Module 8 Flashcards
(16 cards)
What is archival research?
Archival research is research based on archival data.
The term ‘archival’ might evoke an old, dusty library vibe.
Back in the ’80s and ’90s, this was indeed how business students collected archival data for their theses: by wading through real archives, photocopying the pages with the data they needed, and then punching them into Excel.
Nowadays, fortunately, most archival data are digitalized.
What is Internal archival data ?
Archival research relies on internal or external archival data.
Internal archival data are generated within the company that conducts the research.
An example:
A research team employed by Unilever would like to understand to what extent Unilever’s advertising expenditures for their brands are related to their brand sales. To answer this question, the research team uses Unilever’s sales and advertising data for 400+ brands – data that are available within the company.
External archival data ?
External archival data are data that are generated by sources outside a company, and that are not exclusively available to the company but can be used by anyone. Some archival data are publicly available, which means that they are available for free for the entire world to use. Other archival data are commercially available, which means that one has to pay to use them.
The number of commercially available archival datasets is countless. The university’s library contains a wealth of such datasets
When is archival research used?
When is archival research a suitable research strategy?
When you want to learn from past successes/failures in the industry (by tapping into industry wisdom).
When you want to know whether/how an effect changes over time.
When you want to know whether/how an effect is different across countries.
When you want to examine socially sensitive phenomena unobtrusively.
Piecing together archival data
Since archival data have not been collected for the purpose of your research study, it is highly unlikely that all the data that you need for your study have been collected in a single data set.
Often, you need to piece together multiple archival data sets into one new data set that you can subsequently use to address your research questions.
In piecing together different archival datasets, you have to make sure (as always) that your unit of analysis corresponds.
essentially, Various archival datasets can be pieced together into in a single dataset that can be analysed to answer one’s research questions.
Longitudinal data :
Unlike other data sources, archival data can be (and often are) collected over time. These data are longitudinal (rather than cross-sectional, which means at one point in time) in nature. This makes the data ideal if the nature of your research is to examine changes over time.
Archival data are often longitudinal.
Three sources of measurement unreliability in Archival data
unreliability may plague any type of research, but are particularly common in archival research.
These are:
Missing data
Inaccurately recorded data
Fake data
SOLUTIONS for Archival data unreliability
- Listwise deletion
But: check user manual!
If missing = “close to 0”,
then recode missing to 0 (e.g., Compustat: R&D, ADV) - Mean-substitution
Replace missing value
for observation i and variable j with
average value on variable j for all other observations - or Interpolation
single-item measures that capture very concrete constructs. examples
Many of the measurement instruments used in archival research are single-item measures that capture very concrete constructs.
Examples include stock returns, shareholder value, firm profitability, sales, and R&D expenditures.
multi-item measurement instruments in Archival research
most times single item measures ,
However, sometimes multi-item measurement instruments can be desirable in an archival research study.
This is the case when you need to measure a less concrete conceptual variable for which multiple potential measures exist.
For example, suppose you would like to investigate if firms become more profitable when they grow larger. How would you measure the variable firm size?
Multiple potential measures exist (and all of them have been used in prior research):
-The firm’s sales (logic: larger firms have more sales)
-The firm’s number of employees (logic: larger firms employ more people)
-The market value of the firm (logic: larger firms have a higher market value)
Which of these three measures will you choose to measure the conceptual variable firm size? If there is no good reason why one measure would be better than another, you can of course arbitrarily pick one of the three measures and continue with your research.
Alternatively, you can create a COMPOSITE measure that combines all three measures, provided that they have a high Cronbach’s alpha
(that is, they should be interrelated as you consider them indicators of the same underlying construct).
How you can combine multiple measures (also referred to as items or indicators) into a single composite measure when simple averaging is not possible because the items are measured on different scales and/or have a different range.
Combining multiple archival indicators
into a single measure:
1. Standardize each indicator
2. Average the standardized indicators
how measurement validity can be assessed and demonstrated in archival research
Provide precedence
Provide sound logic to support that considerable conceptual overlap exists between construct and measure
Provide evidence of a substantial correlation between your proxy and a valid survey measure for a small subsample of your data
Provide evidence of substantial correlations (r> .3) with related constructs (“nomological validity”)
Internal validity in archival research
Internal validity is the extent to which a study can rule out alternative explanations. To establish a valid relationship between variables (e.g., between X and Y), a researcher needs to limit the influence of extraneous/confounding variables. The less chance there is for “confounding” in a study, the higher the internal validity, and the more confident you can be in the study’s findings.
Internal validity in archival research
So how can you improve the internal validity of archival research?
By including control variables in your analysis!
By including control variables, you can “filter out” or “isolate” the control variables’ effects from the relationship between the variables of interest.
External validity in archival research
External validity (also known as generalizability) is important in archival research. You cannot assume that someone else took care of the external validity because your data have been collected by someone else.
You must always look up how the archival data were collected (e.g., what population was the data collected from?).
for this external validity to hold Results need to be generalizable
Litewise or Mean subsitution or interpolation
This is a cross-sectional data set. For cross-sectional data, you can use either listwise deletion or mean substitution (or a combination of both). Since the number of missing values is limited, it is better to use mean substitution as this allows you to keep your sample size to the full sample size.
when limited data You should be reluctant to throw out data points. Since the number of missing values in this example is limited, it is better to use mean substitution so you can use the information on all 100 companies in your analysis.
Mean substitution is not a good idea for longitudinal data. For longitudinal data, it is best to replace missing values through interpolation
