1-1 Overview
● Data are observations (such as measurements, genders, survey responses) that have been
collected
● Statistics is a collection of methods for planning experiments, obtaining data, and then
organizing, summarizing, analyzing, interpreting, presenting, and drawing conclusions
based on the data
● Apopulation is the complete collection of all elements (scores, people, measurements,
and so on) to be studied; collection is complete in the sense that it includes all subjects to
be studied
● Census is collection of data from every member of population
● Sample is subcollection of members selected from part of population
○ must be collected in appropriate ways; if it isn’t, data may be completely useless
1-2 Types of Data
● Parameter is measurement describing some characteristics of populations
● Statistic is measurement describing some characteristic of sample
● Quantitative data consists of numbers representing counts or measurements
○ Discrete data: number of possible values either finite number or countable number
○ Continuous data: infinitely many possible values that correspond to some
continuous scale that covers a range of values w/o gaps
● Qualitative (or categorical or attribute) data can be separated into different categories that
are distinguished by some non-numeric characteristic
● Common way of classifying data is to use four levels of measurement: nominal, ordinal,
interval, and ratio:
○ Nominal measurements characterized by data consisting of names, labels or
categories
■ should not be used for calculations as they lack any ordering or numerical
significance
○ Ordinal data can be arranged in some order but differences between values are
meaningless or cannot be determined
■ provides information about relative comparisons but not magnitudes of
differences
○ Interval is like ordinal but the difference between data values is meaningful;
however, data at this level don’t have natural zero starting point (where none of
quantity present)
○ Ratio is same as interval but there is also natural zero starting point; differences
and ratios are both meaningful
■ called ratio because zero starting point makes ratios meaningful
1-3 Design of Experiments
● Voluntary response sample (or self-selected sample) is where respondents themselves
decide whether to be included
○ often happens that people with strong interests or opinions more likely to
participate thus responses not representative
○ valid conclusions can only be made about specific group of people who chose to
participate; should be used for making general statements
● Statistical methods driven by data, which is obtained from two sources: observational
studies and experiments ● Observational Study: observe and measure specific characteristics but don’t attempt to
modify subjects being studied
○ cross-sectional study: data measured at one point in time
○ retrospective (case-control) study: go back in time to collect data
○ prospective (longitudinal or cohort) study: go forward in time and observe groups
sharing common factors such as smokers and nonsmokers
● Experiment: apply some treatment and proceed to observe it’s effects of subjects

More
Less