Download Module 3 CNSL 503 Exam Questions and Answers and more Exams Nursing in PDF only on Docsity!
Module 3 CNSL 503
Statistic a numerical value that is generated from the individual scores in the dataset of a sample. Parameter a numerical value generated from the individual scores in the dataset of the entire population. representative sample composed of members that generally possess the same characteristics as those of the population. If a sample is not representative of the population, then it is said to be biased. Biased if a sample is not representative of the population What is the goal of sampling? to gather data that can be used to make predictions or generalizations about a population
Random sampling in which every member of the population has an equal chance of being selected, increases the reliability of the study results. What are 5 sampling techniques? Simple Random sampling Stratified sampling cluster sampling systematic sampling convenience sampling simple random sampling occurs when each individual in the population of size has an equal chance of being selected for the sample. If you have ever written individual names on separate pieces of paper, placed all the pieces of paper in a hat, and selected names from the hat, you have conducted simple random sampling. Stratified sampling
sampling error Though samples provide valuable insights about populations, the sample statistics will deviate somewhat from population parameters. This is the nature of random sampling. Any deviation between a statistic and a parameter How to reduce sampling error?
- larger sample size greater that 30 -use stratified sampling non-sampling errors sample bias; occurs when the researcher has a mistake in the data collection or measurement process. What are 3 non-sampling errors? measurement bias response bias selection bias measurement bias result from poorly worded or misleading questions on a survey or even technical errors in a computer survey.
response bias when participants respond to surveys with inaccurate, untruthful, or exaggerated responses. Selection bias occurs if those who respond or participate in a study are not a truly representative sample of the population. sampling distribution a frequency distribution of each statistic from every possible sample of a given size η from the population. Distribution of sample means the most common sampling statistic represented in a sampling distribution. It is the frequency distribution of each mean from all possible samples of a given size (η) from a population. As the number of samples ________ toward infinity, the sample mean approaches the __________. increase; population mean (thus making them equal) central limit theorem
event defined as one or more outcomes that share a common aspect. What is the formula for probability?
of outcomes in A/ total # of possible outcomes
relative frequency method which involves performing numerous observations of a given situation and recording the number of times the event occurs. A frequency distribution graph can be used to display the distribution of scores Statistically significant if a sample statistic deviates greatly from population parameters to a degree that seems to be beyond chance, then this deviation (p<0.05) hypothesis testing the formal process by which researchers sample data in order to make inferences about a population. Statistical hypothesis a claim made about a population parameter.
What is hypothesis testing? the process by which the claim is tested using a carefully selected sampling method, gathering data, calculating statistical values and probability values, and drawing a conclusion. What are the 4 steps of hypothesis testing?
- state the null (H0) and the alternative (Ha) hypotheses.
- Establish the criteria for deciding whether to reject or fail to reject a null hypothesis. This involves setting a probability value for the hypothesis test 3.Collect the data and compute sample statistics.
- Decide whether to reject the null hypothesis or fail to reject the null hypothesis null hypothesis (H0) is the beginning assumption of any hypothesis test. It states that the treatment or independent variable had no effect, made no difference, or caused no change in the unknown population parameter. Alternative hypothesis (Ha) states that the treatment does cause a change or difference in the population parameter. If the mean exam score for Group 1 is greater than the mean exam score for Group 2, then the researcher's study may support the claim that the new study strategy does increase memory retention when compared to traditional strategies.
type II error (false negative) Type I error false positive; occur when the researcher rejects H0 (the null hypothesis) when it is actually true. To reduce the chance of a Type I error, researchers must set an appropriate alpha level. In fact, the chance of a Type I error equals the alpha level of the study. Type II error false negative; H0 is not rejected and it is not true. Significance level The criterion for deciding whether the ρ-value is "small enough" to reject the null hypothesis critical values or cutoff values, serve as the boundaries for the critical regions. If the test statistic lies in the critical region (region of low probability), then there is reason to reject the null hypothesis. The critical value depends on the alpha level used in the study. Generally, if a test statistic is greater than the critical value at the given alpha level, then it can be considered statistically significant.
What are problems with hypothesis testing? alpha level is arbitrary the larger the sample size the more likely to be statistically significant too much reliance of the p-value as the sole measure upon which conclusion are made misinterpretation of the p-value and the results of hypothesis testing bias towards publishing statistically significant results
