IMPORTANCE OF STATISTICS MR.CHITHRAVEL.V ASST.PROFESSOR ACN

Importance of Statistics in Nursing Research  Researchers link the statistical analyses they choose with the research question, design, and level of data collected.  Allows us to critically analyze the results.  Provide organization and meaning to data.

Where Do You Find Them?  Methods section will contain the planned statistical analysis.  Results section will provide the data generated from testing the hypothesis or research questions.  Data is the analysis using descriptive and inferential statistics.

Levels of Measurement  Measurement is the process of assigning numbers to variables.  For example: Males and females in a study. Males would be assigned as 1 and females assigned as 2.  Every variable in research study that is assigned a specific number must be similar to every other variable assigned that number.

Levels of Measurement  Nominal- aka categorical, naming or classifying. Either does or does not have the characteristic.  Lowest level of measurement and allows for the least amount of statistical information.  Examples- gender, marital status, religious affiliation.  Can you think of one?

Ordinal  Used to show relative rankings of variables or events.  Ranks in order from high to low, but does not indicate how much higher or how much lower.  Intervals are not necessarily equal and there is no absolute zero.  Limited in the amount of mathematical manipulation possible.  Examples- class rank, levels of wellness, levels of height.

Interval  Shows rankings of events or variables on a scale with equal intervals between.  Zero point remains arbitrary and not absolute.  Allows for more mathematical manipulation of data.  Examples- test scores and temperature on a Fahrenheit scale.

Ratio  Shows rankings of events or variables on scales with equal interval and absolute zero.  Most often used in physical sciences.  Highest level of measurement, allows for most manipulation of data.  Number represents the actual amount of the property the object possesses.  Example- height, weight, pulse and BP.

Descriptive Statistics  Procedures that allow researchers to describe and summarize data you definitely know (describes the sample).  Examples: Demographics, clinical data.  Frequency distribution is one way to display data.

Descriptive Statistics Measures of central tendency are used to describe the pattern of responses among a sample.  Mean- most frequently used average, add up numbers (sum) and then divide by the #. Defined as a balance point in a distribution of scores.  Median-50% are above and 50% are below the score. Defined as the middle point in a distribution. Insensitive to extreme scores.  Mode-Most frequently occurring score. May have more than one mode.

Normal Distribution  Most important curve (Bell-shaped).  Most often found in nature and used as the basis for a number of inferential statistics.  Mean, median and mode are equal.

Measure of Variability  Concerned with the spread of data.  Range- the difference between the highest and lowest score.  Semiinterquartile range- indicates the range of the middle 50% of the scores.  Standard Deviation-most stable and most useful, provides an overall measurement of how much participants scores differ from the mean of the group.  Z score-used to compare different measurements, scores are converted to Z scores and them compared.

Inferential Statistics  Data collection procedures that allow researchers to estimate how reliably they can make predictions and generalize findings.  Allows us to compare groups and test hypothesis.  Answer research question in a study.

Inferential Statistics  Parameter- a characteristic of a population.  Statistic- characteristic of a sample.  Not possible to study the whole population so we study a sample and make predictions or statements related to our findings.

Inferential Statistics  2 important qualifications must be conducted to use inferential statistics.  Sample must be representative (drawn with probability, some form of random selection).  Scale used must be either interval or ratio level of measurement.  If nonprobability sampling occurs techniques such as power analysis are used to compensate for this.

Inferential Statistics  Researchers are able to make objective decisions about the outcome of their study by using statistical hypothesis testing.  Scientific hypothesis is what the researcher believes will be the outcome of the study.  Null hypothesis is what can actually be tested by the statistical methods.  Inferential stats use the null hypothesis to test the validity of a scientific hypothesis.

Inferential Statistics  Probability- the notion that in a repeated trial/study under the same conditions we would get the same results.  Statistical probability is based on sampling error. The tendency for stastics to fluctuate from one sample to another is known as sampling error.

Type I and Type II Errors  2 types of errors in statistical inference.  Type I- researcher rejects a null hypothesis when it is actually true.  Type II- researcher accepts a null hypothesis that is actually false.  Type I errors are considered more serious because if a researcher declares that differences exist when none are present the potential exists for patient care to be adversely affected.  Type II errors occur when sample is too small.

Level of Significance  The probability of making a type I error.  Minimum accepted level for nursing research is  “ If I conduct this study 100 times, the decision to reject the null hypothesis would be wrong 5 times out of 100”

LOS  If wanting to assume smaller risk level will be set at  Meaning researcher is willing to be wrong only once in 100 trials.  Decision to use alpha level 0.05 or 0.01 depends of the study significance.  Decreasing the risk of making a type I error increases the risk of making a type II error.

Parametric and Nonparametric Statistics are used to determine significance.  Parametric have 3 attributes: 1.Estimation of at least one population parameter. 2.Require measurement on at least an interval scale. 3.Involve certain assumptions about the variables being studied.  Variable is normally distributed in the overall population.  Most researchers prefer parametric statistic when possible because they are more powerful and more flexible.

Nonparametric  Not based on the estimation of population parameters; usually applied when variable measured on a nominal or ordinal scale, or distribution of scores is severely skewed.

Most Commonly Used Inferential Statistics  Parametric  t statistic-commonly used in nursing research, tests whether 2 group means are different.  ANOVA  ANCOVA  Nonparametric  Chi-square- used when data is at the nominal level, determine difference between groups. Robust and used with small samples.  Fisher’s exact probability.

Tests of Relationships  Interested in exploring the relationship between 2 or more variables.  Studies would use statistics to determine the correlation or degree of association between 2 or more variables.  Pearson r, the sign test, the Wilcoxon matched pairs, signed rank test and multiple regression.