Home | Student thesis | Research | Staff | Consultancy


Statistics theories and methods provide valuable information for decision makers and researchers. The Statistic Unit of Dalarna University is a group of statisticians including professors, lecturers and Ph.D students. We have extensive experience in data analysis, forecasting, hypothesis testing, sample size estimation, dissertation proposal and data interpretation. Our consultancy work would help you facilitate a reliable understanding of statistical concepts and procedures in your work and research.

Why are we interested in consulting

-we want to be involved in applied research

-a way to get contacts with the society and industries out side the university

-part of the education for PhD students

Three Possible Categories for Consultancy

1 Reasearch involving statistician as co-author. Usually involves projects >40h

2 Pure consulting within the university. Usually involves projects 8-40h

3 Contract research outside university

Contact person:

Moudud Alam

Email:maa@du.se

Example projects
1. Road Barrier Repair Costs and Influencing Factors

This paper presents a study that examines repair costs for different road barrier types and factors that influence these costs. The analyses focused on w-beam and cable barriers used as median barriers. To some extent, pipe barriers, Kohlswa-beam barriers, and concrete barriers were also studied. The influencing factors included in this study were road type, speed limit, barrier type, and seasonal effects. A case study was conducted in four regions of the Swedish Road Administration. Data were collected from 1,625 barrier repairs carried out during 2005 and 2006. The results show that the number of barrier repairs and the average repair cost per vehicle kilometer are higher along collision-free roads than along motorways and 4-lane roads. The results also show that the number of barrier repairs and the average repair cost per vehicle kilometer are higher for cable barrier than for other barrier types. No conclusion can be drawn regarding influence of speed limits on barrier repairs and associated costs as the result from the regions are divergent and not statistically significant

Full Paper

2. Quality control of waste to incineration – waste composition analysis in Lidköping, Sweden

In order to decrease environmental impacts in waste management the choice of treatment method must be based on the characteristics of the waste. Present sampling procedures do not provide statistically representative samples of solid waste and this provides difficulties in characterization. The objective of this study was to develop a procedure for waste component analysis and sampling of waste after collection and at plant level. A further objective was to characterize the waste delivered to an incineration plant for physical and chemical properties and to determine the amounts of delivered waste that could be classified as biofuels and fossil fuels. The proportions of recyclables and hazardous waste were also examined.

Full Paper

3. Dödlighet efter hjärtinfarkt har minskat i nästan alla landsting under 1990-taletjan

Störst förbättringar i de landsting som hade sämst resultat från början

Sverige tillhör de länder i världen som har lägst dödlighet efter hjärtinfarkt. En kraftig minskning av denna dödlighet har dessutom skett under 1990-talet. År 1987 var den åldersstandardiserade dödligheten inom 28 dagar i åldrarna 30–89 år 47 procent för männen och 44 procent för kvinnorna. Motsvarande siffror var år 1999 37 respektive 34 procent. Resultaten i denna artikel tyder på att dödligheten efter hjärtinfarkt har minskat för båda könen i nästan samtliga landsting under perioden 1992–1999. Siffrorna varierar mellan sjukvårdshuvudmännen vilket bör föranleda närmare analyser.

Full Paper

What is statistics

Data feature

-Data are qualitative or quantitative attributes of a variable or set of variables. Data are typically the results of measurements and can be the basis of graphs, images, or observations of a set of variables. Data are often viewed as the lowest level of abstraction from which information and then knowledge are derived. Raw data refers to a collection of numbers, characters, images or other outputs from devices that collect information to convert physical quantities into symbols.

Forecasting

-Forecasting can be broadly considered as a method or a technique for estimating many future aspects of a business or other operation. There are numerous techniques that can be used to accomplish the goal of forecasting.

Business modeling

-In theory and practice the term business model is used for a broad range of informal and formal descriptions to represent core aspects of a business, including purpose, offerings, strategies, infrastructure, organizational structures, trading practices, and operational processes and policies. Hence, it gives a complete picture of an organization from a high-level perspective.

Research modeling

-A common usage for a statistical research modeling is to investigate causality, and in particular to draw a conclusion on the effect of changes in the values of predictors on dependent variables or response. Statistical modeling is applied lot of fields, e.g., financial economics, biology, time series econometrics, spatial data.



Visitor's Address
Statistics
School of Technology and Business Studies
Dalarna University
781 70 Borlänge
Sweden
http://www.du.se


Post Address
Statistik
Akademin Industri och samhälle
Högskolan Dalarna
791 88 Falun
Sweden
+46-(0)23-77 80 00


Copyright © 2012 Statistics Unit