final study guide

• hypothesis


  a testable claim or statement that is the foundation of any research study
• null hypothesis


  - assumes no change or effect

  - solution is equal (no change) to the expected value
• alternative hypothesis


  - suggest that something is, will, or has changed

  - the solution is greater the expected value
• symbolic representation of hypotheses


  claims can be represented by using equations
• type 1 error


  - occurs when a true null hypothesis is rejected (false positive)

  - you state something has changed when it did not

  - this refers to as alpha (the chance of making these type of error)

  - example: calling someone guilty when they are innocent
• type 2 error


  - is the failure to reject a false null hypothesis

  - you state something did not change, but it

  - beta is the calculated likelihood of creating this error

  - example: calling something innocent when they are guilty
• interplay between study design and hypothesis

  - the design of a study should be guided by the hypothesis
• formulating a research topic and hypothesis

  A research topic and hypothesis should be clear, specific, and testable
• operational definition in defining variable


  operational definition specify how variables are measured or identified in a study
• cross-sectional studies


  - description:collect data at a single point in time from a sample of individuals- limitations:cannot establish causality; only shows association at one time point, susceptible to prevalence-incidence bias
• case-control studies


  -description:compare individuals with a specific condition (cases) to those without controls to identify factors that may contribute to the condition- limitations:prone to recall bias, selection bias, and cannot provide direct risk estimates or establish a temporal sequence of exposure and outcome
• cohort studies - longitudinal studies

  - description:follow a group of individuals over time to see who develops the outcome of interest, comparing exposure groups- limitations:time-consuming, expensive, and can be affected by loss to follow-up and changes over time that might influence the outcome
• randomized controlled trial (RCTs)


  - description:participants are randomly assigned to experimental or control groups to test the efficacy of intervention- limitations:expensive, ethical concerns with control treatment, may have limited generalizability due to strict inclusion criteria
• systematic reviews and meta-analyses

  - description:synthesize findings from multiple studies on a topic, often including a quantitative pooling of a data in meta-analyses- limitations:can be limited by the quality and heterogeneity of included studies; potential publication bias
• pre-experimental designs


  - description:involve intervention without random assignment, such as case studies or single-group, before-and-after studies- limitations:lack of control groups and randomization, leading to higher susceptibility to con-founding variable, making it difficult to attribute to outcomes directly to the intervention
• quasi-experimental design


  - description:resemble experimental research but lack random assignment to treatment or control, they often use natural experiments or non-randomized group- limitation:potential selection bias and confounding variable are more difficult to control, which can affect the validity of causal inference
• types of distribution


  - normal distribution

  - pareto distribution
• normal distribution is...


  bell shaped
• Pareto distribution is...


  skewed
• bias in statistic


  bias is a systematic error that skews data
• confounding variables


  an external variable that correlates with both the dependent and independent variables
• discrete variables


  variables that can only take certain values
• continuous variables


  variables that can take any value within a range
• independent variable


  variable that is manipulates by the researcher
• dependent variable


  The outcome factor; the variable that may change in response to manipulations of the independent variable.
• creating a research study title

  the title should clearly indicate the independent, dependent variable, and the population being studied
• scales of measurement


  - nominal scale categorizes data

  - ordinal scale ranks data

  - interval scale measures the distance between data points

  - ration scale does the same as interval scale but also has a true zero
• simple random sampling


  - use of a random numbers table

  - randomly pick a number and travel in any direction to get remaining number

  - computer generates random numbers (ex. lotto pick)
• systematic sampling


  - another method of sampling form the population with a defines sample size number

  - define the kth item (k= population size/sample size)
• stratified random sampling


  - population is too large

  - divide the population into "strata" (ex. size or colour)

  - randomly select from each strata

  - proportionally select the number
• cluster sampling


  - divided population into cluster not on specific numbers or group

  - randomly select the cluster to be used
• continuous data


  - refers to numerical data that can take on any value within a range

  - it represents measurements and can have infinitely many values, meaning it can include fractions and decimals

  - often used to represent quantities that are measured, such as time, temp, or distance, where the exact value can vary along a continuum
• discreta data


  - refers to numerical data that can only take specific, distinct values

  - it represents countable items and does not not allow for fractions or decimals between these values

  - often used to count occurrences or categories such as the number of students in a class, the number of cars or the result of a dice roll
• saturation


  often used to determine sample size
• nominal scale


  - a scale in which objects or individuals are assigned to categories that have no numerical properties

  - categories according to criterion

  - discrete variables

  - numbers can represent the label of a category (elephant=3)
• ordinal scale


  - A scale in which objects or individuals are categorized, and the categories form a rank order along a continuum

  - discrete variable

  - ex. ranking students based on time running 100 meters - ranking fastest to slowest

  - distance between values is not important or equal

  - orders the position within a distribution is important
• interval scale


  - a scale in which the units of measurements (interval) between the numbers on the scale are equal in size BUT there is no absolute zero or true zero (numbers can be decimals, positive, or negative)

  - has direction and magnitude, and equal distance between values

  - continuous variable
• ratio scale


  - a scale that has magnitude, direction and equal measurement

  - there is an absolute zero that indicates an absense of the variable

  - continuous variable
• concept and purpose of sampling


  - involves selecting a subset of the population for study to make inferences about the whole population
• stages of sampling


  - define the population

  - specify a sampling procedure and method

  - determine the sample size

  - implement the sampling plan