Module 5 Flashcards
descriptive statistics
- to describe data
- they are statistical procedures which are used to organize, summarize, and simplify data
inferential statistics
- to make inferences
-enables us to generalize or male inferences from a sample of data to a larger group of subjects or a population - allows us to go beyond the data to generalize to the larger population
what are the two broad areas of statistical inferences?
- estimation of population parameters
- hypothesis testing
what is estimation of population parameters
used to estimate population parameters such as means and proportions
what is hypothesis testing?
-used to examine data to see if there is..
- a relationship between variables
- a difference between groups
**hypothesis is an idea that can be tested
describing a population with a population mean, it is a _____
parameter
describing the sample with a sample mean, it is a ___
statistic
important concepts for inferential statistics (7)
- sampling
- sample size
- confidence intervals
- probability
- statistical significance
- hypothesis testing
- level of significance
what is population?
- the group of interest…the group that you want to generalize to
- you can never know a true pop value, only estimate in parameters. Do not report parameters
what is sample?
- a subset of the population of interest
- used to study a health-state of interest and then use the information to make inferences about the larger population
-sample describe using sample statistics, estimate the pop parameters, when reporting results always report sample stats
sampling method
- process researchers use to select subjects from the population being studied
*never assume that a random sampling method was used
what are two types of samples?
- probability
- nonprobability
probability sampling
= random sampling
- every member of the population has a chance of being selected
- the probability of being selected can be calculated
what are probability sampling method? (3)
- simple random sampling
- stratified random sampling
- cluster sampling
types of probability samples: simple random sample
- enumerate all members of population
- select the desired number of individuals at random
- each individual has same probability of being selected
types of probability samples: stratified sample
- organize population into mutually exclusive strata
- select individuals at random within each stratum
- used when the population is naturally divided into subpopulation
types of probability samples: cluster sample
- sample clusters or groups instead of individuals
-examples might be schools, clinics, neighborhoods - selection process is still random
what are nonprobability sampling?
- the members of the population of interest do not have the same opportunity (equal chance) for selection into the study group (s)
- used when the researchers cannot use a random sampling method
types of Nonprobability samples: convenience sample
-non probability sample (not for inference)
- literally a sample of convenience (individuals at the right place at the right time)
types of Nonprobability samples: quota sample
- select a pre-determined number of individuals into sample from groups of interest
- participants are not randomly selected
sampling error
- difference between the sample and the population
- always present in every sample
- researchers always attempt to minimize the sampling error
sources of error in estimating parameters
-sample error:
- a sample may not accurately represent the population
- random selection from a population is the ideal nut there is still always some sampling error
- measurement error: accuracy of the measurements
- random error: noise
sample size
- sample size is always important
- small sample size may not adequately represent the larger populations
- too small of a sample can lead to erroneous conclusions
**as the sample size increases, the error between the sample mean and the population mean should decrease
what are two ways to make estimates?
- could make your estimates using a single value
- use a range of values
point estimate
- a point estimate for a population parameter is the best single number estimate of that parameter
- has the advantage of being very precise
confidence interval
a range values for the estimated population parameter with a level of confidence attached
-also known as interval estimates –> does not have the accuracy that point estimate has, but the interval estimate gives you more confidence
statistical (null) hypothesis
- starts with the assumption that there is no difference or no association between the groups or variables
what does it mean if p-value is ≥ .05?
that means that there is NOT a statistical relationship
what does it mean if p-value is <.05?
that means that there is a statistical relationship
type 1 error
- the p-value is statistically significant (<0.05)
- the researcher rejects the null hypothesis and accepts the alternative (research) hypothesis
this means that the null hypothesis was incorrectly rejected and the research hypothesis is incorrectly accepted which means that the researcher concluded that there was a difference between treatment groups or as association between variables when there was none
type 2 error
- the p-value is not statistically significant (≥0.05)
- the researcher does not reject the null hypothesis
this means that the null hypothesis was not rejected which mean that the researcher incorrectly conclbuded that there was not a difference between treatment groups or an association between variables when there really was one
**too small of a sample size can lead to type 2 error
