Healthcare Statistics Final Exam Questions and Correct Solutions Rated A+

Observational study - observes individuals and measures variables of interest but does not attempt to influence the responses NO TREATMENT IMPOSED Comparative Observational Studies: - Case-Control Study - Cohort Study Case-Control Study - random sample of individuals with a condition (the cases) is compared with a random sample of individuals without the condition (the controls) retrospective approach: memories are not always accurate, bias may be a confounding variable historical-control: case-control studies that utilize existing data from previous studies to make their control group Cohort Study - subjects sharing a common demographic characteristic are enrolled and observed at regular intervals OVER AN EXTENDED PERIOD OF TIME *very powerful but also expensive and may not be adequate to study rare outcomes Experiment - deliberately imposes some treatment on individuals in order to observe their responses purpose is to study whether the treatment causes a change in the response Confounding - two variables (explanatory variables or lurking variables) are confounded when their effects on a response variable cannot be distinguished from each other Population - in a statistical study the entire group of individuals about which we want information Sample - part of the population from which we actually collect information use sample to draw conclusions about the entire population Sampling design - describes exactly how to choose a sample from the population Bias - the design of a statistical study is biased if it systematically favors certain outcomes Undercoverage - some groups in the population are left out of the process of being chosen in the sample eg. sample survey of households will miss not only homeless people but also prison inmates and students in dormitories, random digit dialing excludes people without landline phones Nonresponse - a selected individual cannot be contacted or refuses to cooperate Simple Random Sample (SRS) - of size n consists of n individuals from the population chosen in such a way that every set of n individuals has an equal chance to be the sample selected SHORT TERM UNPREDICTABLE LONG TERM PREDICTABLE INDIVIDUALLY UNPREDICTABLE COLLECTIVELY PREDICTABLE Random digits - long strand of digits 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 each entry in the table is equally likely to be any of the ten digits entries are independent of each other, knowledge of one part of the table gives no information on any other part LABEL, THEN TABLE Stratified Random Sample - sample important groups within the population separately eg. men and women, majority and minority groups Systematic Sample - sample members from a larger population are selected according to a RANDOM STARTING POINT AND A FIXED PERIODIC INTERVAL interval, called the sampling interval, is calculated by dividing the population size by the desired sample size Cluster/ Multistage Samples - involving choosing SRSs within SRSs eg. SRS of counties, SRS of schools within that county, the within each school an SRS of students *more practical than directly selecting an SRS of students from all over the US Subjects - individuals studied in an experiment Factors - explanatory variables in the experiment Treatment - any specific experimental condition applied to the subjects the conditions imposed on the participant during the trial (new drug, surgery technique, etc.) Experimental group - group of individuals receiving a treatment whose effect we seek to understand Control - treatment meant to serve as a baseline with which the experimental group is compared Placebo - control treatment that is fake but otherwise indistinguishable from the treatment in the experimental group eg. sugar pill Randomized Comparative Experiment - experiment that uses both comparison of two or more treatments and chance assignment to subjects to treatments Random Assignment --> Group #s --> Treatments --> Record Results 1. CONTROL: avoid lurking variables, compare 2 or more treatments 2. RANDOMIZE: impersonal chance to assign subjects to treatments 3. USE ENOUGH SUBJECTS: reduce chance variation in the results Statistically significant - observed effect so large that it would rarely occur by chance Ethics - must be the overarching principle guiding experimentation, does the end justify the means, be open to a continuing debate 1. Are all experiments acceptable in the name of science, knowledge, or public's greater good? 2. Is it morally right to include a placebo in a study design when there are safe and efficient treatments already available? 3. Should we stop an experiment if we find that one of the treatments shows early signs of adverse effects? And what if one of the treatments shows early signs of clear superiority? 4. Is it ever acceptable to leave subjects in the dark about the purpose and expected results of an experiment? 5. Should subjects be rewarded for participation? Tuskegee Syphilis Study - In the 1930s Public Health Service Tuskegee study recruited hundreds of poor black sharecroppers in order to observe how syphilis progressed when no treatment was given The subjects were not aware that they were participants in an experiment and were actively deceived about it for decades Beginning in 1943, penicillin became available to treat syphilis, the study subjects were still not treated until word leaked out and the study was forced to end in the 1970s Extreme example of investigators following their own interests and ignoring the well-being of their subjects UNETHICAL By law, all studies funded by the federal government must now obey the following principles: - The organization that carries out the study must have an INSTITUTIONAL REVIEW BOARD that reviews all planned studies in advance in order to protect the subjects from possible harm. All individuals who are subjects in a study must give their INFORMED CONSENT in writing before data are collected. Subjects must be informed about the nature of a study and any risk of harm it may bring. All INDIVIDUAL DATA must be kept CONFIDENTIAL. Only statistical summaries for group of subject may be made public. Any breach of confidentiality is a serious violation of data ethics. The best practice is to separate the identity of the subjects from the rest of the data at once. Clinical Trials - *must have control Treated v. Non-treated Most Elementary Clinical Trial: Random Allocation (Randomized) --> GROUP 1 (treated) GROUP 2 (untreated, control) --> Compare outcomes Random allocation of treatment to groups People 'choose' themselves (volunteer/recommended by doctor), have a condition eg. Type I Diabetes, will be able to decide difference between 2 groups