unknown variables that might be an underlying cause of change in response in the experimental group.Lurking or Confounding Variables – such variables
24 Characteristics of a Well-Designed Experiment Randomization – used to assign individuals to the two treatment groups. Helps to prevent bias in selecting members to the groupsReplication – on many patients reduces the possibility that the differences in occurred by chance alone.
25 Potential Pitfalls of Surveys NonresponseTruthfulness of ResponseFaulty RecallHidden BiasVague WordingInterview InfluenceVoluntary Response
26 Data Collection Techniques (Summary) CensusSamplesExperimentsObservational StudiesSurveysSimulations (previously)