# Biostatsmidtermstudyguide (1)

.docx
Mid-Term Exam Guide In addition to reviewing all content covered through week 3, the information below could guide you as you study for the mid-term exam. The information is not exhaustive of exam content nor is it meant to replace the scope of your study. However, it might help you organize your study, and it contains important knowledge that students are expected to gain from the last 3 weeks. Hierarchy of evidence and its application to EBP Understand how the description and importance of EBP Measure of central tendency Confidence interval Descriptive statistics : used to describe or depict data. Graphs, tables and charts, numerical measures such as central tendency and variability. Inferential Statistics: used to generalize results from a sample to a population through a hypothesis testing. Statistics: An empirical method for: collecting, organizing, summarizing, and presenting data. Making inferences about the population from which the data are drawn. Statistics helps us make rational decisions Sample Size: Determining sample size Factors that can effect the sample size Statistical procedure Type 1 error Confidence level Use of power Analysis: A piori power analysis Post hoc power analysis Hypothesis and hypothesis testing Hypothesis Testing - a process of making scientific decisions by determining if the likelihood of observed difference in a value, fall rates in our example, is not due to chance. Steps in Hypothesis Testing: 1. State the null and alternative hypothesis. 2. Choose the level of significance. 3. Propose an appropriate statistical test. 4. Check assumptions of the chosen test. 5. Compute the test statistics (find the p- value) 6. Find the critical value. 7. Compare the test statistics and critical value to make conclusions/ use the p-value to quantify evidence against the null hypothesis. Null- The hypothesis with no effect and denoted as Ho.
Alternative- the hypothesis that states an effect and denoted as H1. Level of significance- Predetermined criterion for measuring statistical significance. Common choices include 10% (.01), 5% (.05), 1% (.01) or 0.1% (.001). Inferential statistics Sampling methods, their advantages and disadvantages Random sampling- simple random systematic sampling Stratified random sampling: proportionate or disproportionate Cluster sampling Nonrandom Sampling Convenience sampling Volunteer sampling Quota sampling Snowball sampling Differences between population and sample: Population: Entire group of individuals a researcher wants to study. Uses parameters as numerical measure. Sample: subset of a population from which research draws conclusions used to understand the population. Uses statistics as numerical measure. Power analysis, its components and application Variability and measures of variability Sampling error Types of Variables : Qualitative variables: values that are nonnumeric. Example: SBP measured in categories such as high, normal, or low. Quantitative variables: Values that are numeric. Example: SBP measured in mmHg (e.g. 120 mmHg). Discrete variables: values that are countable but do not assume numeric value between countable categories Continuous variables: values that have every possible value on a continuum. Independent Variables: Variable that is either manipulated by the researcher or affects another variable Dependent variable: variable that is affected by an independent variable and becomes the outcome. Validity and reliability : Tool or instrument (device for measuring variables). Two important issues when a tool or instrument is used to measure variables: reliability- is a tool consistently measuring a variable of interest? Validity: Is a tool measuring what it is supposed to measure? Types of Reliability: Internal consistency: do items within a tool measure the same thing?
Test-retest reliability: are the results of the measurement consistent from one time to another time? Interrelater Reliability: is there consistency between individuals' scores on ratings? Types of Validity: Content Validity: whether a measurement tool measures all aspects of a construct of interest Criterion-related validity: how well a tool is related to a particular criterion. Construct validity: extent to which scores of a measurement tool are correlated with a construct we wish to measure. Internal validity: whether there is any uncontrolled or confounding variable that may influence the end result of a study External validity: whether the results of a study can be generalized beyond the study itself. Levels of measurements/ Characteristics Nominal: Mutually exclusive categories. No ranking or ordering imposed on categories. Examples: gender, ethnicity, religious affiliation, political party membership, hair color. Ordinal: same as above plus ranking or ordering. Mutually exclusive categories. Ranking or ordering imposed on categories. Examples: Age, letter grade, Likert type scale, ranking in a race (1 st , 2 nd , 3 rd ), histological ratings. Interval: same as above plus assigned meanings between categories. Mutually exclusive categories with rankings. Specific meanings applied to the distances between categories. No absolute zero. Camparison can be made in ratio. Example: temp. Standardized tests such as IQ, SAT, ACT, TOEFL. Ratio: same as above jplus meaningful zero and ratio or equal proportion. Characteristicsof interval level of measurement. Also an absolute zero. Comparison can be made in ratio. Examples: age, height, weight, income. Understand basic meaning of SPSS and its purpose Grouping Data: Frequency Distribution: Displays possible values and corresponding frequencies Provides summative data Can be either ungrouped or grouped. Ungrouped: suitable for categorical measurements, nominal or ordinal, and continuous measurements with a small range of data values. Grouped: suitable for continuous measurements with a large range of data values. Inserting- Excel: insert tab> Recommended PivotTables. SPSS: Analyze > descriptive statistics > frequencies. Displaying/organizing data: bar chart, histogram, scatter plot, box plot, pie chart. o Presentation of the data affects audience understanding o Factors to consider: the amount of data to describe, the level of measurement, audience characteristics. o Is the data categorical or continuous? Categorical: bar chart, pie chart or line chart. Continuous: histogram, stem and leaf plot, boxplot, or scatterplot (2 variables).