biostats exam 2 part 1

1. what does descriptive statistics estimate? 

1. parameters from a population or sample

2. only the specific data you collected

1. how do we make sure estimated parameters for a population are useful?

1. quantify their accuracy

1. what are the four parts of the central limit theorem? 

1. the sampling distribution will be less spread than the values in the population from which the sample is drawn

2. the sampling distribution will be well modeled by a Gaussian (normal) distribution

3. the spread of the sampling distribution is related to the spread of the population values

4. bigger samples lead to a smaller spread (more precision) in the sampling distribution

what is the central limit theorem?

distribution of sample means approaches a normal distribution as the same size increases

regardless of the shape of the original population’s distribution

1. what does the central limit theorem state about the sampling distribution? 

1. less spread than the values in the population from which the sample is from

2. well modeled by a Gaussian (normal) distribution

3. related to the spread of the population values

1. what does the central limit theorem state about bigger samples? 

1. bigger samples lead to a smaller spread (and more precision) in the sampling distribution

1. what is the standard error? 

1. standard deviation of the sampling distribution

1. what does the standard error measure? 

1. measures accuracy or margin of error (how well you know the true population parameter

1. what does smaller / larger standard deviation mean for the error? what does this mean for precision? 

1. smaller SD = smaller error → more precise

2. larger SD = larger error → less precise

1. error declines with ____________ sample size

increasing

1. what is the confidence interval? 

1. range of values calculated from a sample that is likely to contain the true value of the population parameter

1. what does it mean if you have a 95% confidence interval? 

if you did the study 100 times, ~95 of the ranges provided will contain the true population parameter

1. confidence interval is an interval around what? 

1. around the mean

1. how does standard deviation relate to the confidence interval? 

1. larger SD = wider CI = less confidence

1. how does sample size relate to the confidence interval? 

1. larger sample size = smaller CI = more confidence

1. corresponding z values for 68%, 95%, and 99% confidence: 

1. 1.00, 1.96, 2.58

1. narrow (ex. 80%) vs. broader (ex. 95%) confidence ranges

1. narrow ranges are more informative than broad ranges → but also riskier

2. broader ranges means more confidence on the estimate

1. values falling outside the _____ CI interval are less plausible

1. 95%

1. when do we need to be extra cautious / more confident in studies? 

1. life-threatening studies

2. some examples: 

   1. aggressive new chemotherapy with severe side effects

   2. vaccine safety and efficacy

   3. high-risk surgical techniques

   4. autonomous vehicle breaking systems

   5. nuclear power plant safety

   6. tsunami buoy warning networks

1. what does lowering the confidence interval mean for the chance of a false positive? 

1. lowering confidence interval → increases the chances of a false positive 

1. what do error bars illustrate? 

1. standard errors or confidence intervals

2. figure legends MUST TELL what kind of information the error bars are displaying

1. what do error bars indicate about a population parameter? what do they not indicate? 

1. uncertainty about the population parameter

2. not variability in the data

1. what is the definition of probability? 

1. proportion of times the event would occur if we repeated a random trial repeatedly multiple times under the same conditions

1. what is probability used for? 

1. to connect sample estimates to population parameters