click below
click below
Normal Size Small Size show me how
mgmt212
marketing research
Question | Answer |
---|---|
categorical/classicatory | limited number of distinct values i.e. gender, SES, colour, size, eta |
Continuous | infinite number of distinct values i.e. sales, length, weight |
Dependent variable | variable that is to be predicted or explained - influenced by the independent variable |
independent variable | variable that is expected to influence the dependent variable - can be manipulated by researcher, or be naturally occurring groups |
exploratory research | typically used to provide structure and insight into the research problem. |
conclusive research | test specific hypotheses, examine specific relationships, make predictions, can be descriptive or causal |
descriptive research | (conclusive research) used to describe something, usually market characteristics or functions. i.e. determining the average age of purchasers of your product |
causal research | (conclusive research) used to obtain evidence regarding cause-and-effect relationships. i.e. determining if increased advertising spending has led to an increase in sales |
secondary research benefits | low cost, less effort, less time, at times, the only way to obtain data |
secondary research limitations | collected for some other purpose, no control over data collection, may not be accurate, may be outdated, may need to make assumptions |
survey research | systematic collection of information directly from respondents |
survey research advantages | large sample sizes easy - increases generalisability of results, ease of administering and recording answers, allows advanced statistical analyses, ability to tap into factors and relationships that can't be directly observed |
survey research disadvantages | can take a long time, low-response rates, hard to know if respondents are being truthful, subjectivity when interpreting data |
experimental research | the researcher manipulates one or more variables in such a way that its effect on one or more other variables can be measured |
laboratory experiments | where the treatment manipulation is introduced in an artificial setting. High in internal validity and low in external valdity |
field experiments | where the treatment manipulation is introduced in a completely natural setting (e.g. test market). High in external validity but low in internal validity |
measurement | the assignment of numbers or other symbols to characteristics of objects according to certain pre-specified rules |
scaling | an extension of measurement; involves the generation of a continuum upon which measured objects are located |
operational definitions | specifications of exactly what steps, or operations are conducted to arrive at a particular measurement |
Why is the level of scale measurement important? | determines what info is obtained, which statistical analysis you can use |
comparative scales | a direct comparison of stimulus objects is elicited. e.g. two brands may be compared along a dimension such as quality |
non-comparative scales | only one object is evaluated at a time, the respondent provides whatever standard seems appropriate; e.g. one brand is rated on a scale independent of other brands |
reliability | extent to which a scale produces consistent results if repeated measurements are made on the characteristic; the scale is free from random error |
validity | differences in observed scale scores reflect true differences among objects on the characteristic being measured, rather than systematic or random errors. Refers to the accuracy of the measurement |
population | complete set of observations about which an investigator wishes to draw conclusions. defined by the interest of the investigator and in terms of observations rather than people |
sample | part of the population, also defined in terms of observations |
census | measurement of all members of the population |
determine sample frame | list of all eligible sampling units from which the sample will be drawn (e.g. telephone directories, electoral registers, company lists, club membership lists, etc.) |
sample frame error | failure to account for the entire population |
probability samples | sampling units are selected by chance and for which there is a known chance of each unit being selected |
non-probability samples | chance selected procedures are not used |
simple random sample | each unit has an identical chance of selection, using blind draw or a table of random numbers |
systematic sample | the sample is drawn by selecting a random starting point and selecting every xth element in succession |
stratified sample | the target population is divided mutually exclusive and collectively exhaustive sub-populations or strata - a random sample is taken from each strata |
convenience sample | only criterion for selecting the sampling units is the convenience of the sampler (non-probability) |
judgement sample | an attempt is made to draw a sample of the population using an educated guess - useful if broad population inferences are not required (non-probability) |
referral (snowball) sample | participants provide names of other potential sample units - characteristics will be similar to the person referring (non-probability) |
quota sample | demographic characteristics of interest are int he same proportion as they are in the population - the sample elements are selected based on convenience or judgement (non-probability) |
purposive sample | chosen to achieve some objective, such as heavy users, frequent viewers, small population sub-samples (non-probability) |
research question | determining what information is needed and how it can be obtained in the most feasible way (are interrogative) |
hypothesis | an unproven statement or proposition about a factor or phenomenon that is of interest to the researcher. statements of relationships rather than questions to which answers are sought (Are declarative and can be tested empirically) |
null hypothesis | a statement in which no difference or effect is expected. if accepted (i.e. not rejected) no changes in opinions or actions will be made |
alternative hypothesis | a statement that some difference or effect is expected. accepting will lead to changes in opinions or actions |
mean advantages | easy to understand, simple to calculate, deals with all the data, can be determined exactly, possesses mathematical properties that can be used as the basis for further analysis |
mean disadvantages | may not be truly representative, may give undue weight to items with extremely high or low values |
median advantages | easy to understand, not affected by extreme items, can be obtained even when the values of some items are not known |
median disadvantages | data must be arrayed in order of size, with few items it's unlikely to be representative of the data set, not useful for further analysis, limited use in practical work |
mode advantages | easy to understand, not affected by extreme values, can be instantly identified from data distribution, is the most descriptive average (For some data sets) |
mode disadvantages | possibly not representative if there are only a few items, can't be used for further arithmetic manipulation, sometimes data set contains two or more of this measure of central location |
range | represents the maximum breadth of a data set, crudest measure of dispersion, ignores all other values in the data set, of limited use when exceptionally low and/or high values are present |
error | leftover variation that cannot be explained by any of the other sources |
variation | the sum of squares of the deviations of the values from the mean of those values; can come from different sources such as the model or factor, occurs anytime that all of the data values are not identical |
variance | the difference of each item from the mean is squared, these squared differences are added together, and the result is then divided by the number of items |
standard deviation | the square root of the variance |