Vocabulary List - Lecture notes 1-15 - Introduction to Statistics and Probability PDF

Preview

Summary

Vocabulary Sheet...

Description

1

Vocabulary List Individuals: a single human being as distinct from a group, class, or family. We are all unique individuals. Variables: an element, feature, or factor that is liable to vary or change. Content of the variables can change. Observational study: a type of study in which individuals are observed or certain outcomes are measured. No attempt is made to affect the outcome (for example, no treatment is given). The IMPROVE study is the largest ever global observational study in diabetes. Sample surveys: a survey which is carried out using a sampling method. Sample survey is an important way to find statistics. Sample vs Population: The population is the whole set of values or individuals, you are interested in. The sample is a subset of the population and is the set of values you actually use in your estimation. Census: an official count or survey of a population, typically recording various details of individuals. According to the latest census, our population has increased. Experiment: a scientific test which is done in order to discover what happens to something in particular conditions. This question can be answered only by experiment.

2

Convenience sample: one of the main types of non-probability sampling methods. A convenience sample is made up of people who are easy to reach. Using a one-group, pre-post test design, a convenience sample of 16 community-dwelling female seniors was recruited. Voluntary response sample: a sample made up of volunteers. Compared to a random sample, these types of samples are always biased. For example, people who call in to a radio show poll may have strong opinions about a topic in either direction. Bias: a tendency to prefer one person or thing to another, and to favor that person or thing. Bias against women permeates every level of the judicial system. Simple random sample: a subset of individuals (a sample) chosen from a larger set (a population). In a simple random sampling, the sample mean is an unbiased estimate of the population mean. Table of random digits: a listing of the numbers 0, 1, 2, 3, 4, 5, 6, 7, 8, 9. If we use Table B of random digits to select random samples, which of the following are true, and which are false? Statistic vs Parameter: Parameters are numbers that summarize data for an entire population. Statistics are numbers that summarize data from a sample. Variability: gives you a way to describe how much data sets vary and allows you to use statistics to compare your data to other sets of data.

3

There's a great deal of variability between individuals. Confidence statement: gives an estimated range of values which is likely to include an unknown population parameter e.g. the mean, the estimated range being calculated from a collected sample of data. Margin of error: an amount (usually small) that is allowed for in case of miscalculation or change of circumstances. 1/√n The poll did not include a margin of error. 95% confidence: Random sampling error: the error caused by observing a sample instead of the whole population. The analysis for random sampling error and the number of samples. Undercoverage: some members of a population have zero chance of being included in the survey or experiment. Sampling frame: a list of the items or people forming a population from which a sample is taken. Sampling Frame for the Survey of Enterprises under Quota Limits. Nonsampling error: a catch-all term for the deviations of estimates from their true values that are not a function of the sample chosen, including various systematic errors and random errors that are not due to sampling.

4

There are many factors that affect the occurrence and the degree of sampling and nonsampling error. Nonresponse: the bias that results when respondents differ in meaningful ways from nonrespondents. Nonresponse is often problem with mail surveys, where the response rate can be very low. The number of call back attempts is an important determinant of response rates and nonresponse error. Processing errors: the error in final survey results arising from the faulty implementation of correctly planned implementation methods. This approach reduces the uncertainty of measurement, reducing data processing errors, so it is widely used. Response errors: any error introduced into the survey results due to respondents providing untrue or incorrect information. It is a type of systemic bias. Stratified sample: a sample that is drawn from a number of separate strata of the population, rather than at random from the whole population, in order that it should be representative. Explanatory variable: a type of independent variable. When a variable is independent, it is not affected at all by any other variables. When a variable isn’t independent for certain, it’s an explanatory variable. Response variable: the focus of a question in a study or experiment. Confounding: a variable that is correlated (directly or inversely) to both the dependent variable and independent variable.

5

Analyses were adjusted for confounding variables using logistic regression. Lurking variables: A variable that correlates with the independent variable and the dependent variable in a statistical model. Lurking variables must be accounted for in statistical experiments, so that they do not generate false positives or otherwise generate non-meaningful results. Also called confounding variables. Randomized comparative experiment: an experiment that compares the effect of two or more treatments and also randomly assigns subjects to the different treatments. Controls: take into account (an extraneous factor that might affect results) when performing an experiment. No attempt was made to control for variations Placebo effect: a beneficial effect, produced by a placebo drug or treatment, that cannot be attributed to the properties of the placebo itself, and must therefore be due to the patient's belief in that treatment. The placebo effect refers to all the observable behaviors caused by placebo. Statistically significant: the likelihood that a relationship between two or more variables is caused by something other than random chance. The difference was not large but it was statistically significant. Matching: a statistical technique which is used to evaluate the effect of a treatment by comparing the treated and the non-treated units in an observational study or quasi-experiment (i.e. when the treatment is not randomly assigned). Statistical adjustment: an observed effect of a size that would rarely occur by chance.

6

Statistical adjustment of treatment effect for covariates in clinical trials. Clinical trial: research studies that explore whether a medical strategy, treatment, or device is safe and effective for humans. Two rival laser surgery systems are undergoing clinical trials in the US. Double-blind: denoting a test or trial, especially of a drug, in which any information that may influence the behavior of the tester or the subject is withheld until after the test. In a double-blind trial, there were definite improvements. Completely randomized design: A method for designing experiments that uses random combinations of factors to rule out the effect on the results from nuisance variables, or variables that are not relevant to the problem being solved. To treat the data of completely randomized design. Matched pairs design: a type of randomized block design that has two treatment conditions and pairs subjects based on common variables, such as age, grades, health level, or sex. Block design: the experimenter divides subjects into subgroups called blocks, such that the variability within blocks is less than the variability between blocks. Then, subjects within each block are randomly assigned to treatment conditions. Institutional review board: an independent committee established to review and approve research involving human subjects. The primary purpose of the IRB is to protect the rights and welfare of the human subjects. Informed consent is an important component. The study was approved by our institutional review board and written informed consent was obtained from all subjects.

7

Informed consent: permission granted in the knowledge of the possible consequences, typically that which is given by a patient to a doctor for treatment with full knowledge of the possible risks and benefits. Informed consent should not be a mere contract for research participants to sign. Confidentiality: the state of keeping or being kept secret or private. Data recovery and confidentiality problems. Anonymity: the condition of being anonymous. Most people who agreed to talk requested anonymity. Units of measurement: a definite magnitude of a quantity, defined and adopted by convention or by law, that is used as a standard for measurement of the same quantity. The units of measurement used in this book are internationally standard measurement units. Valid measurement: an indication that does not mislead the observer. Rates vs counts: Counts, also called frequencies, are fairly straightforward. Counts are the total number of events that occur in a defined period of time. Rates are the number of events that occur in a defined period of time, divided by the average population at risk of that event. Random measurement error: Random measurement error in visual acuity measurement in clinical settings. Inconsistencies: the fact or state of being inconsistent. We were asked to investigate the alleged inconsistencies in his evidence.

8

Hidden agenda: a secret or ulterior motive for something. He accused the government of having a hidden agenda. Categorical vs Quantitative: Quantitative variables are numerical variables: counts, percents, or numbers. Categorical variables are descriptions of groups or things, like “breeds of dog” or “voting preference”. Distribution: the action of sharing something out among a number of recipients. He admitted there had been distribution problems. Pie chart vs Bar graph: Pie charts are best to use when you are trying to compare parts of a whole. They do not show changes over time. Bar graphs are used to compare things between different groups or to track changes over time. However, when trying to measure change over time, bar graphs are best when the changes are larger. Line graph: a type of chart which displays information as a series of data points called 'markers' connected by straight line segments. It is a basic type of chart common in many fields....